EUVIMEDEUVIMED entdecken
CrossrefInfokarte

Understanding uncertainty in large language model predictions of early death in critically ill patients: a conformal prediction approach

Fatemeh Shah-Mohammadi, Alexander Millar, Julio C. Facelli, Ramkiran Gouripeddi

JAMIA Open · 2026-05-05 · 9 (3)

DOI: 10.1093/jamiaopen/ooag108 ↗
AbstractBibliografische Angaben

Abstract

Abstract Background Early prediction of in-hospital death remains a significant challenge due to the limited availability of structured data during initial admission. Unstructured clinical notes, which often contain important observations and impressions, are an underutilized resource for real-time risk stratification. While leveraging recent advances in large language models (LLMs) is a promising approach to use this unstructured information, the lack of understanding of the uncertainty of LLM predictions, at the patient level, for such critical forecasts is a serious deterrence for their use in clinical settings. Objective This study aims to demonstrate the use of conformal prediction to evaluate the effectiveness and confidence in predicting in-hospital death probability for an individual patient using LLMs, specifically GPT-4o and unstructured clinical notes. Methods We applied conformal prediction to quantify the uncertainty of GPT-4o’s zero-shot predictions for in-hospital death, leveraging concatenated clinical notes documented from the first 24 h of intensive care unit (ICU) admission in MIMIC-III for patients with acute kidney failure who were admitted through the emergency department (ED). Results Across both classes “in-hospital death” and “in-hospital survive,” the GPT model performed better on the in-hospital death class, achieving precision of 0.52 (95% CI 0.48-0.56), recall of 0.93 (95% CI, 0.90-0.95), and F1-score 0.66 (95% CI, 0.63-0.70). The conformal prediction (CP) framework provided an overall empirical coverage of 90.4%, exceeding the target threshold of 90%. However, class-specific coverage was imbalanced, with 99.7% for the death and 81.1% for the survived class. Conclusions The model’s outputs exhibit overconfidence, particularly in cases of incorrect predictions. Integrating conformal prediction provides a promising approach to quantifying and calibrating uncertainty in large language model outputs for individual patient predictions, thereby enhancing their potential applicability for clinical decision-making.

Wissen, das zu Ihrer Arbeit passt.

Vom kostenlosen Einstieg über die persönliche Recherche bis zur vollständigen Research Suite.

Tarife ansehen →

Sind alle Verlagsvolltexte enthalten?

Nein. Bibliografische Nachweise, Abstracts und Volltexte sind unterschiedliche Inhalte. Ob ein Volltext verfügbar ist, hängt von der Quelle, Open Access und Ihren vorhandenen Lizenzen ab. Ein EUVIMED-Tarif ersetzt keine zusätzlichen Verlagsrechte.

Tarife ansehen →