An Acute Kidney Injury Prediction Model for 24-hour Ultramarathon Runners

Po-Ya Hsu; Yi-Chung Hsu; Hsin-Li Liu; Wei Fong Kao; Kuan-Yu Lin

doi:10.2478/hukin-2022-0070

An Acute Kidney Injury Prediction Model for 24-hour Ultramarathon Runners

J Hum Kinet. 2022 Nov 8:84:103-111. doi: 10.2478/hukin-2022-0070. eCollection 2022 Oct.

Authors

Po-Ya Hsu¹, Yi-Chung Hsu², Hsin-Li Liu³, Wei Fong Kao⁴, Kuan-Yu Lin³

Affiliations

¹ Department of Computer Science and Engineering, University of California San Diego, La Jolla, California, the United States.
² Department of Nurse Practitioner, Fu Jen Catholic University Hospital, Taipei, Taiwan.
³ Department of Nursing, Central Taiwan University of Science and Technology, Taichung City, Taiwan.
⁴ Department of Emergency Medicine, Taipei Medical University, Taipei, Taiwan.

Abstract

Acute kidney injury (AKI) is frequently seen in ultrarunners, and in this study, an AKI prediction model for 24-hour ultrarunners was built based on the runner's prerace blood, urine, and body composition data. Twenty-two ultrarunners participated in the study. The risk of acquiring AKI was evaluated by a support vector machine (SVM) model, which is a statistical model commonly used for classification tasks. The inputs of the SVM model were the data collected 1 hour before the race, and the output of the SVM model was the decision of acquiring AKI. Our best AKI prediction model achieved accuracy of 96% in training and 90% in cross-validation tests. In addition, the sensitivity and specificity of the model were 90% and 100%, respectively. In accordance with the AKI prediction model components, ultra-runners are suggested to have high muscle mass and undergo regular ultra-endurance sports training to reduce the risk of acquiring AKI after participating in a 24-hour ultramarathon.

Keywords: acute kidney injury; extreme sports; injury prevention; machine learning.