To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events
arxiv.org · 7,988 words · saved by 1 readers
N/A
To Recommend or Not to Recommend: Designing and Evaluating AI-Enabled Decision Support for Time-Critical Medical Events ANGELA MASTRIANNI, Drexel University, USA MARY SUHYUN KIM, Children’s National Hospital, USA TRAVIS M. SULLIVAN, Children’s National Hospital, USA GENEVIEVE JAYNE SIPPEL, Children’s National Hospital, USA arXiv:2505.11996v1 [cs.HC]…
related reading
- AI Triage Safety: HealthBench & Emergency Escalation | Counsel Healthcounselhealth.com
- AI for Decision Adviceforethought.org
- Medical AI Safety: We have a problem. – Lauren Oakden-Raynerlaurenoakdenrayner.com
- Medical AI Safety: Doing it wrong. – Lauren Oakden-Raynerlaurenoakdenrayner.com
- Three Challenges for AI-Assisted Decision-Making - PMCpmc.ncbi.nlm.nih.gov
- The impact of AI errors in a human-in-the-loop processlink.springer.com
- The Path to Medical Superintelligence | Microsoft AImicrosoft.ai
- Introducing HealthBench | OpenAIopenai.com
- Enabling physician-centered oversight for AMIEresearch.google
- AI for medicine is overhyped right now - by Dan Eltonmoreisdifferent.substack.com
- slow ai: ai that matches a human’s pace - jenny y. huangjennyhuang19.github.io
- Google’s AMIE Validates The Clinician Cockpit | Counsel Healthcounselhealth.com