Table 1_Research on a machine learning-based predictive model for postoperative neurological dysfunction in acute Stanford type A aortic dissection.xlsx

IntroductionThis study aimed to construct and validate a machine learning (ML) model integrating preoperative, intraoperative, and postoperative multimodal clinical data for individualized prediction of postoperative neurological dysfunction (ND) in patients with acute Stanford type A aortic dissection (ATAAD).
MethodsA retrospective analysis was conducted on 1,228 ATAAD patients (Aortic Disease Center of Beijing Anzhen Hospital, January 2020–December 2023): 853 patients (January 2020–December 2022) for model training/internal validation (via 10-fold cross-validation) and 375 patients (January–December 2023) for external validation. The 853 patients were grouped into control (n = 616) and ND (n = 237), including 203 transient ND (TND) and 34 permanent ND (PND) groups. Data were analyzed using Mann–Whitney U, chi-square (χ2), and Fisher’s exact tests (p < 0.05). Four ML models (SVC-LK, Nu-SVC, AdaBoost, XGBoost) were built with perioperative data; SHapley Additive exPlanations (SHAP) selected 15 robust features from 49 initial ones. Model performance was assessed via ROC-AUC (10-fold cross-validation for training/internal validation, external validation for effectiveness), and the optimal model was identified using DeLong test (two-tailed p-values). A multidimensional analysis compared the optimal model with traditional logistic regression (LR).
ResultsThe XGBoost model exhibited the best performance: AUC = 0.966 (internal validation) and AUC = 0.951 (external validation), outperforming LR and the other three ML models.
ConclusionThe XGBoost algorithm demonstrates superior efficacy in predicting postoperative ND in acute ATAAD patients, providing postoperative early warning, identifying high-risk patients, offering clinical guidance, and enabling timely intervention.

研究背景 本研究旨在构建并验证一款整合术前、术中及术后多模态临床数据的机器学习（ML）模型，用于个体化预测急性Stanford A型主动脉夹层（ATAAD）患者术后神经功能障碍（ND）。
研究方法 本研究回顾性分析了北京安贞医院心脏大血管疾病中心2020年1月至2023年12月收治的1228例ATAAD患者：其中2020年1月至2022年12月的853例患者用于模型训练与内部验证（采用10折交叉验证），2023年1月至12月的375例患者用于外部验证。将853例患者分为对照组（n=616）与ND组（n=237），ND组进一步细分为203例短暂性神经功能障碍（TND）亚组与34例永久性神经功能障碍（PND）亚组。采用Mann-Whitney U检验、卡方（χ²）检验及Fisher确切概率法进行数据分析，检验水准设定为p<0.05。基于围手术期数据构建4种机器学习模型，分别为SVC-LK、Nu-SVC、AdaBoost、XGBoost；通过SHapley可加解释（SHAP）从49项初始特征中筛选出15项稳健特征。采用受试者工作特征曲线下面积（ROC-AUC）评估模型性能：训练与内部验证阶段采用10折交叉验证，外部验证阶段评估模型泛化效能；通过DeLong检验（双侧p值）筛选最优模型。此外开展多维度对比分析，比较最优模型与传统逻辑回归（LR）的性能差异。
研究结果 XGBoost模型表现最优，其内部验证的ROC-AUC为0.966，外部验证的ROC-AUC为0.951，性能优于逻辑回归（LR）及其余3种机器学习模型。
研究结论 XGBoost算法在预测急性ATAAD患者术后ND方面具有优异效能，可用于术后早期预警、识别高危患者、为临床诊疗提供指导并助力及时干预。