Transformer Models for Acute Brain Dysfunction Prediction

TL;DR

This paper presents a transformer-based machine learning system that leverages electronic health records for real-time prediction of acute brain dysfunction in ICU patients, aiming to improve assessment accuracy and patient outcomes.

Contribution

The study introduces a novel transformer model approach for predicting acute brain dysfunction using integrated static and temporal EHR data, outperforming baseline models.

Findings

Achieved a mean AUROC of 0.953 with Long-former transformer.

Demonstrated effective binary and multi-class classification of ABD.

Potential to reduce ICU costs, stay duration, and mortality.

Abstract

Acute brain dysfunctions (ABD), which include coma and delirium, are prevalent in the ICU, especially among older patients. The current approach in manual assessment of ABD by care providers may be sporadic and subjective. Hence, there exists a need for a data-driven robust system automating the assessment and prediction of ABD. In this work, we develop a machine learning system for real-time prediction of ADB using Electronic Health Record (HER) data. Our data processing pipeline enables integration of static and temporal data, and extraction of features relevant to ABD. We train several state-of-the-art transformer models and baseline machine learning models including CatBoost and XGB on the data that was collected from patients admitted to the ICU at UF Shands Hospital. We demonstrate the efficacy of our system for tasks related to acute brain dysfunction including binary classification of brain acuity and multi-class classification (i.e., coma, delirium, death, or normal), achieving a mean AUROC of 0.953 on our Long-former implementation. Our system can then be deployed for real-time prediction of ADB in ICUs to reduce the number of incidents caused by ABD. Moreover, the real-time system has the potential to reduce costs, duration of patients stays in the ICU, and mortality among those afflicted.