From JAMA Network Open: eCART outperformed the other #AI and non-AI early warning scores, identifying more deteriorating patients with fewer false alarms and sufficient time to intervene. https://ja.ma/40gE5dD
Updates
-
Will patients drive #AI adoption in health care? ⚕️ Roy Perlis, Editor in Chief of JAMA+ AI, shares his perspective while attending #JAMASummit AI. Follow JAMA+ AI for the best of the JAMA Network’s content exploring the science of artificial intelligence and digital medicine and its application in health and health care.
-
From JAMA Internal Medicine: Findings show that implementation of TriageGO, an #AI–informed, outcomes-driven decision support system for ED triage, led to a wider distribution of patients with chest pain across ED triage levels. https://ja.ma/3YlvJyO
-
What's the most crucial factor for success in medical #AI? 📊 David Ouyang, MD, a cardiologist at Cedars-Sinai, shares his perspective while attending #JAMASummit AI. Follow JAMA+ AI for the best of the JAMA Network’s content exploring the science of artificial intelligence and digital medicine and its application in health and health care.
-
From JAMA Ophthalmology: A deep learning algorithm accurately discriminated between potentially blinding but treatable arteritic anterior ischemic optic neuropathy from non-ischemic anterior ischemic optic neuropathy. https://ja.ma/3AdkLDA
-
"AI is already in our practice and how we care for patients." 🏥 JAMA Associate Editor and JAMA Network AI Editor Rohan Khera shares his perspective while attending #JAMASummit AI. Follow JAMA+ AI for the best of the JAMA Network’s content exploring the science of artificial intelligence and digital medicine and its application in health and health care.
-
Getting genuinely useful new tech, from wearables to clinical decision support, into the clinic has proven surprisingly challenging. Tanzeem K. Choudhury, PhD, of Cornell Tech joins JAMA+ AI Editor in Chief Roy H. Perlis, MD, MSc, to discuss how to take research into the real world in a way that is scalable and affordable. https://ja.ma/3UfXpns
-
From JAMA Network Open: Existing suicide risk #MachineLearning models worked well in an American Indian population, and performed better than a combined indictor of a positive suicide risk screen result, history of attempt, and recent suicidal ideation. https://ja.ma/3Ueaz4t
-
From JAMA Network Open: Nurses had a more favorable view of LLM draft replies to patient messages than other healthcare workers; >90% of nurses found the LLM improved efficiency, empathy and tone. https://ja.ma/3YovvIq
-
From JAMA: In this Special Communication, Michael Howell, Greg Corrado, and Karen DeSalvo examine how developments with #AI can help decision-makers improve health care while also recognizing its risks. https://ja.ma/4eMX2sO