AUTHOR=Xu Yawen , Sun Xu , Liu Yanqun , Huang Yuxin , Liang Meng , Sun Rui , Yin Ge , Song Chenrui , Ding Qichao , Du Bingying , Bi Xiaoying 

TITLE=Prediction of subjective cognitive decline after corpus callosum infarction by an interpretable machine learning-derived early warning strategy

JOURNAL=Frontiers in Neurology

VOLUME=Volume 14 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2023.1123607

DOI=10.3389/fneur.2023.1123607

ISSN=1664-2295

ABSTRACT=Background and Purpose: Corpus callosum (CC) infarction is an extremely rare subtype of cerebral ischemic stroke. This study seeks to develop and validate models for predicting the risk of subjective cognitive decline (SCD) after CC infarction by machine learning (ML) algorithms.
Methods: This is a prospective study that enrolled 314 (only 3.7%) CC infarction patients from a nine-year cohort comprising 8555 patients with acute ischemic stroke. Telephone follow-up surveys were carried out for the patients with definite diagnosis of CC infarction one-year after disease onset, and SCD was identified by BRFSS questionnaire. Based on the significant features selected by the least absolute shrinkage and selection operator (LASSO), seven ML models were established and their predictive performances were compared by different metrics. Importantly, the SHapley Additive exPlanations (SHAP) was also utilized to examine internal behavior of the highest-performance ML classifier. 
Results: The Logistic Regression (LR)-model performed better than other six ML-models in SCD predictability after the CC infarction, with an AUC of 77.1% in the validation set. Using LASSO and SHAP analysis, we found that infarction subregions of CC infarction, female, 3-month modified Rankin Scale (mRS) score, age, homocysteine, location of angiostenosis, neutrophil to lymphocyte ratio, pure CC infarction, and number of angiostenosis were the top-nine significant predictors in the order of importance for the output of LR-model. Meanwhile, we identified that infarction subregion of CC, female, 3-month mRS score and pure CC infarction were the factors which independently associated with the cognitive outcome. 
Conclusions: This work suggest that the combination of ML-technique and SHAP-explainer has a potential to best predict SCD after CC infarction, emphasizing both the clinical feasibility and interpretability of the optimal ML classifier.