Sometimes you have to be more than super to be No. 1. For four decades, Sikorsky’s CH-53E Super Stallion ruled the American sky as the nation’s largest and most powerful helicopter. But the next-generation version of the chopper, the CH-53K King Stallion, is now champing at the bit.

Lockheed Martin’s Sikorsky Aircraft unit is building the new helicopter for the U.S. Marines. It’s powered by a brand-new engine from GE Aviation that will allow the King Stallion to claim the top spot. Lat week, the U.S. Naval Air Systems Command awarded the company a contract to build 22 of the engines valued at $143 million.

The Marine Corps have plans to buy 200 King Stallions through the program. Each of the helicopters will be using three engines.

Top and above: The King Stallion sports fourth-generation rotor blades with anhedral, or drooped, tips that make it more quiet. Images credit: Lockheed Martin.

GE spent a decade building the new T408 engine. It will allow the CH-53K to carry as much as 27,000 pounds of external load — some 27 real-life stallions — over a mission radius of 110 nautical miles in hot-weather conditions, nearly triple what its predecessor could manage. At 7,378 shaft horsepower, the new engine will provide 57 percent more power and use 18 percent less fuel, compared to the engines used by  the Super Stallion. The new engine also has 63 percent fewer parts, making maintenance easier.

CH-53K will be able to carry as much as 27,000 pounds of external load, nearly triple what its predecessor could manage. Image credit: GE Aviation

GE Aviation is scheduled to deliver the 22 engines to Sikorsky through 2018. But the company is developing new technology so fast it is already thinking about future improvements. One of them includes parts made from a new supermaterial called ceramic matrix composites (CMCs), which were originally developed for gas turbines by scientists at GE Power and GE Global Research. Potential upgrades also include 3D-printed parts. The first jet engines with 3D-printed parts from GE entered service last year.

The new helicopter will have fly-by-wire flight controls, fourth-generation rotor blades with anhedral — or drooped — tips that make the machine quieter, and other new technology.

In the spring of 2016, 32-year-old Nicole Gularte grew weak and lost her ability to see colors from her left eye. She knew that her leukemia had returned.

Gularte’s form of the disease was called acute lymphoblastic leukemia, or ALL. She had been in an exhausting on-and-off battle with cancer for six years, and she was desperate to avoid yet another debilitating round of chemotherapy. She wasn’t particularly thrilled when doctors told her they had gotten lucky and found two nearly perfect bone marrow matches. Long-term studies have shown that nearly half of leukemia patients who receive a bone marrow transplant die or relapse within two years.

The story of what she did next offers a fascinating look into the future of cancer treatment. She rejected the transplant and opted to let the relapse of her ALL take full hold. That allowed her to enroll in a clinical trial of a promising new cancer treatment called CAR T-cell therapy that was run by the University of Pennsylvania and Children’s Hospital of Philadelphia. “I called UPenn,” Gularte says. She made her circumstances clear to the doctors, telling them: “I’ve given up a 10-out-of-10 bone marrow transplant so I can relapse so I can qualify for your CAR-T trial.”

In cell therapy, doctors remove some of a patient’s T-cells, the immune cells that fight against infection, reprogram them to fight and kill cancer, then put them back into the patient. Developed by doctors at Children’s Hospital of Philadelphia, the treatment gained prominence after it saved a young girl named Emily Whitehead in 2012. It’s had a 93 percent success rate in trials with patients with advanced leukemia, but it’s still a very new type of therapy. A refined version of the treatment that saved Whitehead, now called Kymriah and made by Novartis, was the first CAR T-cell therapy approved by the FDA, which in August cleared it for use in children. In October, the FDA approved a second version of CAR T-cell therapy, called Yescarta and made by Kite, to treat b-cell lymphoma for adults.

Gularte next to University of Pennsylvania’s Dr. Carl June, a leading cancer researcher. Image credit: Nicole Gularte.

Most other, similar versions of the treatments are still in the testing phase. But this new form of treatment is a welcome alternative to patients who, like Gularte, find chemo dismaying and bone-marrow transplants too uncertain. “I realized that if there was a chance of something better out there, I needed to research it and come up with my own decision,” Gularte says.

The University of Pennsylvania’s adult cell therapy trials proceeded haltingly until they gained momentum in 2016, just in time for Gularte. She gained admittance to the program, and on September 7, she received her modified T-cells. Doctors had previously removed them from her body, modified them with a virus to recognize her cancer, multiplied them and transfused them back into her body.

She spent the next few days wracked with 105.8 degrees Fahrenheit fever and suffering from several seizure-like episodes as the T-cells started fighting her disease. But her temperature soon lowered, and, on the tenth day, something surprising happened. Her eyesight, which had deteriorated during her fight with leukemia, returned.

“I was half blind in one eye, and totally color blind,” she recalls. “Then, while I was watching TV, I noticed that the girls on the screen had bright green skirts.” When she had her color vision tested, she scored 13 out of 15. Soon, her T-cell levels, which plummet when leukemia patients are battling the disease, returned to normal. She was released from the hospital.

A year later, Gularte’s T-cell activity is elevated, but she is still in remission. She’s become a passionate advocate for CAR T-cell therapy. The University of Pennsylvania’s cell therapy trial is one of more than 800 studies in gene and cell therapy currently underway globally. And based on the 80 percent complete remission rates of these trials, experts anticipate that cell therapy is poised to become a major means for fighting cancer.

Top: In 2016, Nicole Gularte entered a cell therapy trial run by the University of Pennsylvania and Children’s Hospital of Philadelphia with the hopes of fighting her acute lymphoblastic leukemia. It worked, and today her cancer is still in remission. Image credit: Nicole Gularte. Above: GE scientists and others are working to accelerate the manufacturing processes of such cell therapies at the Center for Advanced Therapeutic Cell Technologies in Toronto. Image credit: CCRM.

Tens of thousands of patients per year could be receiving the treatment by 2024, and by 2030, the cell therapy industry is expected to be worth an estimated $30 billion.

While these emerging therapies bring new hope, the process to manufacture them can be lengthy and expensive, and producing enough to meet potential demand is challenging. “Now we need to help make cell therapy affordable and scalable,” says Phil Vanek, general manager for cell therapy growth strategy at GE Healthcare Life Sciences.

GE’s cell therapy business and others are racing to provide technology and processes to make that happen. In collaboration with Center for Commercialization of Regenerative Medicine (CCRM) and the Federal Economic Development Agency for Southern Ontario, they’ve embraced a new cell therapy research and process-development facility called the Center for Advanced Therapeutic Cell Technologies, which officially opened this September in Toronto. Designed to help pharma companies, university researchers, startups and technology companies scale up manufacturing faster, the new center already employs a team of more than 30 biologists, virologists, and biomedical and other engineers, from both GE and CCRM.

“We’re transitioning into the future,” says Gularte. “It’s not just about traditional drug discovery anymore, it’s now about the innovative life sciences industry, and the ways that doctors are learning to work with the body. Cell therapy could potentially eradicate many diseases. I wanted to be part of that.”

Study after study has shown that detecting breast cancer early can dramatically improve the chance of healing and survival¹. “Mammography has been proven to reduce mortality by 20 percent²,” says Claire Goodliffe, marketing director for women’s health at GE Healthcare. But another, less promising set of statistics haunts Goodliffe: As many as 40 percent of women in Europe and 30 percent in the U.S. skip screening³. “They are afraid,” Goodliffe says. “They are afraid of the examination, they are afraid of the pain they may feel, and they are afraid of the results. They are afraid of getting cancer.”

That’s why Goodliffe and her colleagues at GE Healthcare’s campus in Buc, just outside of Paris, set out on a quest to design a mammography machine that wouldn’t scare people. “My design philosophy is to mix science with empathy,” says industrial designer Aurelie Boudier, who joined Goodliffe on the project. “We wanted to build a machine that changed the subjective perception of the mammogram and spoke to the woman to make her feel reassured.” Adds Goodliffe: “We wanted to humanize the examination.”

The project was unusual because like Goodliffe and Boudier, many of the engineers, designers and managers involved in building and manufacturing the machine were women. “We wanted to put the woman at the heart of the project,” says Laura Hernandez, global product manager for the Senographe Pristina, as the machine is called. “This is engineering by women for women.”

This week, Hernandez, and Pristina, are visiting the annual meeting of the Radiological Society of North America (RSNA), the world’s largest gathering for radiologists and other medical professionals.

Top image: Laura Hernandez (left), Claire Goodliffe (middle) and Aurelie Boudier helped develop GE’s new mammography scanner, Pristina (above). “This is engineering by women for women,” Hernandez says. Images credit: GE Healthcare.

Mammography has been around since the 1960s, when French engineers Jean Bens and Emile Gabbay developed a breast-dedicated X-ray machine with a special X-ray tube that emitted low-energy radiation and still allowed doctors to see breast tissue in greater detail. They called their machine the Senographe and brought it to market in 1966. GE Healthcare, which acquired Bens and Gabbay’s company in 1987, has been making mammography systems ever since.

But some three decades later, Goodliffe and her colleagues sensed the mammography needed more than a technology upgrade to break down the emotional barriers that kept women from getting mammograms.

They started by gathering insights from over 1,200 doctors, technicians and patients and 25 clinics. One recurring issue was discomfort tied to the design of the screening systems. During the exam, women place their breasts on a platform the size of a laptop called the bucky, stretch out their arms and support themselves by holding onto handles located on the body of the machine. Older machines typically have angular, metallic buckies that can feel cold and painful. “My reaction [during an exam] is that I want to step back,” says Hernandez, echoing many of the patients the team surveyed.

The world’s first mammography machine was developed by Jean Bens and Emile Gabbay in the 1960s. Image credit: GE Healthcare.

Doctors, on the other hand, wanted to do away with the handles because grasping them caused patients to flex their pectoral muscles and tense up during the exam. “They wanted the women to relax,” Boudier says.

She took the survey findings and started building a mock-up of a new machine in the design lab at Buc. Fanny Patoureaux from the engineering team then brought Boudier’s design to life, fitting inside the machine’s sleek body advanced imaging technology that allows doctors to see the breast in 2D and 3D slices and “read it like a book.” One application even helps them build a “synthetic view” of the breast inside a computer and then use deep learning algorithms to help physicians pinpoint suspicious areas. “We needed to blend all of this high technology with design features that conveyed emotional benefits,” Patoureaux says.

It was a challenge, she admits, but working closely with Boudier allowed the team to “chip away at the anxiety women experience during a mammography exam while providing pristine image quality for accurate diagnoses.”

Another key consideration was manufacturing, since the design also had to be easy to produce. “We were involved very early in the process,” says Beatrice Martin, who now runs the Pristina production line in Buc. Borrowing from GE’s “brilliant factory” principles, she and her team were able to reduce the assembly time by half, compared to previous systems.

The manufacturing floor at GE Healthcare in Buc, France. Using “brilliant factory” principles, the production team led by Beatrice Martin was able to reduce assembly time by half. Image credit: GE Healthcare.

As they moved along, the team invited groups of women to test Boudier’s prototypes and provide more feedback. The final design has a thin, black bucky with smooth round edges made from a carbon fiber composite. The material provides a warm surface “so women won’t move during the exam,” Hernandez says. “We have also designed a new remote control so women can compress their breast with the aid of a technician, a first in the industry.”

Boudier also replaced the handles with armrests and LED lights that encourage women to relax during the exam. “It’s almost spa-like,” Hernandez says.

The main pillar of the machine, which holds the X-ray source, features flowing, overlapping plastic folds meant to symbolize a shawl. Its concave shape allows patients to rest their head against it. “From the beginning, I kept in mind a woman who is feeling anxious and wraps a cover over her shoulders to feel safe,” Boudier says. “I wanted to express that feminine gesture and keep it a metaphor for our design approach.”

Pristina is now available in most parts of the world, and some customers, like the Gustave Roussy Cancer Center in Paris, have fuchsia-painted Pristina rooms where soothing music plays in the background. The latest design for the scanner now also offers an option for hospitals to hide much of the support structure in a wall and blend it with the surroundings.

Last December, Goodliffe went to get her own Pristina mammogram at a clinic in central Paris. “I wanted to feel what other women were going through,” she says. When she arrived at the appointment with her small daughter, the girl wanted to know why her mother was so interested in the machine. “Well, you know, what I do,” Goodliffe said. “I help women take care of their boobies.”

¹ Van Schoor G, Moss SM, Otten JD, et al. Increasingly strong reduction in breast cancer mortality due to screening. Br J Cancer 104:910-914, 2011.
² Marmot MG, Altman DG, Cameron DA, Dewar JA, Thompson SG, Wilcox M. The benefits and harms of breast cancer screening: an independent review. Br J Cancer. 2013;108(11):2205-2240. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3693450/
³ Breast Cancer Screening Programs in 26 ICSN Countries, 2012: Organization, Policies, and Program Reach. National Cancer Institute.

Hospitals can feel pain, too, and computer scientist Karley Yoder is using artificial intelligence to treat it.

Yoder and her colleagues at GE Healthcare are working on apps that enable healthcare providers to analyze the reams of data their facilities generate, quickly diagnose problems and propose treatment. “Hospital operators know in their gut about problems, but they can’t quantify them,” Yoder says. “We give them the tools to identify and resolve those pain points.”

Yoder is spending this week in Chicago at the annual meeting of the Radiological Society of North America (RSNA), the world’s largest gathering for radiologists and other medical professionals. She and her team arrived with a new app that could make chest X-ray imaging more efficient.

X-rays represent more than half of all medical scans, and chest X-rays account for 50 percent of that volume.

Chest X-rays also leave a lot of room for error, Yoder says. She and her team have been searching for the root causes that can lead to bad scans and require the re-scanning of patients. “If you are a clinician taking an X-ray and your patient moves or you have a setting on your machine that inadvertently overexposes the image, you have to repeat the X-ray,” she says. “This exposes the patient to more radiation, slows down the patient flow and also adds extra paperwork because hospitals in the U.S. must report these instances to regulators.” These reports can take a day or more to compile, she says.

The app Yoder and her team developed takes care of the reporting automatically and also allows hospital managers to quickly spot problems. “It automatically pulls all of the information about rejected and repeated X-ray images into a one-page dashboard on the desktop that’s easy to review,” she says. “Administrators can drill in and see if there is a problem with a specific machine or a technician maybe needs more training. Once you quantify and identify the problem, you can quickly deploy a solution and move on.”

GE has been in the medical imaging business for more than a century. Above is an antique X-ray machine inside a GE Healthcare complex in Buc, France. Top: X-rays represent more than half of all medical scans. Images credit: GE Healthcare.

Yoder works in San Ramon, California, GE’s digital headquarters, but writing smart code is only one part of her job. The other is to make sure that healthcare practitioners won’t even notice the application running on their machines. “It’s like Netflix,” she says. “If you had to go to another application or open a new screen to get your movie recommendations, I doubt you’d use it.” She says that “there is always skepticism with new technology. We have to deliver it in a seamless way into the existing workflow.” She says that several GE Healthcare X-ray machines can already run the app and “the list is growing.”

The first iteration of the app will help hospitals reduce patient exposure to radiation, keep bureaucracy at bay, save time and make their radiology departments more efficient. But future iterations of the app or other similar advanced analytics technology may give technicians suggestions and maybe even help doctors with diagnoses. “When I think about deep learning in the healthcare space, I really think about it in three steps,” Yoder says. “We need to build the deep learning model and make sure it does what we want it to do. Next, we need to turn it into a product and deploy it. The third part is where the AI works and it gets really exciting because it allows me to work with the data and refine the model.”

Yoder says that one day artificial intelligence technology could help doctors send patients to the right specialists faster. It could also help them prioritize patients. “The machine can send them an alert: ‘Hey, take a look at this,’ ” she says. “I think that we are going to start seeing systems like this in many places in the healthcare field.”

And beyond, as well. Yoder’s colleagues in San Ramon work on smart software for aviation, energy and other industries where GE is active. She recently discussed her work with an engineer who suggested a possible use of the app in the oil-and-gas field, which is using industrial-grade X-ray machines to image parts for pipelines and other components. “We are very early in these conversations, but it’s the same technology,” she says. “But if you can scan hundreds of images and use an app to identify conditions like pneumothorax, you can probably use it to find a problem with your pipeline.”

When Ana Paula Silveira got pregnant, she and her husband, Alvaro Zermiani, dreamed about seeing the face of their child during her first ultrasound exam. But weeks later, they got to feel it instead.

Both Ana Paula and Alvaro, who live in São Paulo, Brazil, are legally blind. Their son, Davi Lucas, was strong and healthy, but there was no way their eyes could see the first grainy glimpses of their baby on the ultrasound monitor.

They decided to take a different path. The couple made a trip to the office of Dr. Heron Werner, a gynecologist and obstetrician working at the DASA clinic in Rio de Janeiro. He agreed to follow Ana Paula through her pregnancy.

Dr. Werner uses a 3D printer to make lifelike models from images obtained by a GE ultrasound machine. “From the moment we got to the high-quality ultrasound exam, through the possibility of 3D printing it, I realized that it could also serve to enhance the prenatal experience of visually impaired pregnant women,” Dr. Werner says.

Ana Paula agrees. “Holding the small fetus at 12 weeks is an indescribable feeling,” she says. “Following up on our son’s evolution allowed us to have this feeling of being whole, because we feel with our hands.”

Top image: “When we touched the second model, with Davi’s face, we realized his resemblance to us,” Ana Paula says. Above: Ana Paula and Alvaro with Dr. Werner (left) in his office in Rio. Images credit: Ana Paula and Alvaro Zermiani.

Dr. Werner got the idea for 3D printing babies during a visit to Rio’s National Museum, which was then using a tomography machine to digitize its ancient Egyptian exhibits. “We thought, why not use [medical imaging technology] for printing fetus models,” he says.

Ana Paula says that being able to hold a printed model of her son was a great gift. “When we touched the second model, with Davi’s face, we realized his resemblance to us,” she says. “Thanks to the exams and printing, we were able to not only know that our baby was growing healthy but also to have a very real contact and establish a very strong involvement with our son.”

The ultrasound machine, called Voluson E10, is also the first ultrasound system in the OB/GYN field with built-in 3D-printing capability. Doctors can use it to help parents better understand congenital defects such as cleft lips, abnormal extremities or abdominal wall defects. In some cases, 3D printing can enhance discussions about surgical planning and serve as an educational tool.

A real-time ultrasound GIF of a baby’s face taken by the GE’s Voluson 10 machine. Image credit: GE Healthcare

When Dr. Lawrence Platt started his career as an obstetrician and gynecologist 40 years ago, he was fascinated by ultrasound technology. Each time he scanned a patient, he created a grainy black-and-white image of the baby, then drew a picture on top of the ultrasound to help the parents-to-be understand what they were seeing. “For me, an ultrasound is like the Lay’s commercial: I bet you can’t scan just one,” he says.

He certainly doesn’t. Dr. Platt, who calls his work a “labor of love,” cares for mothers and infants during high-risk pregnancies at the Center for Fetal Medicine & Women’s Ultrasound in Los Angeles. He treats women for a variety of pregnancy complications due to pre-existing maternal medical conditions or obstetrical issues, with a focus on using ultrasound in fetal assessment.

The Center for Fetal Medicine serves about 10,000 patients every year for ultrasound and prenatal diagnosis, genetic counseling and high-risk obstetrical consultation. Dr. Platt recently has been using the latest version of GE’s Voluson E10 ultrasound machine to improve imaging for his patients. “When you want to get a higher quality and get as much information as you can possibly can, we go to the E10,” he says. “It’s a very powerful tool that comes with improved diagnostic capabilities for improved care of the patient.”

The Voluson E10, is also the first ultrasound system in the OB/GYN field with built-in 3D-printing capability. Doctors can use it to help parents better understand congenital defects such as cleft lips, abnormal extremities or abdominal wall defects. In some cases, 3D printing can enhance discussions about surgical planning and serve as an educational tool.

GE Healthcare brought the machine to the annual meeting of the Radiological Society of North America (RSNA), the world’s largest gathering for radiologists and other medical professionals, which is taking place this week in Chicago.

Above: The fetus at 12 weeks. Top image: The fetus at 38 weeks. Images credit: GE Healthcare.

The system gives Dr. Platt better views of the cardiovascular system, the heart, as well as other fetal organ structures. The key to the clear images are 2D imaging transducers — the “wands” doctors pass over pregnant women’s bellies. “It provides unbelievable imaging in the first, second and third trimesters,” he says.

Clearer images allow him to see “subtle changes in the fetus,” he says. “If you identify those things earlier, it gives us more options to do something about it.”

Dr. Platt also uses the ultrasound system for gynecological studies, including imaging masses, ovaries, cysts and cancers. “This system is giving the patient their best shot,” he says. “It allows a clinician to integrate their clinical care with the most advanced imaging to make a proper diagnosis. Because we want the best for everybody, don’t we?”

The fetus at 14 weeks. Image credit: GE Healthcare.

After four decades, he has seen thousands of patients and performed thousands of ultrasounds in his practice. The days of drawing on his fuzzy ultrasound pictures are long gone. “Now I use ultrasound to show patients what my drawings are,” he says with a laugh.

Former patients often return with their adult daughters who are pregnant and starting families of their own. “These patients bring in the black-and-white 2D ultrasound pictures that I gave them 30 or 40 years ago,” he says. “I love to show them the new generation of ultrasound; it’s just remarkable.”

GE also benefits from the partnership. Peter Falkensammer, product manager for GE’s Women’s Health Ultrasound unit, says that working with physicians like Dr. Platt enables his team to enrich product development. “This invaluable feedback helps us to provide the best care possible for clinicians and their patients around the world,” he says.

A version of this story originally appeared on GE Healthcare’s The Pulse.

The fetal spine at 23 weeks. Image credit: GE Healthcare.

The fetus at 24 weeks. Image credit: GE Healthcare.

Fetal brain at 27 weeks. Image credit: GE Healthcare.

Fetal hand at 29 weeks. Image credit: GE Healthcare.

For a patient with an acute illness, there’s no graver enemy than time. A diagnosis a week too late, surgery that runs too long — these can be the dividing lines that separate life and death.

But at Bell Land General Hospital in Osaka Prefecture, Japan, medical professionals are working to free up more time for doctors to save more lives by digitizing the way they interact with data.

Time represents a unique challenge for the Japanese healthcare industry. The country’s proportion of elderly residents, already believed to be the highest in the world, is expanding at a rate far surpassing that of any other nation. As a result, Japan is racing to overhaul its healthcare industry by 2025, when the average baby boomer is projected to be 75 or older. At the same time, care providers are facing mounting pressure to treat more patients in less time and deliver better outcomes, all while minimizing costs.

At Bell Land, which is dedicated to treating acute-stage patients, these trends are amplified. “At an acute-stage hospital, it’s unavoidable that the patient’s condition will vary from moment to moment,” said Yoshiaki Suzuki, chief engineer of radiology at Bell Land. “Even if we give it our best effort, lengthy waiting times have an adverse effect on the patient.”

To reduce the length of time patients spend waiting to see a doctor or to obtain examination results, Bell Land is working with GE to automate much of its data analytics workload. The hospital is piloting a new system that will aggregate data automatically from patient charts, diagnostic imaging and other sources and provide a graphical visualization of the information that care providers need

The new system, called Applied Intelligence, enables hospital coordinators and care providers to review information such as waiting times and referral exam volumes in real time to improve the process of making decisions. In the past, this data would have been collected manually, entered into spreadsheets and reviewed by hospital workers over the course of hours or even days. But Applied Intelligence aggregates these numbers instantly without human intervention. It can then suggest ways to improve operations through improved staff allocation, smarter inventory management, and other ways.

Above: GE designed Applied Intelligence to help hospitals make smarter decisions. Top: Osaka, Japan. The Bell Land General Hospital in Osaka Prefecture is working with GE to automate much of its data analytics workload. Images credit: Getty Images.

Much of the methodology driving these improvements is rooted in the digitization of industrial manufacturing — an evolution playing out some 500 kilometers to the north at GE’s Hino Plant, which produces CT scanners and other medical imaging equipment.  Much of the factory is connected to a sensor network that tracks production in real time. The system relies on automated data input. Helpful visualizations enable operators to identify new opportunities for improvement. Over time, these steps allow the managers to standardize and streamline production. The technology already has reduced the need for night shifts, for example.

Bell Land deployed the Applied Intelligence pilot in the hospital’s radiology and enterprise integration departments, where it has already greatly reduced the time workers spend entering and analyzing data. Bell Land expects to see similar gains across its entire facility as it expands the pilot. The hospital hopes these improvements will help ensure that it’s able to effectively serve patients in the years to come.

“If you can actually get a handle on the situation, you get different ideas about how you might solve the problem by doing this or that,” Suzuki said. “Being more efficient doesn’t mean we should work more. Rather, by being more effective at our jobs, we can create more time to treat patients.”

Karen Edelmann’s Doberman, Apollo, developed an odd habit several months ago. He started nudging Edelmann beneath her left breast. Never her right breast, always her left and in the same spot each time. “The first time he did it, he jumped back as if something has scared him,” she said.

Apollo kept returning to her, prodding her left breast in this spot several times a week for about a month. Edelmann paid a visit to Dr. Ian Grady at North Valley Breast Clinic in California. She had had a recent mammogram and it came back normal. But Apollo’s insistence made her concerned.

Edelmann is one of approximately 40 percent of women with dense breasts. Breast density is a measurement of the amount of fatty tissue versus the amount of fibrous connective tissue in the breast. The more fibrous tissue there is, the denser the breast tissue is and the whiter it will look on a mammogram. Both cancer and dense tissue show up white on a mammogram, so looking for tumors in women with dense breasts can be like looking for a snowball in a snowstorm. Because of this, mammography may miss over one-third of cancers in dense breasts.

Karen Edelmann had a mammogram that came back normal, but her dog, Apollo, apparently wasn’t convinced. The Doberman kept nudging her left breast in the same spot, prompting her to seek additional care. After receiving a 3D ultrasound exam on a GE Invenia ABUS (top illustration), a machine designed for women with dense breasts, Edelmann received a diagnosis: Stage 1 breast cancer, right where Apollo had been nudging her. Above image credit: Karen Edelmann. Top image credit: GE Reports.

Women with dense breasts also have a four to six times greater chance of developing breast cancer over their peers who have minimal or no dense breast tissue, according to a study in the New England Journal of Medicine. Furthermore, over 70 percent of breast cancers occur in dense breasts.

A mammogram confirmed Edelmann’s breast density, so Dr. Grady ordered a 3D automated breast ultrasound exam on a GE Invenia ABUS, designed specifically to image women with dense breasts. It is the only FDA-approved ultrasound technology for screening women with dense breasts. A recent University of Chicago study found a 29 percent improvement in detection when ABUS was used alongside a mammogram.

The exam takes about 15 minutes, and the machine generates 3D images of the entire breast to help clearly differentiate between cancer and dense tissue.

A day after her exam, Edelmann learned that she had Stage 1 breast cancer in the very spot where Apollo had nudged. “If she hadn’t come in when she did, the tumor would’ve continued to grow and eventually would’ve been palpable,” Dr. Grady said. “By that time, it could have been Stage 2 or more and required a much more aggressive treatment.”

With early detection, Edelmann was able to avoid chemotherapy and had a shortened radiation schedule. “They wouldn’t have found my cancer without the automated ultrasound,” she said.

She also might not have had an automated ultrasound without Apollo. Dogs have up to 300 million olfactory receptors in their noses, compared to about six million in humans. Additionally, a dog’s brain possesses the ability to analyze smells 40 times more intricately than the human brain. Cancerous cells release different metabolic waste products than healthy cells, creating a smell that some dogs might be able to detect.

Certainly, Apollo has earned a few extra treats this month.

A version of this story originally appeared on GE Healthcare’s The Pulse.

Every time Risa Stack has her routine blood work done, she brings a book to keep her mind occupied and a candy bar to boost her blood sugar. She also alerts the nurse that she might faint. “It’s a whole process,” she says. “I need to be prepared. I pass out on occasion.” She believed in a better way and found it in Drawbridge Health, a healthcare technology company that is developing new ways to draw blood. When she arrived for a site visit earlier this year, she barely had time to settle into her chair. A clinical study coordinator applied a palm-sized device to her arm, and in a matter of minutes the process was finished. “I was talking to a person next to me, and it wasn’t enough for me to even notice,” she recalls. “I said, ‘Hey, this was OK.’”

Drawbridge, a new business founded by GE Ventures, is building an easy-to-use blood collection device that could be used anywhere — at a clinic in San Francisco, in a remote village in Borneo or potentially even at home. Users will be able to apply the device to the upper arm and activate it. It will then store and stabilize the sample in a special cartridge. After a few minutes, the user can remove the cartridge and send it to a laboratory for analysis. “It’s so simple,” says Stack, who leads GE Ventures’ New Business Creation team, which develops and invests in new healthcare, energy and software prospects. “So many people could benefit from this technology.”

The blood collection business is certainly ripe for change, says Lee McCracken, Drawbridge CEO. “Today, blood sampling is dominated by a few large companies,” he says. “They’ve been doing the same thing for decades.” Although he doesn’t expect Drawbridge to “change the world overnight,” he says the device’s applications could include wellness testing, chronic disease management and reproductive health, among others.

Above: The blood stabilization technology inside the device, a high-tech paper-like material known as “the matrix,” was originally developed by scientists at GE Global Research, leveraging knowledge and expertise from the GE Healthcare team. Image credit: Drawbridge. Top: Drawbridge, a new business founded by GE Ventures, is building an easy-to-use blood collection device that could be used anywhere. Image credit: Getty Images.

The playing field is huge. The global blood collection market stands at $7 billion, and health professionals in the U.S. alone draw more than 1 billion blood samples every year. Handling blood is also an important factor in treating patients — blood test results reportedly influence 70 percent of clinical decisions. Then there’s the fear factor. Surveys show that 10 percent of people are afraid of needles and 25 percent require uncomfortable “re-sticks.” The device also could help many men and women whose veins are difficult to access. Stack says the device is an example of a trend in healthcare toward individual control, limiting people’s time away from work or trips to specialized labs. “We are very excited about the opportunity this creates,” she says.

The blood stabilization technology inside the device, a high-tech paper-like material known as “the matrix,” was originally developed by scientists at GE Global Research, leveraging knowledge and expertise from the GE Healthcare team.

The collection device will draw a small amount of blood and channel it onto the matrix, which stores the sample for later extraction and testing. The matrix also stabilizes the collected blood sample and eliminates the need to refrigerate it, which will simplify transporting it to the lab.

When GE Ventures learned about the technology, Stack and her colleagues thought they could build a business around it, as they did with other companies they’ve launched. For example, Vineti is a technology company that uses advanced manufacturing and data analysis software to “industrialize” cell therapy and help make it available for a large number of patients. “The folks in the research center and in GE businesses are bringing us ideas, and we think about business opportunities,” she says.

Drawbridge has made significant process in its product development, and McCracken is optimistic about the future. He says that the technology could even help pharmaceutical companies during drug discovery and drug safety testing. “That is the far end of the spectrum,” he says. “We want to focus on those areas where we can make the biggest difference and be the most helpful.”

In September 2017, Natalie Ray was 28 weeks pregnant with her second child when she felt a pain beneath her rib cage. She assumed it was indigestion, but when it kept her up all night, she called her doctor. She was told to come immediately into Anne Arundel Medical Center (AAMC) in Annapolis, Maryland. When she got there, the doctors ran a series of tests and found that her liver was in distress. They diagnosed her with HELLP syndrome, a serious complication of high blood pressure during pregnancy that typically requires an immediate delivery. “By the end of the day, it wasn’t looking good,” Ray recalls. “The only solution was to get the baby out.”

At 28 weeks, babies are the size of a small eggplant. They can blink their eyes, but still have a long way to go in their development. Twenty-eight weeks is also when Ray’s daughter, Kennedy, came into the world by an emergency C-section, weighing just 1 pound, 13 ounces.

Ray caught a quick glimpse of her daughter before the medical team rushed Kennedy to the Neonatal Intensive Care Unit (NICU) and placed her in an incubator that doubles as a radiant warmer and creates a seamless healing microenvironment for babies. “We were able to see Kennedy in the NICU, but had to wait several days until we could hold her because she was so fragile,” Ray says. “Comparing Kennedy to our first child, Parker, we just couldn’t believe how small she was.”

Top: Natalie Ray gave birth via emergency C-section when she was just 28 weeks pregnant. Her tiny newborn, Kennedy, weighed only 1 pound, 13 ounces and needed immediate medical support. Above: Kennedy’s neonatal team whisked her away and placed her in a Giraffe OmniBed, an incubator and warmer designed by GE that minimizes touching and handling. She stayed there for 45 days. Images credit: Natalie Ray.

Before birth, the womb helps regulate the fetus’ body temperature at about half a degree Celsius above that of the mother. A full-term baby’s temperature typically falls to within a normal range between 36.5 and 37 degrees Celsius after birth. But premature infants struggle to do the same. In fact, for every degree below 36 degrees Celsius, the baby’s survival rate drops by 28 percent.

Kennedy’s incubator and warmer, called the Giraffe OmniBed, allowed doctors to create the right environment and minimize the amount of touching and handling. The machine was designed by GE engineers like Mike Mills, whose own prematurely born son also benefited from it. “I know the equipment and how it works,” he told GE Reports. “But I’ve never seen it in action. Now you see it and it’s your own kid. You don’t understand the value of it until you have used it.”

Tammy Noll, general manager of maternal infant care at GE Healthcare, has her own perspective. “You could think of a full-term baby’s brain like broccoli. When you squeeze it, the shape does not change,” Noll explains. “But a premature baby’s brain is like clay — every movement and touch can have a negative impact, which could lead to cerebral palsy, blindness or issues with fine motor skills.”

Kennedy spent her first 45 days of life in the Giraffe, which kept her warm, helped minimize temperature swings and allowed her to stay in place while she was connected to a spaghetti of feeding tubes and drip antibiotics.

Kennedy’s parents spent hours in the NICU every day, as she was resting under the Giraffe’s translucent dome. “A family’s time in the NICU can be an emotional roller coaster,” says Polly White, a nurse navigator at the AAMC NICU who vividly remembers the Ray family. “To add to the stress, Natalie also had a toddler at home to care for, but she did a wonderful job balancing her time. Kennedy had a few setbacks, yet we were able to get her home just in time for Halloween.” (She was a dalmatian.)

“Comparing Kennedy to our first child, Parker, we just couldn’t believe how small she was,” says Ray. By the time the child’s doctors released her from the NICU unit, she weighed 3 pounds, 6 ounces and continues to get bigger and stronger every day. Image credit: Natalie Ray.

The NICU medical team “was incredible and so understanding,” Ray says. “The AAMC NICU team focuses on family-centered care, which was a wonderful way to bond with Kennedy while she was still in the hospital. Getting discharged from the hospital and going home without your baby is a horrible feeling, but knowing she is receiving the best care gives you some comfort.”

Kennedy was one of 15 million babies born preterm — before 37 weeks of gestation — every year around the world. Even in the U.S., premature birth is a serious predicament and the leading cause of infant death. But technological progress and a growing body of knowledge about prematurity have been increasing the odds in the preemies’ favor. Over the last 10 years, the weight of the smallest baby saved has shifted from 550 to 350 grams, and the youngest baby saved has moved from 26 to 22 weeks.

GE Healthcare’s Noll says her business has been part of the maternal infant care industry for more than 50 years. She says machines like the Giraffe OmniBed play an important role in “helping save smaller and smaller infants. By bringing together the warmer and incubator into one system, we cut down on the movement. If an urgent procedure is needed, you can simply open the hood, fold down the sides and do the procedure right on the bed.”

Fortunately, no procedures were needed for Kennedy. When she left the NICU, she weighed 3 pounds, 6 ounces. She’s being closely monitored but continues to get bigger and stronger every day.

Late November isn’t the best time to visit the Finnish capital of Helsinki. The days are short and gray, the weather is cold, and the streets are covered with slippery slush ushering in a long winter. But Slush is also the name of a huge technology conference — and the reason it’s hard to get a hotel room here this time of the year. A handful of local tech entrepreneurs including Peter Vesterbacka from Rovio, the creators of Angry Birds, launched the event in 2008 to bring together local tech entrepreneurs together.

Although the first event drew just 100 people, the idea scaled quickly. Slush 2017, which started Thursday, attracted 2,600 startups, some 1,500 investors, as many as 20,000 visitors and even Al Gore, who opened the conference. This year’s big theme is data. Young Sohn, chief strategy officer for Samsung Electronics, compared data to “new oil.” Companies here are using it to optimize the movement of cars and electrons as well as employees, patients and products. “Data is becoming more and more important for the products we are building,” said Flickr co-founder Caterina Fake, who gave a fireside chat on Thursday.

Big players like GE, Google, Microsoft, Nokia and Samsung mix with digital companies such as Nexar — which is striving to connect all cars via dashboard cameras, artificial intelligence, and the cloud — and a myriad of startups, including several from GE’s Health Innovation Village in Helsinki’s “Silicon Vallila” district. There are now also Slush events in Tokyo, Shanghai and Singapore, making it one of the world’s largest technology gatherings. “I come here for inspiration, seeing all the crazy things that people can do with data,” says Matti Lehtonen, general manager for GE Healthcare’s anesthesia and respiratory care unit. “They give me new ideas.”

Above: “We are also a little bit adventurous and crazy, in a good way,” says GE Healthcare’s Karla Asikainen. She is building next-generation monitoring ecosystems focused on wireless sensing and data analytics. Top: Slush 2017, which started Thursday, attracted 2,600 startups, some 1,500 investors, as many as 20,000 visitors and even Al Gore, who opened the conference. Images credit: Tomas Kellner for GE Reports.

Many of the ideas come from outside of healthcare. The elevator maker Schindler, for example, pitched its booth a short walk from the GE stand. The company is using Predix, GE’s software platform for the industrial internet, to optimize how elevators move through buildings. Lehtonen thought that he could apply some of Schindler’s insights to optimize operating rooms. “ORs represent 60 percent of hospital revenues, but also 40 percent of their costs,” he says. “If you could fit more operations into a day without paying for overtime, you could save a lot of money.”

During the course of the morning, Lehtonen and his colleagues talked to the Finnish government official responsible for healthcare reform and dropped by Google’s booth to learn how the company recruited developers to use its software. “Partnering is key to future success,” says Jack Page, a product manager in Lehtonen’s unit. “We want to get new people to start playing with us. We want developers to build apps that solve their local needs and distribute them globally.”

GE Healthcare’s Karla Asikainen, for example, is building next-generation monitoring ecosystems focused on wireless sensing and data analytics. One day this tech could lead to “digital twins” of patients and allow clinicians to deliver more predictive and preventive care. She says that while her business has a long legacy of research and innovation in Finland, her team also benefits from access to a rich ecosystem specializing in miniaturization and wireless technologies. “Finland has an amazing pool of talent in the core technologies we need to build the future of monitoring,” she says. “The level of engineering talent in this country and the buzzing ecosystem of startups, especially in wireless and mobile technologies, is tied to the great history of Nokia as well as government initiatives that foster innovation through investments in R&D. We are also a little bit adventurous and crazy, in a good way.”

That means doing their own take on the elevator pitch. Asikainen says that the startup scene here holds pitching competitions such as Polar Bear Pitching where prospective entrepreneurs present ideas while bobbing waist-deep in an ice hole cut in the frozen Baltic Sea. More summery variations involve pitching while skydiving.

Slush looks like a rave that collided with a giant technology mixer. Image credit: Tomas Kellner for GE Reports.

The atmosphere at Slush reflect this spirit. The event takes place inside a massive conference center the size of a city square. The cavernous hall illuminated by neon lights, large LED displays, strobe lights and infused with drifting puffs of artificial smoke, looks like a rave that collided with a giant technology mixer. Walking around, you can bump into business executives dressed in suits and ties as well as visitors wearing makeshift pointy tinfoil hats and polar bear costumes. “The diversity here can be incredibly stimulating, innovation happens at the intersection of so many technologies and industries” says GE Healthcare’s Brandon Henak.

Finnish entrepreneur Mikko Kauppinen, who now runs the Health Innovation Village at GE, says that in the beginning, startups came to Slush because they were frustrated with Europe’s lack of a tech ecosystem similar to what existed in Silicon Valley. But that’s no longer the case, Kauppinen says. “The ecosystem is here,” he says. “Slush has become a global phenomenon. It’s different, it’s huge, and it’s successful, so much so that others want to copy what Finland has done.”

The result is that large companies leave Slush with inspiration, new ideas and partnerships. Promising startups, hopefully, leave flush with new funding. “That’s why we all come here,” Kauppinen says.

It’s time to get excited about monkeys using mind control to move robotic arms and algae that tells time. We’re also keen to try a microscopic data recorder made up of microbes. Meanwhile, scientists are tracking hidden plastic waste in the oceans and finding tornadoes before they form.

Tornado Detection

Above: A new tornado detection method could provide 20 minutes of additional warning time to people in the path of storms like this one in Canada. Image credit: Justin1569 at English Wikipedia. Top: Scientists have hacked E. coli so that it can accumulate a chronological record of the viruses it encounters. GIF credit: Columbia University Medical Center.

What is it? Researchers from Western University in London, Canada, have developed a tornado prediction method using high-altitude radar that they say can forecast a tornado with 90 percent accuracy within a 100-kilometer radius, a vast improvement over today’s methods. The scientists analyzed 16 years of tornado data and correlated it with real-time and archived data from specifically designed radar arrays to make their findings, which were released this month in Atmospheric Science Letters, a journal of the Royal Meteorological Society.

Why does it matter? In a tornado, seconds count. This new tornado prediction method could give meteorologists — and the public — as much as 20 minutes of additional warning time, potentially saving lives and property in the process. The new method reduces false predictions to less than 15 percent, according to the study, and is relatively simple to learn.

How does it work? By adding high-altitude turbulence data gathered from 10 specially built radar arrays to traditional tornado prediction models, scientists were able to see patterns and predictors that haven’t been evident in the past. The Ontario-Quebec radar network was designed to measure wind and turbulence through the upper atmosphere, troposphere and lower stratosphere. It turns out that specific profiles of cloud overshoot — a dome-like knob that forms atop thunderclouds — wind velocities and turbulence were present 90 percent of the time when tornadoes have formed for the 31 tornadoes the data covered. Additionally, all three features were evident 10 to 20 minutes before the tornado formed.

Amputee Robotics

Monkeys were trained to use their thoughts to move a robotic arm and grasp a ball. Image credit: Nicho Hatsopoulos and Karthikeyan Balasubramanian/University of Chicago.

What is it? Neuroscientists at the University of Chicago have taught previously injured monkeys to control robotic arms using electrodes implanted in their brains. Previous experiments have shown how paralyzed human patients can move robotic limbs, but the UC study is one of the first to test the viability of these devices in long-term amputees.

Why does it matter? The research shows the brain is able to create new nerve connections to learn how to control the robotics, even a decade after amputation. That’s great news for amputees, who may be able to regain capabilities lost years ago.

How does it work? Researchers implanted electrode arrays in the brains of three rhesus monkeys who had lost limbs as long as 10 years ago and trained the monkeys to pick up a ball with a robotic arm using thought control. At the beginning of the study, the monkeys’ brains had very few neuron connections in the area that previously had controlled movement of the amputated limb. But as the monkeys were trained — using large servings of juice as rewards — the nerve connections regrew in number and strength, allowing for easier and better control of the robotics. The next step is to equip so-called neuroprosthetic limbs with sensory feedback about touch and spatial location. “That’s how we can begin to create truly responsive limbs, when people can both move it and get natural sensations through the brain-machine interface,” one researcher said.

Finding Plastic Waste In The Oceans

Fluorescent dye makes it possible to see tiny pieces of plastic under a microscope. Image credit: University of Warwick.

What is it? Researchers led by the University of Warwick in the U.K. discovered that using a particular fluorescent dye enables them to quickly and easily identify microscopic pollution in the oceans and beaches. “Nile red” dye lights up when it comes into contact with certain chemicals, making it simple to find among the vast quantities of microscopic material in the sea. dye will stick to and fluoresce microplastics, or plastic particles smaller than 5 millimeters (0.2 inches). Using the dye, researchers were able to prove the quantity of microplastics polluting the oceans was much greater than previously estimated.

Why does it matter? While the ocean plastic gyres— giant islands of garbage — get a lot of press, the amount of microplastics polluting our water is so far unknown. Previous studies found that 99 percent of the plastic waste that we believe to be entering the ocean can’t be detected, meaning it’s either too small to see or is hiding inside the digestive systems of marine life. The dye could allow scientists to map oceanic waste in unprecedented detail, identifying exactly where it is and how much there is.

How does it work? Researchers took samples of beach sand and surface water, then flushed them with nitric acid to eliminate organic material such as fatty substances and wood fragments that otherwise might . They discovered a much higher concentration of microplastics under 1 millimeter (0.04 inches) in size than they’d predicted, and significantly more than they’d have found using traditional methods, which rely on sorting and identifying pollution manually. Using the dye allows researchers to semi-automate the pollution identification process.

Is that the colorAl Gore, who opened the conference this year, said that the world was “in the early stages of a sustainability revolution” and he called it “the greatest business and investing opportunity in the entire history of the world.”

‘Solar’ Panels That Work in the Dark

Printing algae onto a conductive surface creates a cell that can generate an electric current in the dark and in response to light. Image credit: M. Sawa et al. Nature Communications.

What is it? Researchers at Imperial College London and the University of Cambridge printed blue-green algae onto a conductive surface, creating a living “solar” cell that can generate an electric current both in the dark and in response to light. They say the cell could serve as an environmentally friendly power supply for low-power devices such as biosensors.

Why does it matter? The biophotovoltaic device is biodegradable, meaning it might be used in items such as solar panels or batteries, which could decompose in a garden compost pile when used up. Using a plain ink jet printer to create the “battery” makes them cheap, accessible and environmentally friendly, unlike current batteries that use heavy metals and plastics. The devices are around 10 centimeters thick and can be printed in a variety of sizes.

How does it work? Biophotovoltaic cells contain algae that is phototrophic, meaning it converts light into energy. Even in the dark, the algae generates energy by metabolizing its internal storage reserves. When connected to a nonbiological electrode, the cells can function as either a “bio solar panel” when exposed to light or a “solar bio-battery” in the dark. One of the biggest challenges is producing them on a large scale. In the new study, researchers demonstrated that they can use inkjet printing to print the battery, which means they can fabricate cells quickly and with great precision. Nine printed cells connected together can power a digital clock.

Microbe Tape Recorder

What is it? Scientists at Columbia University Medical Center hacked the immune system of a bacteria and turned it into a microscopic data recorder. Researchers modified an ordinary laboratory strain of the ubiquitous human gut microbe Escherichia coli (E. coli), enabling the bacteria to not only record their interactions with the environment, but also time-stamp the events.

Why does it matter? The research lays the groundwork for a new class of technology using bacterial cells for applications as varied as disease diagnosis and environmental monitoring. For example, a patient could swallow the modified bacteria, which then could record their experience through the digestive tract and yield an unprecedented view of . Other potential uses include environmental sensors and studies where bacteria could monitor without disrupting their surroundings.

How does it work? Scientists employed a molecular hack to take advantage of the bacteria’s natural immune system, which copies snippets of DNA from invading viruses so that subsequent generations of bacteria can fight off those pathogens. As a result, the bacteria accumulate a chronological record of the viruses they and their ancestors have survived. Synthetic biologists previously used a similar technique to store movies, books and images in DNA, but this is the first time it’s been used to record cellular activity and the timing of those events.

It’s kind of a no-brainer that Dr. Keith Dreyer would be among those who lead the advance of artificial intelligence into healthcare. Dreyer is a rare breed, a radiologist who teaches at Harvard Medical School, but he also holds a degree in mathematics and has a doctorate in computer science. So it’s fitting that Dreyer serves as the chief data science officer at Partners HealthCare, a healthcare network that includes Brigham and Women’s Hospital and Massachusetts General Hospital, two of America’s most prestigious medical institutions.

Earlier this year, Partners and GE Healthcare signed a 10-year agreement to “integrate artificial intelligence into every aspect of the patient journey.” Why? A hospital generates some 50 petabytes of data per year on average, enough to fill 20 million four-drawer filing cabinets with standard pages of text. But 97 percent of the information never gets used.

Not for long, if digitization continues to gain steam. Dreyer says “thousands of algorithms” are in the works that use data to help medical professionals do their jobs better and more efficiently.

We caught up with Dreyer in Chicago last week at the annual meeting of the Radiological Society of North America (RSNA), the world’s largest gathering of radiologists and other medical professionals. Here’s an edited version of our conversation.

GE Reports: Everybody seems to be talking about machine learning and artificial intelligence at RSNA this year. What is going on?

Keith Dreyer: You have to look at the evolution of the field. When I was getting my PhD in computer science 20 years ago, some of my projects touched AI. But the algorithms weren’t sophisticated enough and there wasn’t enough data. So I went back into radiology and medicine and focused on building out the digital infrastructure.

Now, because of all of the data streaming across the internet and the amount of money invested in the space, AI is coming back. We can actually see the stuff work. For example, the neural net architecture and deep learning have vastly improved as we started looking for things online.

The computers themselves also got so much faster. Back then, if you tried to train an algorithm, it took four months just to run one computation. Now you can do the same thing in 10 minutes and iterate quickly.

GER: Why do we need AI in healthcare?

KD: You have to have it. There’s too much data for humans to analyze.

GER: Can you give us an example?

KD: Modern medical scanners encode an image pixel in 56 bits [giving it 72 quadrillion possible “shades”]. But the machine brings down the amount of information to 16 bits [per pixel, or 65,536 shades] before the radiologists see it. So, in theory, 40 bits of information is being lost. And that’s just one pixel. We have about 10 billion images stored in our archives at our healthcare system alone.

GER: These numbers are overwhelming. Where do you start?

KD: I’m on the board of the American College of Radiology and we’ve created what’s called the Data Science Institute. We realize that there are huge opportunities with AI and machine learning, but we need to create a structure around it.

First we have to define the clinical challenges we have, and then apply data science to create the prediction models. As you can imagine, there are thousands of algorithms already being built right now. We need mechanisms to integrate them into the workflow, patient care, all of those kinds of things.

Above: Keith Dreyer says there are “thousands of algorithms” in the works that use data to help medical professionals do their jobs better and more efficiently. Image credit: Getty Images. Top: There’s too much data for humans to analyze, Dreyer says. Image credit:Partners HealthCare.

GER: Let’s start from the beginning. How do you build an algorithm for doctors?

KD: Stroke detection is a good example. It’s critical to detect and correctly identify stroke as soon as possible, because there’s only a limited window of time when you can actually treat [the patient] and preserve the neurons. The [specific] type of stroke affects treatment. Let’s say we do 200,000 MRI exams of the brain per year and 20,000 are stroke. We can annotate those 20,000, measure the brain lesions caused by the stroke and so on. Next we use the entire 200,000-image set to train the algorithm and use it to identify the type of stroke. When it’s finished, we come back with a test set to see how accurate it was and repeat the process.

GER: Is your image sample large enough to train the algorithm?

KD: As I said before, we have about 10 billion images stored inside of our archives. So if you’re looking for specific rare diseases, maybe it’s not enough. But the findings inside our data are pretty consistent for most of the work that we do.

Ideally, you should be using your exams that were done on scanners that you’re familiar with and then annotated by the right people. If you get any noise in the annotations, the algorithm is just going to train with less accuracy. Those are the fundamental challenges.

GER: Who are the people working on AI and machine learning at Partners HealthCare?

KD: It would be very hard for any single physician or any single data scientist today to solve these problems. It takes a team approach. We’ve created a Center for Clinical Data Science, which has about 35 people. They are a combination of data and computer scientists, physicians, workflow people and others. We currently have 41 projects in the pipeline, and it would be pretty hard to imagine how we could do it in any other fashion.

GER: What diagnoses?

KD: Some are in pulmonology, others in pathology and neurology, and some are in imaging.

GER: When are you going to start using them?

KD: First of all, you need an FDA approval. But even if we had approvals and actually deployed 41 algorithms inside one of our own hospitals, we could never support them. We have 70,000 employees, 6,000 physicians and over a dozen hospitals. Before we start to get too crazy with the creation of algorithms, we have to work with companies like GE. They have the scale and knowledge to help us.

GER: How does GE Healthcare help you?

KD: The relationship with GE Healthcare is an integral part of what we are doing. I could come up with the greatest algorithm in the world, but GE knows how to deploy it across the globe and what needs to be done to integrate it into the existing infrastructure. Do the results go to a referring clinician first, or to the emergency room doctor, for example? If that workflow isn’t put in place first, it just won’t work.

GER: What do you mean by workflow?

KD: We haven’t even scratched the surface of getting AI integrated in a way to make it work the best. For example, when we look at a CT image of the head, we might have 1,000 images to review. And today, you just have to step through all 1,000 images. Well, if an AI can run before us and say, those are the four of the 1,000 images that you need to review, do I need to even scroll through 1,000 images? Couldn’t it just show me the four I need, and then give me some information? But am I still the human making the decisions?

GER: Is AI going to replace doctors one day?

KD: I firmly believe that a radiologist plus an AI will beat a radiologist, and will also beat an AI working alone. We have to figure out how to make them work together.

GER: What does the future of AI in medicine look like?

KD: One interesting area is population health, being able to identify a group or a population at risk. You could pull data off a wearable device, like a Fitbit, and say, OK, I’m seeing a variability in heart rate, I’m seeing a change in motion, and that gives me risk considerations for a patient who needs further diagnostic workup.

If you can detect patients before they become symptomatic, you’ve got a much better prognosis. I think that’s where a lot of this is going to end up.

Walking around Munich this week feels like stepping into a Christmas card. A dusting of snow lines the peaked roofs and cobblestoned streets in the city center, creating the perfect backdrop for the city’s festive holiday markets. But a few miles from the edge of town, several hundred engineers, industrial designers and business executives have already opened their big present: a new GE center that will allow the company’s current and potential customers to take a deep dive into additive manufacturing — a group of technologies that includes 3D printing — and learn about design, prototyping, production and other key parts of the business.

“Our vision is very simple: We want to democratize manufacturing,” says Mohammad Ehteshami, who runs GE Additive, the GE business unit developing machines, materials and expertise for the nascent industry. The business has expanded from 560 people in late 2016 to 1,200 today, producing more than 500 printers per year. The new center is a key part of its drive to bring additive manufacturing into the mainstream. “Additive is so powerful that you either lead it or you get victimized by it,” Ehteshami says.

Jennifer Cipolla, GE Additive’s global leader in charge of customer experience centers like the one that just opened in Munich, has spent the last couple years running a similar facility GE built in Pittsburgh. That facility is helping GE businesses like Aviation, Power and Healthcare to 3D-print machine parts and products.

GE has invested $3 billion in the additive manufacturing space, including $200 million in research and development. It acquired majority stakes in 3D-printer makers Concept Laser and Arcam, which also makes the special powders used for metal printing. To date, GE has shipped 25,000 3D-printed parts for machines like the best-selling LEAP jet engine, which brought in more than $200 billion in orders.

The new GE center that will allow the company’s current and potential customers to take a deep dive into additive manufacturing. “Additive is so powerful that you either lead it or you get victimized by it,” says GE Additive Ehteshami. Top and above images credit: GE Additive.

Cipolla says that “within two very short years, the conversation around 3D printing has shifted from ‘Why should I get into additive manufacturing and why is it important?’ to ‘Oh my gosh, my competitors are doing additive and I’m behind! How do I catch up?’” She continues, “Instead of trying to convince people that additive manufacturing is the way of the future, they’re already there. It’s now about taking the deep domain expertise that GE has built up over many years and helping our customers to realize the full value of 3D printing, from design and selecting the right parts fit for printing, to prototyping, optimizing the production process and getting the parts certified.”

Some 150 customers attended today’s opening, including manufacturing heavyweights like BMW Group and Oerlikon. The two are already using 3D printing, have their own machines and want to increase their domain expertise. Others are exploring the field and want to learn how to adjust their current operations to incorporate additive technologies.

Maximilian Meixlsperger, leader of additive manufacturing metals at BMW Group, said that the company started in 2005 with a single Concept Laser machine and already 3D-prints 10,000 metal components per year. They included parts for the original BMW 507 from the late 1950s — once owned by Elvis Presley — plus customized dashboards for the all-new Rolls-Royce Phantoms and the new BMW i8 Roadster. “Productivity is the key for additive manufacturing to become a game changer in the automotive industry,” he says. He wishes that in the future, “every single product from the BMW Group will have additively manufactured parts.”

Florian Mauerer, head of the additive business unit at Oerlikon, calls additive the physical leg of the information revolution. It allows engineers to print parts that are stronger and lighter directly from a digital file, layer by layer. “The crowd will separate from those who have it and those who don’t,” he says. “The possibilities are almost unlimited.”

To date, GE has shipped 25,000 3D-printed parts like the tip of this fuel nozzle for the best-selling LEAP jet engine. The engine brought in more than $200 billion in orders. Image credit: GE Aviation.

GE invested $15 million in the Munich center. Its surgically clean interior looks like a Hollywood version of the factory of the future — but there’s nothing fictional about it. A long blue LED ribbon wraps around the perimeter of the entrance into the 2,700-square-foot center, which is made from smooth concrete. There are several 3D printers of various sizes located along the perimeter of the ground floor and separated by folding glass walls. Made by Arcam and Concept Laser, these machines can print entire engine blocks as well as delicate skull implants that doctors can use for reconstructive surgery.

The room forms an atrium with a broad set of stairs leading to the second level, which holds the Additive Academy, where visitors will learn about 3D printing from GE and industry experts, and a “collaboratory,” where they can develop their designs and test different additive manufacturing applications. “It’s really about us imparting our knowledge that we have gained over the past decade in additive,” says GE Additive’s Matthew Beaumont, who runs the new center.

Beaumont calls the center a “world-class training facility” that will help customers design 3D-printable parts and incorporate additive manufacturing into their business models. “The plan is to have examples of all of our machines here on the floor, that the customers come in, see, touch and actually use.”

GE decided to build the first global additive center in Munich because Germany is ground zero for 3D printing for metals. Concept Laser, for example, founded by the pioneering inventor Frank Herzog, is located about two hours from here, in Lichtenfels. GE Additive broke ground on a new 105 million euro factory there in November.

Beaumont says that the new center will give GE “an opportunity to show what we’re doing, as well as hear from customers what they’d really like to have in the next generation of machines and the experience they’ve already had with them.” Says Peter Stracar, who leads GE in Europe: “Nothing drives innovation more than the interaction between companies and customers.”

The internal clock that tells us when to wake up, when to eat and when to go to sleep might seem mundane, but it was the basis of research for this year’s winners of the Nobel Prize in Physiology or Medicine. Three scientists, Jeffrey Hall, Michael Rosbash and Michael Young won the prestigious award by unearthing the three genes that interact to regulate our circadian rhythms and showing how those rhythms connect to health problems like obesity, diabetes and cardiovascular diseases.

The trio joined an elite group of biologists whose fascination with the secret lives of cells also led them to Nobel Prize-winning discoveries in medicine or physiology. But they share more than just the Swedish award: 75 percent of recent winners of the Nobel Prize relied on a version of the DeltaVision microscope from GE Healthcare during their research. This year’s winners, for example, used it to “peek inside our biological clock and elucidate its inner workings.”

This type of “peeking” wasn’t possible up until 25 years ago. Researchers could not keep cells alive long enough to study their behavior. Once detached from their host bodies, living cells wither under the hot glare of the microscope. The DeltaVision solved that problem with an environmental chamber that mimics the temperature, humidity and other aspects of a body closely enough to keep living cells ticking for several weeks.

Above: The DeltaVision machine’s added resolution allows scientists to see more than they’ve ever been able to see with light microscopy. Pictured here is a toxoplasma gondii parasite. Top:The design allows researchers to tag bacteria with fluorescent molecules and use them to illuminate hidden features. Here we see a tissue section stained for immune cells. Images credit: GE Healthcare.

There are other benefits. A different DeltaVision product uses software and high-definition cameras to observe bacteria, viruses and other samples in 3D even beyond Ernst Abbe’s diffraction barrier, which limited microscopic resolution to roughly half the wavelength of the light the microscope used. The DeltaVision machine’s added resolution allows scientists to see more than they’ve ever been able to see with light microscopy, such as watching how biofilms form in real time, or viewing a cell’s nuclear pores or other subcellular structures.

The design also allows them to tag bacteria with fluorescent molecules and use them to illuminate hidden features. Paul Nurse and Lee Hartwell, who used one of the first versions of the machine, depended on this feature while doing their research into how cells divide. As the cells lived happily in the environmental chamber, the scientists were able to record clear, highly magnified time-lapse images of biological processes as they occurred. That work earned them the Nobel Prize in 2001.

Finding cell structures can be hard. In some ways, it’s like looking for a single back alley on a citywide map of Los Angeles. Elizabeth Blackburn, president of the Salk Institute and 2009 winner of the Nobel Prize, used the DeltaVision in her research on chromosomes. She was looking for telomeres — structures that protect the ends of chromosomes and are essential to understanding aging, cancer and other stem-cell disorders.

Sensory cells of the inner ear. Image credit: GE Healthcare

Blackburn found the telomeres by setting her cell sample on the DeltaVision’s automated stage, which lets the scientist use a joystick to scan the sample in three dimensions (marked by x,y and z axes). Viewing her specimen on a computer monitor, Blackburn was able to zero in on telomeres she found in much the same way one would use a Google map to zoom in on the right street address. She could then punch in the coordinates of her favorite spots, directing the digital camera to take continuous photos of those specific areas over a period of time. The microscope automatically stored the data to her computer so she could analyze it further.

Many of these breakthroughs may just be phase one for the Nobel laureates. For instance, Dr. Yoshinori Ohsumi, who won the 2016 Nobel Prize for his study of the protein’s recycling process, known as autophagy, also relied on an older version of DeltaVision microscope.

Tissue section stained for epithelial cell markers. Image credit: GE Healthcare.

The next step for this kind of research will likely involve super-resolution microscopy of yeast, the cells of which share many properties with human cells. GE Healthcare’s latest version of the DeltaVision includes a super-resolution system that produces images in two and three dimensions. Advanced research in super resolution has the potential to unlock more of autophagy’s secrets and open new doorways to translate this basic science into disease treatment and prevention.

The Nobel Committee for Physiology or Medicine will surely be watching.

Music fans traveling northwest on highway 86 toward the Coachella music festival next year might not give the rolling hills of California’s Imperial Valley more than a passing glance. But energy insiders know it as the site of a major technological feat that could herald a new era in power-grid resiliency.

In May, the Imperial Irrigation District (IID) performed the first “black start” of a power plant in North America. They did it by starting and revving up the El Centro power station to full power with only a GE battery energy storage system.

Why does it matter? Utilities that derive a lot of their power from renewable sources — as is common in California — typically keep gas and coal-fired thermal power plants running on standby to pick up the slack when the sun isn’t shining or the wind stops blowing. Along the way, they generate emissions and burn expensive fuel.

But the 33-megawatt grid-scale battery storage system in the Imperial Valley gives the IID enough energy capacity to power up to 44,000 homes and shut these plants down and supply electricity as needed.

Above: A carrot field in Imperial Valley, California. The agriculture industry in the area depends on reliable electricity. Top: A 33-megawatt grid-scale battery storage system in the Imperial Valley gives the local irrigation district enough energy capacity to power up to 44,000 homes, shut down coal-fired power plants running in a stand-by mode, and supply electricity as needed. Images credit: Getty Images.

That’s not all. Utilities typically rely on diesel or gas generators to bring the idled power plants back online, a solution that taxes both the budget and the environment. It turns out the battery, along with data and software, can also restart the power plant. “With the Imperial Valley battery storage system, we are definitely leaving behind the earlier stages of stand-alone grid battery storage,” says Mirko Molinari, general manager of distributed grid systems at GE Power. “We are now deploying systems in which the battery itself is just a commodity assigned to a routine job.”

Molinari says that while the battery is still a critical component, most of the value comes from “the sophisticated higher-level hardware and software.”

For the “black start,” for example, plant operators used data and GE software to make sure that the voltage, phase and frequency from the storage system’s batteries matched the power on the grid. This process called synchronization allowed them to restore power evenly and safely. Then, as the plant came back online, it recharged the battery.

Molinari says that batteries could also help reduce power failures in the future, or at least make them easier and cheaper to fix.

“The speed and flexibility required by today’s energy generation makes it enormously complex,” Molinari says.“It’s extremely difficult to determine exactly how much power is needed at a particular moment.”

NASA scientists reinvented the wheel in preparation for further space exploration, a woman who was born without a womb delivered a healthy baby, and lab-grown patches are keeping mouse and rat hearts beating. We’re pumped — are you?

Springy Tires For Mars

What is it? NASA engineers developed a puncture-proof tire made of a special woven-mesh metal that immediately springs back into shape while moving over jagged or uneven surfaces. Space-grade tires used since the 1960s haven’t coped well with the unforgiving surface of Mars, but engineers have high hopes for their new tire, which eventually could be a boon to Earth drivers as well.

Why does it matter? The aluminum tires used on the nuclear-powered Mars Curiosity robot started shredding after just a year roving over the sandy, rocky surface of the red planet. Amazon isn’t delivering replacements just yet, so NASA needed a durable tire that was tough enough to withstand the harsh conditions, including daily temperature swings from minus 200 degrees to 70 degrees Fahrenheit, and wouldn’t tear or become deformed. Engineers worked with various woven metals, similar to what’s used today, but couldn’t figure out how to prevent the inevitable dents that accumulate over the expected 10-year life of the tire. A chance encounter between two engineers led them to collaborate using a “shape-memory alloy” — a super-elastic metal that pops back into place, even after intense strain.

How does it work? The nickel-titanium (NiTi) alloy engineers settled on has about 30 times more elasticity than the aluminum tires now used on Mars. That extra elasticity means tires made from it can carry nearly 10 times the weight, grip better on rocks and sand and climb slopes about 23 percent steeper. “We can actually deform this all the way down to the axle and have it return to shape, which we could never even contemplate in a conventional-metal system,” said NASA materials scientist Santo Padula. The elasticity comes from the alloy’s crystal structure, which is composed of stretchy bonds at the molecular level. Engineers are working with Goodyear to develop a tire for Earth use, so off-roaders can be as high-tech as the Mars rovers.

Transplanted Uterus

Above and top: A uterine transplant clinical trial in Dallas has reached a major milestone with the birth of this healthy baby. Images credit: Baylor Scott & White Health.

What is it? The first U.S. baby born to a woman with a transplanted uterus was delivered this month at Baylor University Medical Center in Dallas. The U.S. baby was the first born from a transplant outside Sweden, where the procedure has led to eight births since 2014.

Why does it matter? The procedure opens up new possibilities for women with certain infertilities, including those born without a uterus. It’s also one of the first instances of transplant surgery being used as a temporary measure. Dr. Liza Johannesson, a uterus transplant surgeon at Baylor who also worked in Sweden, noted the significance of the procedure’s success in a new hospital under a new team. “To make the field grow and expand and have the procedure come out to more women, it has to be reproduced,” she told The New York Times.

How does it work?Surgeons implant a uterus from a volunteer or cadaver into a woman who was born without one, or whose uterus was damaged by illness or trauma. In-vitro fertilized eggs then are transferred to the woman’s new uterus. Once she delivers a baby, doctors remove the uterus so that she can stop taking immune-suppressing anti-rejection drugs, which elevate her risk for infection, cancer, heart disease and bone marrow loss. So far, 10 women have been involved in Baylor’s clinical trial. Eight have received transplants, including the new mother. Four transplants failed, one recipient is trying to conceive, and another currently is pregnant.

Artificial Heart Patch

What is it? Duke University scientists created an artificial heart muscle that can be patched over dead tissue in rats and mice, and hopefully one day in humans who have suffered heart attacks.

Why does it matter? Dead heart muscle won’t regenerate, and scar tissue left after a heart attack can’t contract or send electrical signals, both of which are necessary for proper heart function. Some 12 million people worldwide suffer from the resulting heart failure. Duke biomedical engineers think doctors could one day implant their artificial heart tissue over existing dead muscle, restoring its ability to beat and carry electrical currents.

How does it work? The patch cells are grown from human stem cells in a jelly-like culture. Various types of muscle cells are needed for the patch, including cells responsible for muscle contraction, cells that provide the heart’s structural framework, and cells that form blood vessels. The patches also secrete enzymes and growth hormones, possibly helping damaged tissue recover. The Duke team spent years determining the right combination of cells, hormones, nutrients and culture conditions to grow patches large enough to cover the dead parts of the heart muscle. They discovered along the way that gently rocking the cells improved nutrient delivery by bathing the cells. That led to bigger cells and therefore larger patches, up to 16 square centimeters and five to eight cells thick. The patches take about five weeks to grow to adult muscle strength, and they have been shown to work on rat and mouse hearts. However, they’ll need to be significantly thicker (roughly 1.1 centimeters) to work in humans. The team’s findings appear in Nature Communications.

Biological Crystals Power Music

Tapping or squeezing crystals of the amino acid glycine provokes an electrical response. “It is really exciting that such a tiny molecule can generate so much electricity,” said Sarah Guerin of the University of Limerick. Image credit: Sean Curtin/True Media

What is it? Scientists at the University of Limerick in Ireland discovered a cheap, environmentally friendly way to power devices such as mobile phone speakers and car sensors using energy produced by glycine, an amino acid.

Why does it matter? Glycine is the simplest amino acid. As a naturally occurring molecule, it can be produced commercially at less than 1 percent the cost of synthetic compounds used to generate electricity in cars, phones and remote controls. Plus, glycine has no toxic byproducts such as lead or lithium, making it a sustainable energy source.

How does it work? Glycine, when tapped or squeezed, generates electricity. Limerick researchers grew long, narrow crystals of glycine in alcohol and produced enough energy to power simple electronic devices just by tapping the crystals. Scientists started by using computer models to predict the electrical response of a wide range of crystals. Glycine “was off the charts,” said Sarah Guerin, lead author of the study, which appears in Nature Materials. The predictive computer models also helped determine what kinds of crystals to grow (long and narrow) and where best to cut and press those crystals to generate electricity. “It is really exciting that such a tiny molecule can generate so much electricity,” said Guerin.

Stretchable Bacteria Batteries

Textile-based bio-batteries are stable electricity generators despite repeated stretching and twisting, making them well-suited for use in wearable tech. Image credit: Seokheun Choi

What is it? Scientists at Binghamton University, State University of New York, developed a stretchy, flexible bacteria-powered bio-battery made of fabric that potentially could be integrated into wearable electronics, or “smart clothes.”

Why does it matter? Researchers hope that one day the small, microbial fuel cells will replace oil, coal or even solar energy as a long-lasting, universally available and inexpensive renewable energy source that can generate power in any conditions. In the meantime, the textile-based bio-batteries are a platform for wearable technology because they have proven to be stable electricity generators despite repeated stretching and twisting. That flexibility means they easily can be incorporated into clothing to collect real-time information about the wearer or surrounding environment.

How does it work? Bacteria in microbial fuel cells generate electricity when they eat. As the bacteria break down complex organic molecules, energy is released and can be tapped to generate power. Roughly 16 of the microbial fuel cells connected together can power a light-emitting diode (LED). Researchers think sweat from the human body may be a potential food source to support the bacteria, which would make maintaining them simple and cheap, and allow them to generate power almost indefinitely. The team’s paper, “Flexible and Stretchable Biobatteries: Monolithic Integration of Membrane-Free Microbial Fuel Cells in a Single Textile Layer,” appears in Advanced Energy Materials.

During World War II, the Weymouth Naval Aviation Station, just 10 miles south of Boston, was home base for 12 military blimps that protected the New England coastline by keeping watch for German U-boats.

But for the past 20 years, the 1,500-acre piece of land — which spreads over two counties and three townships — has sat vacant because of arguments about conflicting zoning rules and the challenges of dealing with multiple South Shore municipalities.

But over the next 15 years, the site, now known as Union Point, is set to transform. Developer LStar Ventures is building a sustainable city that will include 10 million square feet of commercial space, 4,000 residential units, rooftop gardens and branches of some of the prestigious local universities. Interspersed throughout will be plazas and green spaces as well as housing for the elderly and people with disabilities. All of the buildings will feature smart technology and be LEED-certified, and the community will run completely on renewable energy by 2050.

The site’s developers are hoping to attract not only Boston’s young professional class but also major employers, including Amazon. A key part of their bid to become home to the tech giant’s second headquarters: The city will be a testing ground for experimental technology that could make Union Point a model for new developments going forward.

Above and top: This 1,500-acre swath of land outside Boston, which was once home to the Weymouth Naval Aviation Station, has sat vacant for 20 years, but that’s about to change. The site will become a sustainable “smart” city, complete with data-collecting streetlights, rooftop gardens and LEED-certified buildings. Plans call for the community to run entirely on renewable energy by 2050. Images credit: LStar Ventures.

For example, starting next year, GE will install smart streetlights complete with sensors that can track sound, light and other environmental conditions. City planners will be able to analyze that data using apps running on Predix, GE’s cloud-based platform for the industrial internet. A similar system already is up and running in San Diego, where the city is using the information to help people find parking spaces.

Operators at Union Point might decide to use the data for other purposes, such as helping people avoid congested areas or timing traffic lights to cut down on traffic.

LStar, which specializes in turning around distressed properties, initially expected to build a fairly standard suburban residential district on the site. But knowing the area and realizing what an unprecedented opportunity a site this large with access to public transportation was, Corkum told the local officials who had to approve the deal that he wanted to do more.

“I told them,” Corkum explains. “ ‘Give me three months to brainstorm and build a coalition for something more ambitious.’ ” He spoke to local businesspeople, environmentalists and civic leaders about want they wanted. Local authorities quickly approved the sweeping plan that came out of these sessions — to build a smart, sustainable city that meshed commercial, educational, cultural and recreational elements.

To execute on the plan, Corkum went to the best Boston had to offer, including architecture firm Elkus Manfredi (known for New York’s Hudson Yards) and Sasaki Associates, founded by Hideo Sasaki, a former chairman with the Harvard University Graduate School of Design. Corkum met with local universities, including MIT’s Media Lab, to discuss using the site as a testing ground for new technologies.

He also approached GE, which moved its headquarters to Boston in 2016, about helping not only with Union Point’s technological infrastructure but also with LStar’s bold vision for powering Union Point with renewable energy.

“This is what we do,” says Eliot Assimakopoulus, business leader for government solutions at GE Grid Solutions. His team is working with LStar on a master energy plan that will take into account all current sources of energy, forecast Union Point’s growing needs and map out how to meet those needs most efficiently, paving the way for renewables.

Corkum says that while all of this new technology is exciting, it’s important that it serves the people who will be living and working at Union Point.

“Union Point is striving to be a real community with homes, offices, retail and restaurants,” says Corkum. “But it’s also going to be a living laboratory.”

Charles Proteus Steinmetz, one of the leading lights who spread electricity across America a century ago, often pointed out that energy in the form of heat, water or steam was the raw material of the electrical industry. The GE engineer and inventor hated waste and urged industry to harness energy “whenever [it was] available as a by-product” and convert it into electricity. Today, he would probably say the same thing about data.

Even though modern power plants generate gigabytes of valuable information every day, much of it never gets used. But that’s changing. New York Power Authority, the largest state public utility in the United States, just opened a new 25,000-square-foot digital “mission control” center, in White Plains, New York. The center allows engineers to process gigabytes of data and mine it for valuable insights. It also enables them to control all 16 of NYPA’s power plants as well as key points within its massive power transmission network stretching across 1,400 miles, which supplies a quarter of the state’s electricity, including power for New York’s airports and subways. “With the opening of this state-of-the-art center, we are modernizing our state energy system and creating a more resilient, reliable and flexible power grid helping to grow our clean energy economy,” New York Governor Andrew Cuomo said in a statement. (Some 75 percent of NYPA’s electricity comes from hydropower.)

The new facility, called Integrated Smart Operations Center, or iSOC, comes complete with an 81-foot video wall where operators can review insights supplied by data analytics and use them to predict possible failures, schedule asset maintenance for the least disruptive times and even compare notes with their colleagues in the field. “This is just the beginning on our journey,” said NYPA President Gil Quiniones. He said that NYPA was on its way to becoming “the first end-to-end digital utility, not in the U.S., but in the world.”

Top: NYPA President Gil Quiniones said that NYPA was on its way to becoming “the first end-to-end digital utility, not in the U.S., but in the world.” Image credit: NYPA. Above: GE is helping NYPA connect its hydroelectric plant downstream from Niagara Falls to the Industrial Internet. Image credit: Getty Images.

The benefits can be huge. Bill Ruh, CEO of GE Digital, which is supplying NYPA with software and data analytics, says that industrial digitization is a bigger opportunity than the consumer Internet. The International Energy Agency reported last month that in the U.S. alone, digitalization had the potential to save around $80 billion per year, or about 5 percent of total annual power-generation costs. Quiniones says that center has already helped NYPA save $3 million, and the utility expects expect to recoup $1 billion in efficiencies over the next decade.

Sanjay Chopra, a solution architect from GE Digital involved in the NYPA project, says that a true digital utility will “digitize everything from the turbines to the toasters and all that’s in the middle. As a consumer, I want to be able to use electricity in the most efficient way and know how the price affects me on an hour-by-hour basis,” he says. “As a producer, I need to be able to understand what the demand is out there for electricity, and how do I send onto the grid the cheapest and most efficient electricity I have.”

Centers like the one NYPA just opened will play a key role. It collects information from sensors about temperature, vibrations, wear and factors like energy usage. It can also pull in weather and other data from outside sources. The information first travels to GE’s Asset Performance Management software powered by Predix, GE’s application development platform for the Industrial Internet. Apps running on the system help operators understand the conditions inside NYPA’s power plants, transformers, cables and other electrical assets, predict and prevent equipment failures, and avoid power outages. “We help them proactively resolve a problem before it becomes a major disruption,” Chopra says. “They can use the insights to optimize maintenance on those assets and arrange it when there are scheduled downtimes, rather than taking costly, unplanned downtimes.”

GE engineers Eskil Berg, Charles Steinmetz, Ernst Berg, and Langdon Gibson (left to right) pose in raincoats on the “Maid of the Mist” boat ride at Niagara Falls. The team was taking a break from work on the high voltage alternating-current transmission line form Niagara Falls to Buffalo, New York, built in the 1890s.. Image credit: Museum on Innovation and Science Schenectady.

One app, for example, allows NYPA to pull in marine information and monitor boat traffic near its subsea lines crossing from the mainland to Long Island. NYPA can use it to alert captains of nearby ships to refrain from dropping anchor and damaging the cables. Another app, called NY Energy Manager, is gathering data from 11,000 buildings in the state and pieces of the most power-hungry equipment, and allows customers to reduce their costs by operating them in a more efficient manner.

The system also allows NYPA to build “digital twins.” These virtual representations of the equipment understand how the assets operate normally, flag readings that are out of bounds, and send warnings to NYPA engineers in the iSOC. These engineers can take a closer look, discuss the findings with their peers across the network and schedule maintenance, if necessary. Operators also can use the system, which can monitor equipment made by GE and other manufacturers, to simulate multiple scenarios and predict possible outcomes.

Betsy Timoney, GE Digital’s liaison with the NYPA, says that in the future, the system will include an analysis of “relational data” that will allow the utility to combine financial information about, say, maintenance costs and the impact of a potential problem on performance. “The next big thing will allow them to look at how much it would cost to do something this year versus next year,” she says.

Ruh called the opening “a seminal moment” signaling the first phase of a power-industry transformation that will reshape how utilities do business. Said Ruh: “NYPA is laying the blueprint for how every utility in the world can operate.”

Even Steinmetz would be surprised!

Crews in California are fighting another deadly wave of wildfires, which have killed and injured dozens of people, burned millions of acres and destroyed thousands of structures. In December, for example, the Skirball fire closed the 405 Freeway, a major traffic artery linking Los Angeles with the San Fernando Valley, and burned homes in Bel-Air, one of the nation’s poshest neighborhoods. “This is kind of the new normal,” Gov. Jerry Brown told reporters at a news conference. “We’re facing a new reality in this state, where fires threaten people’s lives, their property, their neighborhoods and, of course, billions and billions of dollars.”

State and local departments have dispatched thousands of men and women to fight the fires on the ground, but also from the air. One weapon in the Los Angeles County Fire Department’s arsenal is the Firehawk, a modified Black Hawk UH-60 helicopter that can carry 1,000 gallons of water and fly near intense fires.

“These machines are experiencing some of the most extreme conditions you can image on a helicopter,” says Bill Neth, a senior manager at GE Aviation. “Every time the aircraft is fighting fire, it goes to maximum power six to eight times per hour. It must deal with the heat but also the heavy lifting when the tank if full of water. There is no margin for error.”

Sikorsky originally developed the chopper for the U.S. Army. But engineers modified the Firehawk, which is powered by a pair of souped-up T700 GE helicopter engines, for firefighting, medical evacuation, and other help and rescue missions.

Neth says that GE Aviation engineers studied Black Hawks that returned from Iraq and Afghanistan to improve the hot section of the engine. They put in parts from advanced nickel alloys and made the engines more resistant to wild temperature swings, airborne debris and degradation from thermal distress. The engine can now withstand extreme conditions and still deliver the necessary power.

The engines also power a pump that can fill up the Firehawk’s enormous water tank in just 1 minute through a retractable snorkel hose while hovering over a water source. The helicopter also can land and ingest water through a connector on the side of the tank.

Earlier this year, GE Aviation received for the first time a rare exemption from the U.S. Federal Aviation Administration to equip a pair of Firehawks used for fighting forest fires in Oregon, Idaho and elsewhere in the Western U.S. with a military version of the T700 engine. Bart Brainerd, president of Firehawk Helicopters, said in a statement that the new engines were able to increase the choppers’ available payload in hot and high conditions by as much as 50 percent and also provide “near instantaneous response to power demands and precision rotor speed control.”

GE has completed 20,000 orders for the T700 and its close cousin, the CT7. They have completed more that 100 million flight-hours, but engineers keep working on making it better. They recently 3D-printed large sections of the CT7, combining some 900 engine components into just 16 and reducing the number of parts by 35 percent. “This is going to change the way the entire world approaches design and production,” says Josh Mook, one of the engineers who worked on the project. “It’s our job to help them figure out how to use this revolutionary technology.”