American hospitals are rolling out AI chatbots in patient portals as more people seek health advice from large language models. Hartford HealthCare and K Health's PatientGPT is expanding to tens of thousands of patients this week, whilst Epic's Emmie chatbot is being deployed by systems including Sutter Health and Reid Health. A KFF poll found one in three American adults have used AI chatbots for health information, with 19 per cent citing inability to afford care. However, a Nature Medicine study showed chatbots correctly identified medical conditions only 33 per cent of the time when users created their own prompts, compared with 95 per cent accuracy in controlled scenarios. Experts question whether chatbots improve patient outcomes, with concerns about monitoring, liability and whether this addresses underlying care gaps in America's underperforming healthcare system.

Hartford HealthCare and K Health have launched PatientGPT, an AI system that provides 24/7 patient support whilst accessing secure medical records within the healthcare network. The tool is rolling out in beta to a limited number of patients through Hartford HealthCare's patient portal. PatientGPT helps patients understand lab results, ask health questions based on their medical history, identify medication interactions, and connect to virtual or in-person care. The system operates within HIPAA-compliant infrastructure and does not diagnose or prescribe treatment autonomously. Developed by K Health over nearly a decade, the AI uses specialised agents designed to educate patients within clinical guardrails. Available only to patients aged 18 and over in Connecticut, it escalates to human clinicians when necessary. Patient data is not used to train external AI models.

What You Should Know:– A new study published in Annals of Internal Medicine from K Health – a Clinical AI platform has shed light on the potential of artificial intelligence (AI) to enhance the quality of care in virtual urgent care settings.– The retrospective cohort study, conducted at Cedars-Sinai Connect, an AI-assisted virtual urgent care clinic, compared the initial diagnostic and management recommendations generated by AI with the final decisions made by physicians who had access to these recommendations.– The research, which analyzed 461 physician-managed virtual visits for adults presenting with common symptoms such as respiratory, urinary, vaginal, eye, or dental issues between June 12th and July 14th, 2024, revealed some compelling findings.AI and Physician AgreementThe initial AI recommendations and the final physician recommendations were in agreement for 56.8% of the visits. This suggests a significant level of overlap in their clinical assessments.Quality Assessment: AI Often Deemed SuperiorHowever, the most striking finding emerged when expert physician adjudicators evaluated the quality of both concordant and nonconcordant recommendations. Across the weighted study population, AI recommendations were more frequently rated as optimal (77.1%) compared to the decisions made by the treating physicians (67.1%). Further analysis showed that the quality scores were equal between AI and physicians in 67.9% of cases. Importantly, in the instances where the recommendations differed in quality, AI recommendations were rated as better in 20.8% of cases, while physician recommendations were deemed better in only 11.3% of cases.AI Strengths: Red Flags and Guideline Adherence:The study authors suggest that AI’s superior performance in certain situations might stem from its ability to more effectively identify critical red flags and adhere to established clinical guidelines. This could lead to more consistent and evidence-based initial recommendations.Physician Strengths: Adapting to Dynamic Information:On the other hand, physicians demonstrated an advantage in adapting their recommendations based on the evolving information gathered during the virtual consultation