Clinical Decision Support

Follow this topic Ask about this topic

Clinical decision support studies how computer systems can help clinicians interpret patient records, identify risks, choose tests, and plan treatment. Approaches range from statistical and causal models to Bayesian reasoning, reinforcement learning, guideline rules and knowledge graphs, and language-model systems using retrieval or multiple agents; hybrid designs often use AI to extract information and deterministic logic to apply clinical rules. Systems are tested on electronic health records, guideline-based cases, medical images, and medication tasks, with growing use of reader studies and prospective workflow evaluations. A central challenge is that strong benchmark accuracy does not ensure safe performance with incomplete or shifting data, and systems must manage uncertainty, harmful errors, clinician oversight, and fit with real workflows.

Latest papers

244 papers27 papers in the last four weeks, up 42% on the four weeks before. 0.2% of all new papers.

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations
Dec 1, 2025David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj +54Healthcare Clinical Decision Support
MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support
Nov 20, 2025Elias Hossain, Md Mehedi Hasan Nipu, Maleeha Sheikh +5Selective Prediction Healthcare
College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA · Department of Computer Science and Engineering, North South University, Dhaka 1229, Bangladesh · Department of Electrical and Computer Engineering, Purdue University Fort Wayne, Fort Wayne, IN 46805, USA +4
Timely Clinical Diagnosis through Active Test Selection
Oct 21, 2025Silas Ruhrberg Estévez, Nicolás Astorga, Mihaela van der SchaarClinical Decision Support Clinical Decision-Making
University of Cambridge Cambridge, UK
Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription
Feb 4, 2025Mahdi Alkaeed, Sofiat Abioye, Adnan Qayyum +6Medical LLMs Open-Weight Language Models
Department of Computer Science and Engineering, College of Engineering, Qatar University, Doha, Qatar · Birmingham City University, Birmingham, United Kingdom · College of Science and Engineering, Hamad Bin Khalifa University (HBKU), Doha, Qatar +2

Dec 1, 2025J/K move · Enter open · S save

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

David Wu, Fateme Nateghi Haredasht, Saloni Kumar Maharaj, Priyank Jain+53

Healthcare Clinical Decision Support Human-in-the-Loop AI AI Safety Evaluation Clinical Language Model Evaluation

Open paper AskPDF arXiv

Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety profiles remain poorly characterized. We present NOHARM (Numerous Options Harm Assessment for Risk in Medicine), a 1,100-task benchmark of primary care-to-specialist consultation cases to measure the frequency and severity of potentially harmful errors from LLM-generated medical consultation recommendations. NOHARM covers 10 specialties, with 12,747 expert annotations for 4,249 clinical management options. Across 20 notable LLMs and 4 widely used retrieval-augmented generation (RAG) clinical AI tools, direct application of recommendations carried potential for severe harm in up to 24.6% of cases, with errors of omission accounting for more than 80% of severe errors. Harm potential was not uniform across systems, with clinical AI tools outperforming generalist LLMs, and multi-agent AI teaming further improving performance in generalist models. In a randomized study of 101 U.S.-licensed generalist physicians, AI assistance improved physician performance compared to conventional resources. However, AI-assisted physicians frequently omitted valuable AI-generated recommendations and still scored lower than many AI systems alone. Had those recommendations been incorporated, combined human-AI responses would have outperformed both the human and AI system as used, suggesting complementary strengths and unrealized potential in human-AI teaming. Collectively, these results show that despite strong performance on medical knowledge benchmarks, widely used AI tools can produce medical consultation advice with the potential for severe harm, and highlight the need for explicit measurement of clinical safety. The benchmark and leaderboard are publicly available to support ongoing evaluation and improvement of AI systems used for clinical care.

Latest papers

First, do NOHARM: a medical safety benchmark and randomized study of physician and AI teaming on clinical consultations

MedBayes-Lite: A Clinical Uncertainty Governance Layer for Risk-Aware Medical Decision Support

Timely Clinical Diagnosis through Active Test Selection

Open Foundation Models in Healthcare: Challenges, Paradoxes, and Opportunities with GenAI Driven Personalized Prescription