Risk Stratification for ICU Delirium using Pervasive Ambient Sensing Information
2026-06-17 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how sounds and light levels in hospital ICUs might help predict when patients develop delirium, a serious brain condition. They tested several computer models using data from 309 patients and found that sounds were especially useful for prediction. Combining sound and light data improved predictions for the short term. This approach could help doctors notice delirium risk earlier by using sensors without bothering patients.
deliriumIntensive Care Unit (ICU)neural networkssound pressure levelslight intensityShapley Additive ExplanationsAUCprediction modelsambient sensing
Authors
Jiaqing Zhang, Sabyasachi Bandyopadhyay, Miguel Contreras, Jessica Sena, Yuanfang Ren, Andrea Davidson, Ziyuan Guan, Tezcan Ozrazgat-Baslanti, Subhash Nerella, Azra Bihorac, Parisa Rashidi
Abstract
Delirium is a common and serious complication in the Intensive Care Unit (ICU), associated with increased morbidity, prolonged hospital stays, and higher healthcare costs. Despite its prevalence, early prediction and prevention remain challenging. Environmental factors such as ambient sound and light may influence the onset of delirium, yet they are often overlooked in risk assessments. In this study, we examined whether light intensity and sound pressure levels can independently predict delirium across multiple prediction horizons. We evaluated four efficient sequential neural network models on data collected from 9 ICUs across 309 patients to predict delirium for 10 prediction-window sizes. We reported feature importance and direction of influence using Shapley Additive Explanations analysis. The convolutional model achieved the strongest discrimination, with AUC = 0.80 on sound data and on combined data. Sound features were the dominant predictors overall. Integrating sound with light improved short-term ($<1$ week) prediction, with the combined model assigning the highest risk immediately after the sensing period. These findings suggest that passive ambient sensing, especially sound, can add a clinically meaningful, interpretable signal for delirium risk estimation and offer a practical pathway to enrich multimodal ICU prediction and prevention strategies.