What happened in healthcare technology this week, and why it’s important.
How AI and Facial Recognition Could Spot Stroke and Other Diseases
Eric Niiler in The Wall Street Journal (subscription required) reports that researchers are training computer algorithms in efforts to identify ailments and speed treatment quickly. Patients at Johns Hopkins Hospital suspected of having a stroke might get an unusual request from physicians: Can we film your face? The doctors’ goal is to identify stroke patients by facial characteristics instead of waiting for brain scans or blood tests, helping speed both treatment and recovery. The Johns Hopkins team is training a computer algorithm to recognize changes in the patient’s features, such as the paralysis of certain facial muscles or unusual eye movements, that might indicate damage to the brain from a stroke as opposed to seizures, severe migraines, or anxiety disorders.
Meanwhile, other researchers at the Massachusetts Institute of Technology are looking at facial recognition to diagnose the progression of amyotrophic lateral sclerosis, or ALS, a degenerative nerve disease that affects the muscles. And a Florida-based startup has developed a tool to help pediatricians diagnose rare genetic conditions by analyzing images of children’s facial features.
Florida-based biotech firm FDNA has developed a software program that aims to use facial recognition to diagnose rare genetic conditions in young children. The Face2Gene platform allows a doctor to upload scans of a patient’s face to a smartphone app and then get a recommendation on whether the image might indicate one of 1,500 conditions or syndromes associated with facial features. The platform has 47,000 users, including geneticists, neurologists, pediatric specialists, and researchers.
In Boston, researchers at Massachusetts General Hospital and MIT are using facial recognition to identify and track ALS, a progressive neurodegenerative disease that affects nerve cells in the brain and spinal cord, which leads to the deterioration of muscles affecting movement, speech, and eventually breathing. The team is working with EverythingALS, a nonprofit patient group that is part of a foundation set up to speed methods of diagnosis and potential cures for the disease.
Why it’s important – Early research efforts point to a future in which facial scans, perhaps embedded in a smartphone camera or even a bathroom mirror, might monitor our general health while picking up signs of long-term neurological ailments such as dementia. Some researchers believe algorithms might even be used to track how well a treatment or drug works by detecting changes in a person’s face. However, as AI tackles health conditions with multiple causes — such as heart disease, cancer, or dementia — computer scientists who develop the algorithms will have to work closely with doctors to explain how the AI makes the decisions that lead to its diagnosis.
Infographic of the week – Olivier Gevaert and the team at Stanford University identify federated learning as a unique solution to this challenge that also enables the proliferation and active sharing of digital twin technology without revealing patient information. Federated learning is a technique that uses a decentralized approach to training machine learning models. Rather than collecting local data samples onto large servers for constant fine-tuning of machine learning models, federated learning allows devices to train and update models without explicitly exchanging data while keeping the data locally on the device and only sharing the model updates. Here is the paper in The Lancet https://lnkd.in/gTRQiFes
Apple Plans AI-Powered Health Coaching Service, Mood Tracker and iPad Health App
Apple Inc. is working on an artificial intelligence-powered health coaching service and new technology for tracking emotions, its latest attempt to lock in users with health and wellness features. Mark Gurman reports on the plans in his Bloomberg article online. The new coaching service — codenamed Quartz — is designed to keep users motivated to exercise, improve eating habits and help them sleep better, according to people who know the project. The idea is to use AI and data from an Apple Watch to make suggestions and create coaching programs tailored to specific users, said the people, who asked not to be identified because the initiatives haven’t been announced yet.
The tools for tracking emotion and managing vision conditions, such as nearsightedness, will be added to the health app this year. The initial version of the emotion tracker will let users log their mood, answer questions about their day and compare the results over time. But in the future, Apple hopes the iPhone could use algorithms to determine a user’s mood via their speech, what words they’ve typed, and other data on their devices.
Why it’s important – The move is part of a broader health push at the company, which has made such features central to its devices, especially the Apple Watch. Its latest efforts also include expanding the health app to the iPad and features that could help users with poor vision. It will be interesting to see how much airtime these developments receive at the annual WWDC conference on June 5th. Stay tuned.
Podcast of the week – The world lost a powerful voice and advocate for patients’ rights this week. I was deeply saddened by the news of Casey Quinlan H.U.M.A.N.🌟 passing. Casey fiercely advocated for all things #PatientsIncluded, #GimmeMyDamnData, equity, inclusion, and burning down the status quo that harmed patients. Here’s Casey talking with Grace Cordovano, Ph.D., BCPA, on (no surprises) The Value of Our Medical Information: https://open.spotify.com/episode/7oR2dVLFdlmHch9HNADjuE
Two-component system could offer a new way to halt internal bleeding
Anne Trafton in MIT News that MIT engineers have designed a two-component system that can be injected into the body and help form blood clots at the sites of internal injury. These materials, which mimic how the body naturally forms clots, could offer a way to keep people with severe internal injuries alive until they can reach a hospital. Unlike previously developed hemostatic systems, the new MIT technology mimics the actions of both platelets — the cells that initiate blood clotting — and fibrinogen, a protein that helps forms clots.
Why it’s important – Blood loss from traumatic events such as car crashes contributes to more than 2.5 million deaths per year worldwide. This blunt trauma can cause internal bleeding from organs such as the liver, which is difficult to detect and treat. In such cases, it’s critical to stop the bleeding as soon as possible until a patient can be transported to the hospital for further treatment. Finding ways to prevent internal bleeding could significantly impact the armed services, where delayed treatment for internal hemorrhage is one of the largest causes of preventable death.
Amazon pulls the plug on Halo health tracking devices
Amazon announced it would close its Halo division. It is notifying employees in the U.S. and Canada of layoffs and telling Halo users that the device and app will no longer function as of August 1. Jessica Hagen reports on this development in her article in MobiHealthNews. Amazon Halo is a wrist-worn health tracker with an accompanying app that uses health metrics designed to give users a comprehensive look at their health and wellness and to provide actionable recommendations to make improvements. Customers will be provided full refunds on Amazon Halo Band, Amazon Halo View, Amazon Halo Rise, and Amazon Halo accessory band purchases made within the past 12 months. They can also receive refunds for unused Halo subscription fees. The company said health data pertaining to the Halo wearables would also be deleted on August 1.
Why it’s important – This announcement underscores the difficulties that even large tech companies like Amazon have in getting traction in the health wearables space. The company entered the wearable device market in August 2020 with the release of Halo. It has since added new features to its wearable, including Movement Health, and has updated the Halo line, adding the Halo View in 2021 and Halo Rise in 2022.
Top Smart Algorithms In Healthcare
Dr. Bertalan Mesko and his team at The Medical Futurist Institute posted this article online this week. As artificial intelligence tools have been invading more or less every area of healthcare, they made a list to keep track of the top AI algorithms aiming for better diagnostics, more sophisticated patient care, or further sighted predictions of diseases.
Why it’s important – By enumerating the top AI tools they discovered in healthcare so far, they also aim to add what they believe is already useful for the work of medical professionals.
A simple paper test could offer early cancer diagnosis
Another article from Anne Trafton in MIT News. MIT engineers have designed a new nanoparticle sensor that could enable early cancer diagnosis with a simple urine test. The sensors, which can detect many different cancerous proteins, could also be used to distinguish the type of tumor or how it is responding to treatment. The nanoparticles are designed so that when they encounter a tumor, they shed short DNA sequences excreted in the urine. Analyzing these DNA “barcodes” can reveal distinguishing features of a particular patient’s tumor. The researchers designed their test to be performed using a strip of paper, similar to an at-home Covid test, which they hope could make it affordable and accessible to as many patients as possible.
Why it’s important – This kind of testing could be used not only for detecting cancer but also for measuring how well a patient’s tumor responds to treatment and whether it has recurred after treatment. The researchers are now working on further developing the particles with the goal of testing them in humans.
A research team airs the messy truth about AI in medicine — and gives hospitals a guide to fix it
In public, hospitals rave about artificial intelligence. They trumpet the technology in press releases, plaster its use on billboards, and sprinkle AI into speeches touting its ability to detect diseases earlier and make health care faster, better, and cheaper. But on the front lines, the hype is smashing into a starkly different reality. Casey Ross in Stat reports that a new report aims to drag these tensions into the open through interviews with physicians and data scientists struggling to implement AI tools in healthcare organizations nationwide. Their unvarnished reviews, compiled by researchers at Duke University, reveal a yawning gap between the marketing of AI and the months, sometimes years, of toil it takes to get the technology to work the right way in the real world.
The research team, dubbed the Health AI Partnership, has leveraged the findings to build an online guide to help health systems overcome implementation barriers that most organizations now stumble through alone. It’s a desperately needed service at a time when the adoption of AI for decision-making in medicine is outpacing efforts to oversee its use.
Why it’s important – The challenges uncovered by the project point to a dawning realization about AI’s use in health care: building the algorithm is the easiest part of the work. The real difficulty lies in figuring out how to incorporate the technology into the daily routines of doctors and nurses and the complicated care delivery and technical systems surrounding them. AI must be finely tuned to those environments and evaluated within them so that its benefits and costs can be clearly understood and compared. As it stands, health systems are not set up to do that work — at least not across the board. Many are hiring more data scientists and engineers. But those specialists often work in self-contained units that help build or buy AI models and then struggle behind the scenes to keep them working properly.
These microbes found in tumors promote cancer. What if we just kill them?
Most bacteria in the human body help us thrive, but recent studies show that some infiltrate tumors, helping them grow, spread, and become more difficult for the immune system to destroy. National Geographic’s Sanjay Mishra reports (subscription required) that a study published recently in Nature shows that bacteria in oral and colorectal tumors can directly promote cancer by suppressing the human immune response and helping cancer cells spread more rapidly. An accompanying study published in the journal Cell Reports finds that some anticancer drugs, such as 5-fluorouracil, may be effective because they also kill the bacteria which help the tumor develop.
Why it’s important – Together, these two studies suggest that understanding the relationship between tumors and their resident microbes could be vital for fighting and eliminating certain cancers. So far, Bullman’s study shows that 15 percent of the 1,846 screened bioactive compounds that can kill F. nucleatum and other microbes also have potential as cancer chemotherapy drugs. That suggests that existing drugs can be reevaluated for their efficacy as both anticancer drugs and antimicrobial drugs— specifically targeting tumor-dwelling bacteria.
FDA approves first-ever fecal transplant pill to restore gut bacteria
The Food and Drug Administration (FDA) has announced the approval of the first-ever pill for fecal transplants, marking a significant milestone. Mrigakshi Dixit reviews this approval in her article in Interesting Engineering online. Seres Therapeutics, based in Massachusetts, developed the new pill after rigorously testing this version of the stool-based treatment. The FDA approved the prescription of pills based on a study of nearly 180 patients. According to the findings, approximately 88 percent of patients who followed the pill regimen did not experience reinfection after eight weeks. On the other hand, reinfection occurred in roughly 60 percent of those who received dummy pills, the Associated Press reported.
Why it’s important – The pill was created for people at risk of reinfections caused by the bacteria Clostridium difficile (C. diff). This bacteria frequently causes symptoms such as severe nausea, stomach ache, and diarrhea. Developed using healthy bacteria found in human waste, the pill could be an effective tool to fight gut infections. According to experts, this new pill method makes fecal transplants easier and less invasive.
Kaiser Foundation Hospitals’ new nonprofit Risant Health is acquiring Geisinger Health
While not a technology article, it’s one announcement this week that generated a buzz online and in print. The move was announced Wednesday by both the Kaiser Foundation Hospitals and Geisinger Health. The definitive agreement will make Geisinger the first health system to join Risant Health. Susan Morse was one of the dozens of writers posting on the announcement in her article in Healthcare Finance online. Geisinger will maintain its name and mission and continue working with other health plans, employed physicians, and independent providers. Risant Health will operate separately and distinctly from Kaiser Permanente’s core integrated care and coverage model while building upon Kaiser Permanente’s 80 years of expertise in value-based care.
Why it’s important – Risant Health is a new nonprofit organization created by Kaiser Foundation Hospitals to expand and accelerate the adoption of value-based care in diverse, multi-payer, multi-provider, community-based health system environments. It is expected to grow by acquiring and connecting a portfolio of like-minded, nonprofit, value-oriented community-based health systems anchored in their respective communities. Health systems that become part of Risant Health will continue to operate as regional or community-based health systems while gaining expertise, resources, and support through Risant Health’s value-based platform, Kaiser said. In the announcement, Kaiser said it hoped to invest $5 billion in Risant over the next five years in addition to its spending on Kaiser’s core operations. The company expects to add five or six health systems to Risant in that time. This will be one to watch for sure.