Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics

Chi-Yung Cheng; Chia-Te Kung; Fu-Cheng Chen; I-Min Chiu; Chun-Hung Richard Lin; Chun-Chieh Chu; Chien Feng Kung; Chih-Min Su

doi:10.3389/fmed.2022.964667

Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics

Front Med (Lausanne). 2022 Oct 20:9:964667. doi: 10.3389/fmed.2022.964667. eCollection 2022.

Authors

Chi-Yung Cheng^{1

2}, Chia-Te Kung², Fu-Cheng Chen², I-Min Chiu^{1

2}, Chun-Hung Richard Lin¹, Chun-Chieh Chu², Chien Feng Kung³, Chih-Min Su²

Affiliations

¹ Department of Computer Science and Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan.
² Department of Emergency Medicine, Kaohsiung Chang Gung Memorial Hospital, Chang Gung University College of Medicine, Kaohsiung, Taiwan.
³ Graduate Institute and Department of Intelligent Commerce, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan.

Abstract

Purpose: To build machine learning models for predicting the risk of in-hospital death in patients with sepsis within 48 h, using only dynamic changes in the patient's vital signs.

Methods: This retrospective observational cohort study enrolled septic patients from five emergency departments (ED) in Taiwan. We adopted seven variables, i.e., age, sex, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and body temperature.

Results: Among all 353,253 visits, after excluding 159,607 visits (45%), the study group consisted of 193,646 ED visits. With a leading time of 6 h, the convolutional neural networks (CNNs), long short-term memory (LSTM), and random forest (RF) had accuracy rates of 0.905, 0.817, and 0.835, respectively, and the area under the receiver operating characteristic curve (AUC) was 0.840, 0.761, and 0.770, respectively. With a leading time of 48 h, the CNN, LSTM, and RF achieved accuracy rates of 0.828, 0759, and 0.805, respectively, and an AUC of 0.811, 0.734, and 0.776, respectively.

Conclusion: By analyzing dynamic vital sign data, machine learning models can predict mortality in septic patients within 6 to 48 h of admission. The performance of the testing models is more accurate if the lead time is closer to the event.

Keywords: dynamic vital sign; machine learning model; mortality; prediction model; sepsis.