Recommendations of K Health’s AI Physician Mode matched the quality of doctors' decisions in two-thirds of patient cases while offering higher quality recommendations overall in the remaining third
Findings presented at the breaking news scientific plenary session during the American College of Physicians (ACP) Internal Medicine Meeting 2025
K Health, the leading clinical AI Primary Care platform, announced novel study results showing that the recommendations of its AI Physician Mode matched doctors' clinical decisions in two-thirds of real patient cases, offering higher quality overall in the remaining third.
The study, conducted by investigators from Cedars-Sinai, Tel Aviv University, and K Health, used experienced primary care physicians to review and rate AI versus traditional physician recommendations for acute complaints in a virtual urgent care setting and found that AI guidance was more frequently rated as optimal than physicians’ actual care decisions.
The findings, presented as part of a scientific plenary session today at the American College of Physicians Internal Medicine Meeting, were also published simultaneously in the peer-reviewed journal Annals of Internal Medicine.
“We put AI to the test in real-world situations, not static textbook scenarios. Everyday primary care patients are messy, there are so many variables and factors—you’re dealing with complex human beings, and AI has to deal with incomplete data and a very diverse set of patients. We learned that if you train the AI on the treasure trove of de-identified clinical notes and use day-to-day provider care as an always-on reinforcement learning mechanism, you can reach the level of accuracy you would expect from a human doctor, sometimes even exceeding it,” said Ran Shaul, Co-founder & Chief Product Officer of K Health.
American healthcare can benefit from efficiencies in diagnosis that could create greater capacity to meet more complex patient care needs. K Health is hacking medicine for the masses with AI that is available 24/7 to deliver smarter, faster and better patient care. The company’s AI Physician Mode synthesizes a patient’s entire medical record before their primary care visit, then provides their healthcare provider with AI-driven clinical recommendations. It is already being used by some of the top health systems in the country, including Cedars-Sinai, Hackensack Meridian Health and Hartford HealthCare.
“This study validates what we've long believed at K Health—that AI trained on high-quality clinical data can transform healthcare delivery. We've harnessed billions of data points from patient medical records to enhance medical decision-making at the point of care in ways previously unimaginable," said Allon Bloch, Co-Founder and CEO at K Health. "By bringing together AI's processing power with physician expertise, we're establishing a new paradigm for patient care that combines access, accuracy, and clinical excellence."
The retrospective study was conducted using data from Cedars-Sinai Connect, a virtual primary and urgent care program that began in 2023. An extension of Cedars-Sinai’s in-person care, Cedars-Sinai Connect aims to expand virtual healthcare for patients in California through a mobile app that allows individuals to quickly and easily access Cedars-Sinai experts for acute, chronic, and preventive care.
The study reviewed 461 physician-managed visits with the AI recommendations offered to treating physicians from June 12 through July 14, 2024. Key medical issues addressed during these virtual urgent care visits were adults with respiratory, urinary, vaginal, vision or dental symptoms.
Expert physician review of AI and physician decision-making showed that in approximately two-thirds of cases, physicians made nearly or exactly the same clinical decisions as the AI recommendation. In the remaining third, AI recommendations were rated superior nearly twice as often as those of the doctors.
"The results of this study highlight the complementary strengths of AI and physician expertise," said Caroline Goldzweig, MD, Cedars-Sinai Medical Network chief medical officer and co-senior author of the study. "This study demonstrates the potential for responsible AI integration, allowing physicians to spend more time focusing on the critical aspects of patient care that require human connection."
The research found that potentially harmful recommendations occurred only 2.8% of the time with AI, versus 4.6% of the time with physicians. This may be in part due to how the AI Physician Mode strictly follows medical guidelines and is able to identify subtle details that physicians occasionally missed. In about 20% of cases, the AI did what good doctors do - it said 'I don't know' when it was not confident enough to make a recommendation, mirroring how experienced clinicians approach uncertainties.
For more information about K Health's AI-driven healthcare solutions, visit khealth.com
About K Health:
K Health is a Clinical AI platform that co-pilots with doctors to provide patients with access to higher quality medicine. Its suite of clinical AI agents enable both online and brick-and-mortar primary care delivery. K Health partners with Cedars-Sinai, Hackensack Meridian Health, Hartford HealthCare, and other leading systems. K Health was founded in 2016, has raised over $400M from leading investors, and is headquartered in New York City. Notable investors include Valor Equity Partners, Claure Group, Mangrove Capital Partners, 14W, Notable Capital, Lerer Hippeau, Primary Venture Partners, Comcast Ventures, PICO Venture Partners, Max Ventures, and other strategic healthcare partners. For more information, please visit khealth.com.
View source version on businesswire.com: https://www.businesswire.com/news/home/20250403068767/en/
