Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
Abstract
Invasive mechanical ventilation is a lifesaving therapy, but timely, safe discontinuation is essential to preventing extubation failure (EF) and related risks to health. We present a novel approach to EF prediction that leverages features classified in free-text respiratory therapy notes using a large language model and logistic regression pipeline. Applied to a patient cohort from University of Washington Medicine, our method identifies clinically meaningful EF-related features that improve EF prediction performance when included alongside structured patient data. We further highlight how differences in target populations in prior EF prediction studies, such as heterogenous inclusion criteria and EF definition, can lead to systematic differences in model performance and hinder generalizability between studies.
Related
- Enhancing CFD-LES air pollution prediction accuracy using data assimilation
- Enhancing generalization in endwall film cooling prediction: Incorporating the superposition principle into transformer-based neural operators
- Dynamic control of carbon-ion radiation dose distribution amid respiratory motion challenges: A review of prediction research using geant4 and deep learning physics-constrained models.
- An integrated machine learning framework for cerebral aneurysm rupture status classification using clinical, morphological, and hemodynamic features
- Enhancing pair production with optimized chirped electric fields
BibTeX
@misc{chaiken2026enhancing,
title = {{Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes}},
author = {Izzy Chaiken and Aditya Khowal and Neha A. Sathe and Mark M. Wurfel and Lucy Lu Wang},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.17532},
eprint = {2609.17532},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.17532},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes
AU - Izzy Chaiken
AU - Aditya Khowal
AU - Neha A. Sathe
AU - Mark M. Wurfel
AU - Lucy Lu Wang
PY - 2026
DA - 2026/09/01
PB - arXiv
DO - 10.48550/arxiv.2609.17532
UR - https://arxiv.org/abs/2609.17532
AB - Invasive mechanical ventilation is a lifesaving therapy, but timely, safe discontinuation is essential to preventing extubation failure (EF) and related risks to health. We present a novel approach to EF prediction that leverages features classified in free-text respiratory therapy notes using a large language model and logistic regression pipeline. Applied to a patient cohort from University of Washington Medicine, our method identifies clinically meaningful EF-related features that improve EF prediction performance when included alongside structured patient data. We further highlight how differences in target populations in prior EF prediction studies, such as heterogenous inclusion criteria and EF definition, can lead to systematic differences in model performance and hinder generalizability between studies.
ER -