How is #AI transforming healthcare? #StanDOM 's Nigam Shah shares his insights & personal journey on NEJM AI's Grand Rounds Podcast. bit.ly/44LiGtg

GPT-4, together with retrieval-augmented generation, can precisely extract and compare medical guideline recommendations in oncology from different associations. Read the Case Study by Dyke Ferber et al.: nejm.ai/3WSVQ19

#ArtificialIntelligence #AIinMedicine

Original Article by Tej A. Patel et al.: Spending Analysis of Machine Learning–Based Communication Nudges in Oncology nejm.ai/4aq6oIb

#AIinMedicine

Perspective by Peter Szolovits, PhD: Large Language Models Seem Miraculous, but Science Abhors Miracles nejm.ai/4aqBIqe

On the latest episode of AI Grand Rounds, Dr. Nigam Shah from Stanford University advocates for a dual approach to AI in #healthcare : addressing current challenges with clinicians and exploring visionary strategies. Listen to the full episode: nejm.ai/ep18

#generativeAI

A Letter by Jeffrey M. Feit, MD, MSHA, about “Evaluation of Sepsis Prediction Models before Onset of Treatment” nejm.ai/3QJoRZd

A machine learning intervention for serious illness conversations saved over $13 million for patients with cancer by reducing end-of-life therapy and outpatient costs. Read the full study results by Tej A. Patel et al.: nejm.ai/4aq6oIb

RAG improves a GPT copilot in oncology guidelines questions. No RAG: 57% correct. RAG: 84% correct. Is that enough? The need for a human pilot remains, but attaching reliability evidence like this paper to a copilot can help clinicians make entrustment decisions. NEJM AI

Peter Szolovits, PhD, discusses the capabilities and incomprehensibility of large language models (LLMs) and their use in medicine. Read the Perspective “Large Language Models Seem Miraculous, but Science Abhors Miracles”: nejm.ai/4aqBIqe

Finally out in NEJM AI 🤖, led by Dykex from katherlab: 'GPT-4 for Information Retrieval and Comparison of Medical Oncology Guidelines'. We've developed a RAG pipeline using the GPT-4 API to answer medical oncology questions based on guidelines. Previous studies have claimed

1/ Is it possible for a machine-learning clinical intervention to align patient preferences and spending reductions?

In NEJM AI, we report on one of the first economic evaluations of a ML-based intervention as part of a prospective trial.

Link: ai.nejm.org/doi/full/10.10…

Original Article: “AI-MARRVEL — A Knowledge-Driven AI System for Diagnosing Mendelian Disorders” by Dongxue Mao, PhD, et al. nejm.ai/3WfeyQ5

#ArtificialIntelligence #AIinMedicine

Editorial: “Are Stronger Feature Representations All You Need for Histology Image Search?” by Drs. Richard J. Chen and Faisal Mahmood (@AI4Pathology) nejm.ai/4b7zhtl

#ArtificialIntelligence #AIinMedicine

In the latest episode of the AI Grand Rounds podcast, Dr. Nigam Shah shares his journey from training as a doctor in India to becoming a leading figure in biomedical informatics in the United States. Listen to the full episode: nejm.ai/ep18

Scaling Note Quality Assessment Across an Academic Medical Center with AI and GPT-4: nej.md/3vTyKMD