Predicting post-stroke cognitive impairment using machine learning: A prospective cohort study

Wencan Ji; Canjun Wang; Hanqing Chen; Yan Liang; Shaohua Wang

doi:10.1016/j.jstrokecerebrovasdis.2023.107354

Predicting post-stroke cognitive impairment using machine learning: A prospective cohort study

J Stroke Cerebrovasc Dis. 2023 Nov;32(11):107354. doi: 10.1016/j.jstrokecerebrovasdis.2023.107354. Epub 2023 Sep 14.

Authors

Wencan Ji¹, Canjun Wang², Hanqing Chen³, Yan Liang³, Shaohua Wang⁴

Affiliations

¹ Nanjing Medical University, Nanjing, China; Jiangsu Research Center for Primary Health Development and General Practice Education, Jiangsu, China; Department of General Practice, Zhongda Hospital, Southeast University, Nanjing, China.
² Center of Clinical Laboratory Medicine, Zhongda Hospital, Southeast University, Nanjing, China.
³ Department of General Practice, Zhongda Hospital, Southeast University, Nanjing, China.
⁴ Nanjing Medical University, Nanjing, China; Department of Endocrinology, Affiliated Zhongda Hospital of Southeast University, Nanjing, China. Electronic address: gyjwsh@126.com.

PMID: 37716104
DOI: 10.1016/j.jstrokecerebrovasdis.2023.107354

Abstract

Background: Post-stroke cognitive impairment (PSCI) is a serious complication of stroke that warrants prompt detection and management. Consequently, the development of a diagnostic prediction model holds clinical significance.

Objective: Machine learning algorithms were employed to identify crucial variables and forecast PSCI occurrence within 3-6 months following acute ischemic stroke (AIS).

Methods: A prospective study was conducted on a developed cohort (331 patients) utilizing data from the Affiliated Zhongda Hospital of Southeast University between January 2022 and August 2022, as well as an external validation cohort (66 patients) from December 2022 to January 2023. The optimal model was determined by integrating nine machine learning classification models, and personalized risk assessment was facilitated by a Shapley Additive exPlanations (SHAP) interpretation.

Results: Age, education, baseline National Institutes of Health Scale (NIHSS), Cerebral white matter degeneration (CWMD), Homocysteine (Hcy), and C-reactive protein (CRP) were identified as predictors of PSCI occurrence. Gaussian Naïve Bayes (GNB) model was determined to be the optimal model, surpassing other classifier models in the validation set (area under the curve [AUC]: 0.925, 95 % confidence interval [CI]: 0.861 - 0.988) and achieving the lowest Brier score. The GNB model performed well in the test sets (AUC: 0.919, accuracy: 0.864, sensitivity: 0.818, and specificity: 0.932).

Conclusions: The present study involved the development of a GNB model and its elucidation through employment of the SHAP method. These findings provide compelling evidence for preventing PSCI, which could serve as a guide for high-risk patients to undertake appropriate preventive measures.

Keywords: Cognitive impairment; Gaussian Naïve Bayes; Ischemic stroke; Machine learning; Prediction model; SHAP.