Tag

Clinical Decision Support

All articles tagged with #clinical decision support

Harvard study finds AI outperforms doctors in emergency triage
technology27 days ago

Harvard study finds AI outperforms doctors in emergency triage

A Harvard Science study shows AI systems outperformed human doctors in emergency department triage using the same electronic health records; AI reached 67% exact/close diagnoses vs 50–55% for humans and performed better on longer-term treatment planning (89% vs 34%). However, the test used only text-based data and did not assess signals like distress or appearance, framing AI as a second-opinion tool rather than a replacement for clinicians. Experts see AI as potentially reshaping medicine while emphasizing accountability and ongoing evaluation.

Early-stage medical AI struggles to diagnose, study finds
healthcare1 month ago

Early-stage medical AI struggles to diagnose, study finds

A Jama Network Open study testing 21 large language models across 29 clinical vignettes finds AI chatbots fail to propose multiple differential diagnoses when patient information is incomplete, with failure rates over 80% for differential diagnoses; accuracy improves with more complete data, but the results underscore that AI should support—not replace—clinical judgment, especially in early, uncertain cases.

OpenEvidence Secures $210M to Revolutionize Medical Search and Longevity
technology10 months ago

OpenEvidence Secures $210M to Revolutionize Medical Search and Longevity

OpenEvidence, a rapidly growing medical AI platform used by over 40% of U.S. physicians, announced a $210 million Series B funding round at a $3.5 billion valuation, and launched OpenEvidence DeepConsult™, an AI agent designed to assist physicians with advanced medical research, aiming to improve clinical decision-making and patient outcomes.

AI's Impact on Medicine: Doctors Unprepared, ChatGPT Outperforms Students, Eye Care Falls Short
healthcare2 years ago

AI's Impact on Medicine: Doctors Unprepared, ChatGPT Outperforms Students, Eye Care Falls Short

A new study warns that physicians are not adequately prepared for the integration of artificial intelligence (AI) tools, such as clinical decision support (CDS) algorithms, into clinical practice. The success of these technologies depends on physicians' understanding of these tools, which is currently lacking. The study recommends targeted training and a hands-on learning approach to enhance physicians' understanding of AI tools. The University of Maryland School of Medicine has proposed incorporating explicit coverage of probabilistic reasoning tailored to CDS algorithms in medical education and clinical training. The launch of the Institute for Health Computing aims to educate and train healthcare providers on the latest technologies, including AI, to enhance disease diagnosis, prevention, and treatment.

The Future of Medicine: A.I. Could Replace Doctors Sooner Than Expected
healthcare-technology2 years ago

The Future of Medicine: A.I. Could Replace Doctors Sooner Than Expected

Artificial intelligence (AI) devices may soon take on the roles of doctors, with machine learning and natural language processing being the main technologies driving this transformation. AI tools are already being used in healthcare for administrative functions, image analysis, clinical decision support, and even fully automated diagnosis and treatment. While regulatory challenges and concerns about errors in training datasets remain, the potential of AI in improving healthcare outcomes and addressing financial challenges is significant. As the quality and scope of clinical data continue to grow, these tools will increasingly enhance the productivity of providers and may even substitute for them in certain cases.