Large Language Models ↔ clinical decision-making

Relations (1)

related 2.32 — strongly supporting 4 facts

Large Language Models are evaluated for their role in clinical decision-making through academic research [1] and specialized testing environments like AgentClinic [2]. Furthermore, their utility is constrained by medical hallucinations [3] and a lack of causal reasoning [4], both of which directly impact their reliability in clinical decision-making processes.

Facts (4)

Sources

Medical Hallucination in Foundation Models and Their ... medrxiv.org medRxiv 2 facts

claimLarge Language Models (LLMs) exhibit systematic errors known as medical hallucinations, where the models generate incorrect or misleading medical information that can adversely affect clinical decision-making and patient outcomes.

claimLarge Language Models primarily rely on statistical correlations learned from text rather than the causal reasoning required for effective clinical decision-making.

Bridging the Gap Between LLMs and Evolving Medical Knowledge arxiv.org arXiv 1 fact

referencePaul Hager, Friederike Jungmann, Robbie Holland, Kunal Bhagat, Inga Hubrecht, Manuel Knauer, Jakob Vielhauer, Marcus Makowski, Rickmer Braren, Georgios Kaissis, et al. published 'Evaluation and mitigation of the limitations of large language models in clinical decision-making' in 2024.

A Comprehensive Benchmark and Evaluation Framework for Multi ... arxiv.org arXiv 1 fact

referenceAgentClinic is a multimodal agent environment that treats clinical decision-making as a sequential task involving external tools and electronic health records, demonstrating that interactive diagnosis is more challenging for Large Language Models than static answering.