Shaoji Li,1,* Hongjian Li,2,* Baofang Wu,1,* Rujun Pan,3 Yuqi Liu,4 Jiayin Wang,1 De Wei,3 Hongzhi Gao1 

1Department of Neurosurgery, the Second Affiliated Hospital of Fujian Medical University, Quanzhou, 362000, People’s Republic of China; 2School of Medical Imaging, North Sichuan Medical College, Nanchong, 634700, People’s Republic of China; 3Department of Neurosurgery, Fuzhou University Affiliated Provincial Hospital, Fuzhou, 350001, People’s Republic of China; 4Department of Intensive Care Unit, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, 362000, People’s Republic of China

*These authors contributed equally to this work

Correspondence: De Wei; Hongzhi Gao, Email weidele@fjmu.edu.cn; gaohongzhi@fjmu.edu.cn

Background: Post-traumatic cerebral infarction (PTCI) is a severe complication resulting from traumatic brain injury (TBI), which can lead to permanent neurological damage or death. The investigation of the factors associated with PTCI and the establishment of predictive models are crucial for clinical practice.
Methods: We made a retrospective analysis of clinical data from 1484 TBI patients admitted to the Neurosurgery Department of a provincial hospital from January 2018 to December 2023. Predictive factors were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) and multivariable logistic regression analysis. Several machine learning (ML) classification models were developed and compared. The interpretations of the ML models’ predictions were provided by SHAP values.
Results: Key predictors included age, bilateral brain contusions, platelet count, uric acid, glucose, traumatic subarachnoid hemorrhage, and surgical treatment. The logistic regression (LR) model outperformed other ML algorithms, demonstrating superior performance in the test set with an AUC of 0.821, accuracy of 0.845, Matthews correlation coefficient (MCC) of 0.264, area under the receiver operating characteristic curve (AUROC) of 0.711, precision of 0.56, and specificity of 0.971. It had stable performance in the ten-fold cross-validation.
Conclusion: ML algorithms, integrating demographic and clinical factors, accurately predicted the risk of PTCI occurrence. Interpretations using the SHAP method offer guidance for personalized treatment of different patients, filling gaps between complex clinical data and actionable insights.

Keywords: traumatic brain injury, post-traumatic cerebral infarction, retrospective study, machine learning, prediction model