Reliability and Clinical Utility of Machine Learning to Predict Stroke Prognosis: Comparison with Logistic Regression
Su-Kyeong Jang, Jun Young Chang, Ji Sung Lee, Eun‐Jae Lee, Yong‐Hwan Kim, Jung H. Han, Dae‐Il Chang, Han‐Jin Cho, Jae‐Kwan Cha, Kyung Ho Yu, Jin‐Man Jung, Seong Hwan Ahn, Dong‐Eog Kim, Sung‐Il Sohn, Ju Hun Lee, Kyung‐Pil Park, Sun U. Kwon, Jong S. Kim, Dong‐Wha Kang, KOSNI Investigators
Abstract
The accurate prediction of functional recovery after a stroke is essential for post-discharge treatment planning and resource utilization. Recently, machine learning (ML) algorithms with baseline clinical variables have demonstrated better performance for predicting the functional outcome of ischemic stroke compared with preexisting scoring systems developed by conventional statistics. 1,2 However, most studies compared model performance by area under curve (AUC) only, and ML and conventional statistical approaches were not sufficiently evaluated in terms of the reliability and clinical utility. 3 We aimed to compare the performance of the ML with that of the conventional logistic regression (LR) model by evaluating accuracy, reliability, and clinical utility using AUC comparison, calibration, and decision curve analysis to predict the outcome of a stroke using KOrean Stroke Neuroimaging Initiative (KOSNI) database.