What happened in health care technology this week, and why it’s important.
Epic is going all in on generative AI in healthcare. Here’s why a handful of health systems are eager to test-drive it
Heather Landi kicks off the coverage this week with her article in Fierce Healthcare online. UNC Health has been tapped to test-drive Epic’s generative AI tools to help overworked clinicians respond to a deluge of patient messages. The initial rollout will begin with five to 10 physicians at UNC Health. The program will use generative AI to auto-draft responses to some of the most common and time-intensive patient messages. The health system joins other early adopters from UC San Diego Health, the University of Wisconsin Health, and Stanford Health Care. Epic announced in April during the Healthcare Information and Management Systems Society Conference in Chicago that it was working with Microsoft to integrate large language model tools and AI into its electronic health record software. The health IT vendor and the tech giant are collaborating to combine the Azure OpenAI Service with Epic’s EHR software with an initial focus on drafting message responses.
“They’re going to be using this in the early-stage adoption to look for things like, ‘What is the accuracy of the text that the system is drafting?’ and, ‘What are the potential use cases in terms of how physicians can make it more effective for them?’ We also think that having this multispecialty approach we may help Epic understand where there may be opportunities for specialty-specific tweaking of the models to make it more effective for a given specialty.”Brent Lamm, UNC Health’s Senior Vice President and Chief Information Officer, UNC Health
Why it’s important – Physicians and informatics leaders will also evaluate the tech’s user interface to ensure it is easy for clinicians to use. The health system expects to eventually scale up the generative AI-based messaging tool to a broader group of physicians. Along with the draft message responses, Epic and Microsoft also are working on using generative AI to analyze medical records while looking for trends.
Infographic of the week – The opportunity for the retailers, led in market share by CVS Health’s Minute Clinic and Kroger’s The Little Clinic, is to serve up population health and a health data infrastructure/platform that can enable health citizens to have a data-enabled, contemporary #digitalhealth medical home. This model could also scale to under-served people.
Drug Delivery System for Chronic Diseases Created Using AI
Wilmer Eye Institute, Johns Hopkins Medicine researchers say they have used artificial intelligence models and machine-learning algorithms to successfully predict which components of amino acids that make up therapeutic proteins are most likely to deliver therapeutic drugs to animal eye cells safely. Published May 2 in Nature Communications, the new research showed that artificial intelligence-designed models accurately predicted an effective sequence of amino acids, also known as peptides or small proteins, that would bind to a particular chemical in rabbit eye cells and safely dispense medications over several weeks, reducing the need for frequent, strict treatment schedules. The team specifically investigated peptides that bind to melanin. This compound provides color to the eye but has the advantage of being widely present throughout specialized structures in eye cells.
“We believe we are well on the way to finding solutions in trying to improve patient care and quality of life using drug delivery systems. The ultimate goal is creating something that we can translate out of the lab and actually make people’s lives better.”Laura Ensign, Ph.D., Marcella E. Woll professor of ophthalmology at the Johns Hopkins University School of Medicine
Why it’s important – The project, a collaboration with researchers from the University of Maryland, holds promise for advancing new and more tolerable drug treatments for common chronic blinding eye diseases, including glaucoma and macular degeneration, which affect 3 million and about 20 million people in the United States, respectively. Current drug therapies for these diseases, consisting of multiple daily eyedrops or frequent eye injections, are effective. Still, such delivery systems may be difficult to sustain and tolerate over time and have encouraged scientific efforts to develop delivery systems that would bind to components of eye cells and safely extend the therapeutic impact of the medications they carry.
iHealthScreen receives FDA 510(k) for AI-enabled eye screening system
Jessica Hagen reports that iHealthScreen, maker of AI-enabled software for retinal imaging, received FDA 510(k) clearance for its iPredict Eye Screening System that leverages AI to help providers determine if a patient over 50 has age-related macular degeneration. The iPredict System screens for AMD by using AI to analyze high-resolution images of a patient’s eyes taken with a color fundus camera. The test can be done in five minutes, and results are available within 60 seconds.
Why it’s important – If a medical task is repetitive and/or data-driven, it is ripe for automation. Screening the eye for signs of age-related macular degeneration is one of those. In 2019, 19.8 million individuals in the U.S. lived with some form of age-related macular degeneration, an increase of more than 2.75 times previous estimates, according to a study in JAMA Ophthalmology.
Video of the week – Can Our Current Workforce Meet Patient Expectations: Tina Shah, MD, set the stage for the Top of Mind Summit with a keynote address that tackled a pervasive and challenging issue in health care: provider burnout. Her presentation, which came on the first night of the Summit, set the stage for many of the sessions that followed the next day. Whether it was intentional or not, the audience at Top of Mind heard again and again from a variety of speakers that burnout was an issue affecting many parts of health systems.
Dr. Shah offered three concluding thoughts on how health systems can move forward and ensure that their clinicians are prepared to meet the demands of patients. First, technology solutions must be co-designed with the patient and provider experience in mind. Second, technology should be leveraged to reduce the cognitive load on clinicians. It needs to be better integrated and operate in the background to make care delivery easier for clinicians, not more burdensome. And finally, clinicians simply need more time and greater resources to confront all the challenges they’re facing. “And when we do that … there’s no limit in where we can go,” she said.
You can view Dr. Shah’s entire presentation here: https://connectedmed.com/resources/top-of-mind-summit-opens-with-keynote-focused-on-burnout-in-health-care/?utm_source=ccminsights&utm_medium=email&utm_content=tom23-shah-keynote-burnout-blogpost-insightsQ22023&utm_campaign=insights-23
State of Digital Health Q1’23 Report
CB Insights’ latest report (subscription required) reveals that global digital health funding holds steady at $3.4B in Q1’23 after plummeting for four straight quarters. Care delivery and navigation tech companies saw 44% of all funding and 37% of all deals across seven digital health categories. Half of the category’s funding went to 5 of the quarter’s top 10 deals. As a result, the category also saw the highest average disclosed deal size ($12.6M).
Why it’s important – Global digital health funding and deals stabilize after a year of decline. That’s good news for startups seeking funding to advance their business goals in 2023.
Brain signatures for chronic pain identified in a small group of individuals
For the first time, researchers have recorded pain-related data from inside the brain of individuals with chronic pain disorders caused by stroke or amputation (phantom limb pain). Four participants, three with post-stroke pain and one with phantom limb pain were surgically implanted with electrodes targeting their ACC and OFC. Several times a day, each participant was asked to answer questions related to how they would rate the pain they were experiencing, including strength, type of pain, and how their pain level was making them feel emotionally. They would then initiate a brain recording by clicking a remote-control device, which provided a snapshot of the activity in the ACC and OFC at that exact moment. Using machine learning analyses, the research team was able to use activity in the OFC to predict the participants’ chronic pain state.
Why it’s important – The findings are a key step to identifying pain-specific biomarkers toward personalizing pain management for individuals, leading to the development of new technologies and advances to better understand brain circuits, a major component of the NIH BRAIN Initiative. Chronic pain is one of the most significant contributors to disability worldwide. Neuropathic pain is caused by damage to the nervous system itself. It most commonly occurs due to injury to the nerves in our bodies, but for the individuals in this study, their pain is thought to originate from the brain itself. This kind of pain does not respond well to current treatments and can be debilitating for people living with it. These findings, which represent a first step towards developing novel methods for tracking and treating chronic pain, were published in Nature Neuroscience and funded by the National Institutes of Health’s Brain Research Through Advancing Innovative Neurotechnologies (BRAIN) Initiative and the Helping to End Addiction Long-term Initiative, or NIH HEAL Initiative.
America’s drug shortages reach new heights
Shortages of cancer drugs and other life-saving medications are reaching their worst point in a decade, forcing physicians to develop workarounds and the Biden administration to mount an all-of-government response. Axios’ Tina Reed reports the story. There are more than 300 drugs in shortage, the highest since 2014, per the American Society for Health-System Pharmacists. While the Biden administration and Congress are both examining ways to address what has been dubbed a national security issue — including via a reauthorization of the Pandemics and All-Hazards Preparedness Act, or PAHPA. But solutions could be expensive and disruptive. The FDA can identify problems and work with manufacturers but lacks the expertise and, in some cases, authority to address more significant economic issues around the industry.
Why it’s important – The shortfalls are surfacing deeply entrenched problems in America’s drug supply chain, particularly around commonly-used generic drugs. A recent House hearing examined a “race to the bottom” in price that chills investment in manufacturing and can leave just one or two companies actively producing a drug in shortage. There are more than 300 drugs in shortage, the highest since 2014, per the American Society for Health-System Pharmacists. America’s drug shortage problem could get worse as generics makers cut back on manufacturing, but it’s unclear whether the government is capable of responding.
Finally, let’s remember all who have served our nation this Memorial Day weekend.