Incorporating patient values in large language model recommendations for surrogate and proxy decisions

Incorporating patient values in large language model recommendations for surrogate and proxy decisions
Critical Care Explorations; Victoria J Nolan, Jeremy A Balch, Naveen P Baskaran, Benjamin Shickel, Philip A Efron, Gilbert R Upchurch Jr, Azra Bihorac, Christopher J Tignanelli, Ray E Moseley, Tyler J Loftus; 8/24
Surrogates, proxies, and clinicians making shared treatment decisions for patients who have lost decision-making capacity often fail to honor patients' wishes, due to stress, time pressures, misunderstanding patient values, and projecting personal biases. Advance directives intend to align care with patient values but are limited by low completion rates and application to only a subset of medical decisions. [Likert] scores were highest when patient values were captured as short, unstructured, and free-text narratives based on simulated patient profiles. This proof-of-concept study demonstrates the potential for LLMs [large language models] to function as support tools for surrogates, proxies, and clinicians aiming to honor the wishes and values of decisionally incapacitated patients.