Explainable Deep Learning Model for Predicting Serious Adverse Events in Hospitalized Geriatric Patients Within 72 Hours

Abstract

Ting-Yu Hsu,1 Chi-Yung Cheng,1,2,* I-Min Chiu,1,2 Chun-Hung Richard Lin,2 Fu-Jen Cheng,1 Hsiu-Yung Pan,1 Yu-Jih Su,3 Chao-Jui Li1,* 1Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung, Taiwan; 2Department of Computer Science and Engineering, National Sun Yat-Sen University, Kaohsiung, Taiwan; 3Department of Internal Medicine, Division of Rheumatology, Allergy and Immunology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan*These authors contributed equally to this workCorrespondence: Chi-Yung Cheng; Chao-Jui Li, Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, 123 Ta-Pei Road, Niao-Sung, Kaohsiung, 833, Taiwan, Tel [phone] ext. 8415, Email [email protected]; [email protected]: The global aging population presents a significant challenge, with older adults experiencing declining physical and cognitive abilities and increased vulnerability to chronic diseases and adverse health outcomes. This study aims to develop an interpretable deep learning (DL) model to predict adverse events in geriatric patients within 72 hours of hospitalization.Methods: The study used retrospective data (2017– 2020) from a major medical center in Taiwan. It included non-trauma geriatric patients who visited the emergency department and were admitted to the general ward. Data preprocessing involved collecting prognostic factors like vital signs, lab results, medical history, and clinical management. A deep feedforward neural network was developed, and performance was evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). Model interpretation utilized the Shapley Additive Explanation (SHAP) technique.Results: The analysis included 127,268 patients, with 2.6% experiencing imminent intensive care unit transfer, respiratory failure, or death during hospitalization. The DL model achieved AUCs of 0.86 and 0.84 in the validation and test sets, respectively, outperforming the Sequential Organ Failure Assessment (SOFA) score. Sensitivity and specificity values ranged from 0.79 to 0.81. The SHAP technique provided insights into feature importance and interactions.Conclusion: The developed DL model demonstrated high accuracy in predicting serious adverse events in geriatric patients within 72 hours of hospitalization. It outperformed the SOFA score and provided valuable insights into the model’s decision-making process. Keywords: explainable machine learning, deep learning algorithm, adverse events, mortality

Keywords

• explainable machine learning
• deep learning algorithm
• adverse events
• mortality