Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes

Izzy Chaiken, Aditya Khowal, Neha A Sathe, Mark M Wurfel, Lucy Lu Wang
Proceedings of the 7th Conference on Health, Inference, and Learning, PMLR 333:468-492, 2026.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v333-chaiken26a, title = {Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes}, author = {Chaiken, Izzy and Khowal, Aditya and Sathe, Neha A and Wurfel, Mark M and Wang, Lucy Lu}, booktitle = {Proceedings of the 7th Conference on Health, Inference, and Learning}, pages = {468--492}, year = {2026}, editor = {Healey, Elizabeth and Fries, Jason and Pollard, Tom and Tang, Shengpu and Zink, Anna and Hartvigsen, Tom and Agrawal, Monica and Finlayson, Sam and Glicksberg, Benjamin and Beaulieu-Jones, Brett and Wang, Kai and Fontalvo, Daseyra and Sarker, Tasmie and Chen, Irene and Alsentzer, Emily}, volume = {333}, series = {Proceedings of Machine Learning Research}, month = {29--30 Jun}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v333/main/assets/chaiken26a/chaiken26a.pdf}, url = {https://proceedings.mlr.press/v333/chaiken26a.html}, 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.} }
Endnote
%0 Conference Paper %T Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes %A Izzy Chaiken %A Aditya Khowal %A Neha A Sathe %A Mark M Wurfel %A Lucy Lu Wang %B Proceedings of the 7th Conference on Health, Inference, and Learning %C Proceedings of Machine Learning Research %D 2026 %E Elizabeth Healey %E Jason Fries %E Tom Pollard %E Shengpu Tang %E Anna Zink %E Tom Hartvigsen %E Monica Agrawal %E Sam Finlayson %E Benjamin Glicksberg %E Brett Beaulieu-Jones %E Kai Wang %E Daseyra Fontalvo %E Tasmie Sarker %E Irene Chen %E Emily Alsentzer %F pmlr-v333-chaiken26a %I PMLR %P 468--492 %U https://proceedings.mlr.press/v333/chaiken26a.html %V 333 %X 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.
APA
Chaiken, I., Khowal, A., Sathe, N.A., Wurfel, M.M. & Wang, L.L.. (2026). Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical Notes. Proceedings of the 7th Conference on Health, Inference, and Learning, in Proceedings of Machine Learning Research 333:468-492 Available from https://proceedings.mlr.press/v333/chaiken26a.html.

Related Material