A new study led by investigators from Mass General Brigham has found that ChatGPT was about 72 percent accurate in overall clinical decision making, from coming up with possible diagnoses to making final diagnoses and care management decisions.
Reviewed by Lily Ramsey, LLMAug 22 2023 The large-language model artificial intelligence chatbot performed equally well in both primary care and emergency settings across all medical specialties. The research team's results are published in the Journal of Medical Internet Research.
Marc Succi, MD, corresponding author, associate chair of innovation and commercialization and strategic innovation leader at Mass General Brigham and executive director of the MESH Incubator The study was done by pasting successive portions of 36 standardized, published clinical vignettes into ChatGPT. The tool first was asked to come up with a set of possible, or differential, diagnoses based on the patient's initial information, which included age, gender, symptoms, and whether the case was an emergency.
Related Stories"ChatGPT struggled with differential diagnosis, which is the meat and potatoes of medicine when a physician has to figure out what to do," said Succi. "That is important because it tells us where physicians are truly experts and adding the most value-;in the early stages of patient care with little presenting information, when a list of possible diagnoses is needed.
Danmark Seneste Nyt, Danmark Overskrifter
Similar News:Du kan også læse nyheder, der ligner denne, som vi har indsamlet fra andre nyhedskilder.
Short-term use of immunosuppressants not linked to cancer riskRelatively short-term use of immunosuppressant medications to control an inflammatory disease was not associated with an increased risk of later developing cancer, according to new research led by scientists at the University of Pittsburgh and Mass Eye and Ear, a member of the Mass General Brigham health care system, and published in the journal BMJ Oncology.
Læs mere »
ChatGPT shows 'impressive' accuracy in clinical decision makingA new study led by investigators from Mass General Brigham has found that ChatGPT was about 72% accurate in overall clinical decision making, from coming up with possible diagnoses to making final diagnoses and care management decisions.
Læs mere »
Goldman Sachs explores investment adviser sale in retreat from mass marketPersonal financial management business grew from United Capital acquisition in 2019
Læs mere »
Driver killed, engine block launched into home after crash in western Mass.A 19-year-old man was killed and his car’s engine block was launched into a local home after a crash Sunday night in western Massachusetts. The incident began at 8:45 p.m. Sunday when a state police trooper tried to stop a Nissan Altima on Route 202 in Belchertown. The driver sped away from the trooper, ran a red light at the…
Læs mere »
Estrogen-negative cancers respond to anti-estrogenic therapies, study showsAnti-estrogenic therapies can suppress the growth of cancer that does not express estrogen receptors; when combined with immune checkpoint inhibitor therapies, they halt tumor progression in mice models.
Læs mere »