What type of study is this?

This is a Validation Study study.

December 10, 2025BioengineeringOpen Access

An External Validation Study on Two Pre-Trained Large Language Models for Multimodal Prognostication in Laryngeal and Hypopharyngeal Cancer: Integrating Clinical, Treatment, and Radiomic Data to Predict Survival Outcomes with Interpretable Reasoning

View Full Paper

Ask AI

Bookmark

Authors

External validation reveals that language models predict mortality and recurrence in hypopharyngeal cancer, highlighting the role of clinical data.

Integration of radiomic features improved mortality and recurrence predictions in hypopharyngeal cancer.
GPT-4o achieved peak AUC of 0.730 for mortality prediction, while Gemma-2-27b reached 0.736.
Analysis of patient data included sensitivity, specificity, and Kaplan–Meier survival analysis.
The study highlights the potential of language models in enhancing prognostic stratification in clinical settings.

Yap et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

External validation reveals that language models predict mortality and recurrence in hypopharyngeal cancer, highlighting the role of clinical data.