Realtime, multimodal invasive ventilation risk monitoring using language models and BoXHED

TL;DR

This study introduces a novel method that combines clinical notes and language models to improve real-time invasive ventilation risk monitoring in ICUs, outperforming existing approaches and enabling earlier detection.

Contribution

It presents an innovative approach integrating clinical notes with language models into real-time risk monitoring, enhancing performance and lead time over prior methods.

Findings

Achieved AUROC of 0.86 in risk prediction

Demonstrated increased lead time for flagging ventilation risk

Outperformed state-of-the-art in all reported metrics

Abstract

Objective: realtime monitoring of invasive ventilation (iV) in intensive care units (ICUs) plays a crucial role in ensuring prompt interventions and better patient outcomes. However, conventional methods often overlook valuable insights embedded within clinical notes, relying solely on tabular data. In this study, we propose an innovative approach to enhance iV risk monitoring by incorporating clinical notes into the monitoring pipeline through using language models for text summarization. Results: We achieve superior performance in all metrics reported by the state-of-the-art in iV risk monitoring, namely: an AUROC of 0.86, an AUC-PR of 0.35, and an AUCt of up to 0.86. We also demonstrate that our methodology allows for more lead time in flagging iV for certain time buckets. Conclusion: Our study underscores the potential of integrating clinical notes and language models into realtime iV risk monitoring, paving the way for improved patient care and informed clinical decision-making in ICU settings.