New onset delirium prediction using machine learning and long short-term memory (LSTM) in electronic health record. (27th October 2022)

• Record Type: Journal Article
• Authors: Liu, Siru; Schlesinger, Joseph J; McCoy, Allison B; Reese, Thomas J; Steitz, Bryan; Russo, Elise; Koh, Brian; Wright, Adam
• Is Part Of: Journal of the American Medical Informatics Association. Volume 30:Number 1(2023)
• Page Start: 120
• Page End: 131
• Publication Date: 2022-10-27
• Subjects: deep learning -- explainable machine learning -- delirium -- predictive models; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocac210
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective: To develop and test an accurate deep learning model for predicting new onset delirium in hospitalized adult patients. Methods: Using electronic health record (EHR) data extracted from a large academic medical center, we developed a model combining long short-term memory (LSTM) and machine learning to predict new onset delirium and compared its performance with machine-learning-only models (logistic regression, random forest, support vector machine, neural network, and LightGBM). The labels of models were confusion assessment method (CAM) assessments. We evaluated models on a hold-out dataset. We calculated Shapley additive explanations (SHAP) measures to gauge the feature impact on the model. Results: A total of 331 489 CAM assessments with 896 features from 34 035 patients were included. The LightGBM model achieved the best performance (AUC 0.927 [0.924, 0.929] and F 1 0.626 [0.618, 0.634]) among the machine learning models. When combined with the LSTM model, the final model's performance improved significantly ( P = .001) with AUC 0.952 [0.950, 0.955] and F 1 0.759 [0.755, 0.765]. The precision value of the combined model improved from 0.497 to 0.751 with a fixed recall of 0.8. Using the mean absolute SHAP values, we identified the top 20 features, including age, heart rate, Richmond Agitation-Sedation Scale score, Morse fall risk score, pulse, respiratory rate, and level of care. Conclusion: Leveraging LSTM to capture temporal trends and combining it with the LightGBM model can significantly improve the prediction of new onset delirium, providing an algorithmic basis for the subsequent development of clinical decision support tools for proactive delirium interventions.