There has been a lot of talk about the potential for AI in health, but most of the studies so far have been stand-ins for the actual practice of medicine: simulated scenarios that predict what the impact of AI could be in medical settings.<\/p>\n
But in one of the first real-world tests of an AI tool, working side-by-side with clinicians in Kenya, researchers showed that AI can reduce medical errors by as much as 16%.<\/p>\n
In a study available on OpenAI.com<\/a> that is being submitted to a scientific journal, researchers at OpenAI and Penda Health, a network of primary care clinics operating in Nairobi, found that an AI tool can provide a powerful assist to busy clinicians who can\u2019t be expected to know everything about every medical condition. Penda Health employs clinicians who are trained for four years in basic health care: the equivalent of physician assistants in the U.S. The health group, which operates 16 primary care clinics in Nairobi Kenya, has its own guidelines for helping clinicians navigate symptoms, diagnoses, and treatments, and also relies on national guidelines as well. But the span of knowledge required is challenging for any practitioner.<\/p>\n That\u2019s where AI comes in. \u201cWe feel it acutely because we take care of such a broad range of people and conditions,\u201d says Dr. Robert Korom, chief medical officer at Penda. \u201cSo one of the biggest things is the breadth of the tool.\u201d <\/p>\n Read More: A Psychiatrist Posed As a Teen With Therapy Chatbots. The Conversations Were Alarming<\/a><\/p>\n Previously, Korom says he and his colleague, Dr. Sarah Kiptinness, head of medical services, had to create separate guidelines for each scenario that clinicians might commonly encounter\u2014for example, guides for uncomplicated malaria cases, or for malaria cases in adults, or for situations in which patients have low platelet counts. AI is ideal for amassing all of this knowledge and dispensing it under the appropriately matched conditions. <\/p>\n Korom and his team built the first versions of the AI tool as a basic shadow for the clinician. If the clinician had a question about what diagnosis to provide or what treatment protocol to follow, he or she could hit a button that would pull a block of related text collated by the AI system to help the decision-making. But the clinicians were only using the feature in about half of visits, says Korom, because they didn\u2019t always have time to read the text, or because they often felt they didn\u2019t need the added guidance.<\/p>\n So Penda improved on the tool, called AI Consult, that runs silently in the background of visits, essentially shadowing the clinicians\u2019 decisions, and prompting them only if they took questionable or inappropriate actions, such as over prescribing antibiotics.<\/p>\n \u201cIt\u2019s like having an expert there,\u201d says Korom\u2014similar to how a senior attending physician reviews the care plan of a medical resident. \u201cIn some ways, that\u2019s how [this AI tool] is functioning. It\u2019s a safety net\u2014it\u2019s not dictating what the care is, but only giving corrective nudges and feedback when it\u2019s needed.\u201d<\/p>\n