Becker's Hospital Review

42 INNOVATION financial incentives with quality to drive down costs. He said smaller health systems' move toward value-based care could stall if they "don't have access to the best practices, tools, technology, and systems — all of which Risant Health can bring." "In the face of exponentially increasing competition in the healthcare landscape, it is critical for healthcare organizations to be trailblazers," said Shari Rajoo, MD, vice president and chief medical officer for population health at Johnson City, Tenn.-based Ballad Health. "At this point, I remain very optimistic about what this could mean for new partnership possibilities for healthcare organizations and am excited to see what Risant Health yields." Payers are oen reluctant to enter into value-based care contracts because so much of what they do is set up for fee-for-service, said Catherine MacLean, MD, PhD, senior vice president and chief value medical officer of New York City-based Hospital for Special Surgery. Kaiser Permanente and Danville, Pa.-based Geisinger might be big enough to change all that. ey also have something else the disruptors don't — at least not yet. "CVS and Optum are focused on ambulatory care and do not own or control any hospitals," Dr. MacLean said. "Given that 40 percent of U.S. healthcare expenditures occur in the hospital, I think Risant will have greater control over total care costs through judicious use of hospitals and by managing hospital efficiencies." Hospital leaders watching Other health system executives say they're taking a wait-and-see approach on whether Risant Health is an approach that can be emulated. "at type of model allows you to have financial and operational alignment with our industry's mission — which is to take great care of our community and patients by keeping them healthy and well," said Jennifer Stephens, DO, chief value and ambulatory care officer for Allentown, Pa.-based Lehigh Valley Health Network. "However, the key to any of these ventures is to deliver outcomes aligned with that mission in an operationally efficient, patient-centric, and value- add manner. If they can't do that, they won't be successful." e optimistic view is that Kaiser Permanente "will be able to amalgamate their treasure trove of best-in-class electronic tools into a unified, enterprise-infrastructure platform for population health management," said Jeffrey Guterman, MD, chief research and innovation officer for the Los Angeles County Department of Health Services. He noted that the health system's EHR, KP HealthConnect, uses Epic as its core. "However, it has significant differences from other implementations of the country's most popular EHR," he said. "at, combined with the other unique structures found at Kaiser, is where the challenge for this development will be." Dr. Guterman said he hopes the "optimist in me" wins out and Risant Health speeds the "recognition that fee-for-service sick care has little to do with improving the health of a population." "If Risant can serve as the first nationwide platform to begin this journey of data-driven integrated outcomes, we all have a stake in its success," he said. Mr. Adams acknowledged that many disruptors have been better than health systems at responding to changing consumer expectations "but should not come at the price of further deteriorating our healthcare system." But that doesn't mean Risant is only competing with healthcare's newer entrants. Mr. Adams said it's also open to collaborating with them. "Our primary focus is on pushing back against fragmented, disconnected, sick-care-based healthcare in America today, and making the best of Kaiser Permanente available in more communities through new models," he said. "Over time, we will partner with other organizations that share our ambition." n ChatGPT on par with an 'intern or resident,' Mass General Brigham finds By Giles Bruce C hatGPT is 72 percent accurate at making clinical decisions, performing better at final diagnoses and worse at determining possible diagnoses, according to an Aug. 22 study by Mass General Brigham researchers. "No real benchmarks exist, but we estimate this performance to be at the level of someone who has just graduated from medical school, such as an intern or resident," said the study's corresponding author, Marc Succi, MD, associate chair of innovation and commercialization at Somerville, Mass.-based Mass General Brigham and executive director of its MESH Incubator, in an Aug. 22 news release. The researchers fed 36 published clinical scenarios into ChatGPT, asking it to come up with possible, or differential, diagnoses, then gave it additional information before requesting a final diagnosis and treatment plan, according to the study in the Journal of Medical Internet Research. The artificial intelligence chatbot was 77 percent accurate in its final diagnoses, 68 percent accurate in clinical management decisions such as what medications to take, and 60 percent accurate in differential diagnoses. Adam Landman, MD, CIO and senior vice president of digital at Mass General Brigham, said in the release that the health system "sees great promise" for large language models such as ChatGPT. "We are currently evaluating LLM solutions that assist with clinical documentation and draft responses to patient messages with a focus on understanding their accuracy, reliability, safety and equity," he stated. "Rigorous studies like this one are needed before we integrate LLM tools into clinical care." n

• Cover