Despite the positive results from the study, the researchers emphasized the study\u2019s limitations and raised concerns that their results may be used by others to suggest AI replace doctors. Dr. Adam Rodman, a general internis\u00ad\u00ad\u00adt and medical educator at Beth Israel Deaconess Medical Center and the co-author of the study, said<\/a> he gets \u201ca little bit queasy about how some of these results might be used.\u201d<\/p>\n \t\t \n\t\t\tDownload the SAN app today to stay up-to-date with Unbiased. Straight Facts\u2122.\t\t<\/p>\n \n\t\t\tPoint phone camera here\t\t<\/p>\n What did the studies find?<\/p>\n The research team tested the model in different ways. The first way tested against curated medical training cases. These cases are specifically designed to test doctors\u2019 diagnostic thinking and are just like the exams physicians take in school.\u00a0<\/p>\n In these tests, the AI model consistently outperformed across these scenarios. But the way that test where the AI really excelled was with historical real-world ER cases.\u00a0<\/p>\n During this test, researchers pulled patient cases from Beth Israel Deaconess Medical Center to get as close to real conditions as possible. The researchers noted that they gave the AI raw electronic health record data, which they described as \u201cmessy\u201d and similar to what actual doctors encounter.\u00a0<\/p>\n The team tested the data at two different points: when the patient arrived at triage and then later when the patient was ready for admission. In the first test, the AI got the correct diagnosis 67% of the time, compared to 50% and 55% for the two human doctors it measured against. By the time the patient was ready for admission, the AI\u2019s diagnosis jumped to 81%, compared to 70% and 79% for the human doctors.\u00a0<\/p>\n Although the tests were not conducted during the hospital visit, the researchers found that the AI was effective at making diagnoses.\u00a0<\/p>\n \u201cWe can definitively say \u2026 reasoning models can meet that criteria for making diagnostic reasoning at the highest levels of human performance,\u201d Rodman said, according to Vox.\u00a0<\/p>\n ChatGPT is still no doctor<\/p>\n While specific models developed for the medical field performed well in tests, that doesn\u2019t mean ChatGPT or other large language models are a replacement for a general physician. Something the researchers specifically noted.\u00a0<\/p>\n \u201dNo one should look at this and say we do not need doctors,\u201d Rodman said.<\/p>\n A previous study published in February in Nature Medicine<\/a> found that ChatGPT underestimated the severity of a patient\u2019s condition in 52% of cases.<\/p>\n \t\t\tStart your day with fact-based news.<\/p>\n![\"QR](\"https:\/\/www.newsbeep.com\/au\/wp-content\/uploads\/2026\/04\/app-download-block-qr-code.png\")
<\/p>\n