Multimodal Machine Learning for Predicting Postoperative Functional Outcomes in Surgically Treated Supratentorial Deep Intracerebral Hemorrhage: A Prospective Multicenter Study

Min Cui¹Yanyi Yanyi Liu²Qi He¹Weiming Xiong¹Yang Liu¹Lei Xu¹Yongbing Deng¹Xingwei Tan^1,3*

• ¹Chongqing Emergency Medical Center, Chongqing, China
• ²The Affiliated Yongchuan Hospital of Chongqing Medical University, Chongqing, China
• ³The Third Affiliated Hospital of Chongqing Medical University, Chongqing, China

Background: Early prediction of functional outcomes after surgery for spontaneous supratentorial deep intracerebral hemorrhage (sICH) remains difficult. This study developed and validated multimodal machine-learning models incorporating clinical, imaging, physiological, and biomarker data, including temperature management strategies, and explored interpretability using SHAP. Methods: This prospective multicenter cohort enrolled 285 surgically treated sICH patients. Outcome was defined as favorable (mRS 0–3) versus unfavorable (mRS 4–6). Data were split by stratified random sampling into a training set (n=199) and a test set (n=86). LASSO with 10-fold cross-validation (1-SE rule) selected key predictors. Five classifiers (Random Forest, neural network, decision tree, k-nearest neighbors, naïve Bayes) were trained with 10-fold cross-validation and evaluated on the test set. Performance was assessed using AUC (95% CI) and standard classification metrics; AUCs were compared by DeLong's test. SHAP was applied to the best model. Results: LASSO identified eight predictors: admission GCS, hematoma volume, TNF-α, GFAP, IL-1β, admission NIHSS, mean body temperature, and peak ICP. On the test set, Random Forest achieved the highest performance (AUC 0.883, 95% CI 0.829–0.937; accuracy 0.824; F1-score 0.836), with no significant AUC difference versus the neural network (AUC 0.867; P=0.312). SHAP ranked admission GCS and hematoma volume as the most important features, followed by TNF-α and GFAP. Conclusions: A multimodal Random Forest model provided good discrimination for predicting postoperative functional outcomes in surgically treated sICH, and SHAP improved interpretability by quantifying feature contributions.