Niu Yanxiang, Chen Xin, Fan Jianqi, Liu Chunli, Fang Menghao, Liu Ziquan, Meng Xiangyan, Liu Yanqing, Lu Lu, Fan Haojun
Institute of Disaster and Emergency Medicine, Tianjin University, Tianjin, China.
Wenzhou Safety (Emergency) Institute, Tianjin University, Wenzhou, 325000, China.
Sci Rep. 2025 Apr 3;15(1):11498. doi: 10.1038/s41598-025-93579-0.
Early and accurate prediction of neurological outcomes in comatose patients following cardiac arrest is critical for informed clinical decision-making. Existing studies have predominantly focused on EEG for assessing brain injury, with some exploring ECG data. However, the integration of EEG, ECG, and clinical features remains insufficiently investigated, and its potential to enhance predictive accuracy has not been fully established. Moreover, the limited interpretability of current models poses significant barriers to clinical application. Using the I-CARE database, we analyzed EEG, ECG, and clinical data from comatose cardiac arrest patients. After rigorous preprocessing and feature engineering, machine learning models (Logistic Regression, SVM, Random Forest, and Gradient Boosting) were developed. Performance was evaluated through AUC-ROC, accuracy, sensitivity, and specificity, with SHAP applied to interpret feature contributions. Our multi-modal model outperformed single-modality models, achieving AUC values from 0.75 to 1.0. Notably, the model's accuracy peaked at a critical point within the 12-24 h window (e.g., 18 h, AUC = 1.0), surpassing EEG-only (AUC 0.7-0.8) and ECG-only (AUC < 0.6) models. SHAP identified Shockable Rhythm as the most influential feature (mean SHAP value 0.17), emphasizing its role in predictive accuracy. This study presents a novel multi-modal approach that significantly enhances early neurological outcome prediction in critical care. SHAP-based interpretability further supports clinical applicability, paving the way for more personalized patient management post-cardiac arrest.
心脏骤停后昏迷患者神经功能预后的早期准确预测对于明智的临床决策至关重要。现有研究主要集中在脑电图用于评估脑损伤，也有一些研究探索心电图数据。然而，脑电图、心电图和临床特征的整合仍未得到充分研究，其提高预测准确性的潜力尚未完全确立。此外，当前模型的有限可解释性对临床应用构成了重大障碍。我们使用I-CARE数据库，分析了昏迷心脏骤停患者的脑电图、心电图和临床数据。经过严格的预处理和特征工程，开发了机器学习模型（逻辑回归、支持向量机、随机森林和梯度提升）。通过AUC-ROC、准确性、敏感性和特异性评估性能，并应用SHAP来解释特征贡献。我们的多模态模型优于单模态模型，AUC值在0.75至1.0之间。值得注意的是，该模型的准确性在12-24小时窗口内的一个关键点达到峰值（例如18小时，AUC = 1.0），超过了仅使用脑电图（AUC 0.7-0.8）和仅使用心电图（AUC < 0.6）的模型。SHAP确定可电击心律是最具影响力的特征（平均SHAP值0.17），强调了其在预测准确性中的作用。本研究提出了一种新颖的多模态方法，显著提高了重症监护中早期神经功能预后的预测。基于SHAP的可解释性进一步支持了临床适用性，为心脏骤停后更个性化的患者管理铺平了道路。
