Shen Junbo, Xue Bing, Kannampallil Thomas, Lu Chenyang, Abraham Joanna
Department of Computer Science and Engineering, Washington University in St Louis, St Louis, MO 63130, United States.
AI for Health Institute, Washington University in St Louis, St Louis, MO 63130, United States.
J Am Med Inform Assoc. 2025 Mar 1;32(3):459-469. doi: 10.1093/jamia/ocae316.
Early detection of surgical complications allows for timely therapy and proactive risk mitigation. Machine learning (ML) can be leveraged to identify and predict patient risks for postoperative complications. We developed and validated the effectiveness of predicting postoperative complications using a novel surgical Variational Autoencoder (surgVAE) that uncovers intrinsic patterns via cross-task and cross-cohort presentation learning.
This retrospective cohort study used data from the electronic health records of adult surgical patients over 4 years (2018-2021). Six key postoperative complications for cardiac surgery were assessed: acute kidney injury, atrial fibrillation, cardiac arrest, deep vein thrombosis or pulmonary embolism, blood transfusion, and other intraoperative cardiac events. We compared surgVAE's prediction performance against widely-used ML models and advanced representation learning and generative models under 5-fold cross-validation.
89 246 surgeries (49% male, median [IQR] age: 57 [45-69]) were included, with 6502 in the targeted cardiac surgery cohort (61% male, median [IQR] age: 60 [53-70]). surgVAE demonstrated generally superior performance over existing ML solutions across postoperative complications of cardiac surgery patients, achieving macro-averaged AUPRC of 0.409 and macro-averaged AUROC of 0.831, which were 3.4% and 3.7% higher, respectively, than the best alternative method (by AUPRC scores). Model interpretation using Integrated Gradients highlighted key risk factors based on preoperative variable importance.
Our advanced representation learning framework surgVAE showed excellent discriminatory performance for predicting postoperative complications and addressing the challenges of data complexity, small cohort sizes, and low-frequency positive events. surgVAE enables data-driven predictions of patient risks and prognosis while enhancing the interpretability of patient risk profiles.
早期发现手术并发症有助于及时治疗并积极降低风险。机器学习（ML）可用于识别和预测患者术后并发症风险。我们开发并验证了一种新型手术变分自编码器（surgVAE）预测术后并发症的有效性，该模型通过跨任务和跨队列呈现学习来揭示内在模式。
这项回顾性队列研究使用了4年（2018 - 2021年）期间成年手术患者电子健康记录中的数据。评估了心脏手术的六种关键术后并发症：急性肾损伤、心房颤动、心脏骤停、深静脉血栓形成或肺栓塞、输血以及其他术中心脏事件。在五折交叉验证下，我们将surgVAE的预测性能与广泛使用的ML模型以及先进的表征学习和生成模型进行了比较。
共纳入89246例手术（49%为男性，年龄中位数[四分位间距]：57[45 - 69]岁），其中目标心脏手术队列有6502例（61%为男性，年龄中位数[四分位间距]：60[53 - 70]岁）。在心脏手术患者的术后并发症方面，surgVAE总体表现优于现有的ML解决方案，宏观平均精确率均值为0.409，宏观平均受试者工作特征曲线下面积为0.831，分别比最佳替代方法（按精确率均值得分）高3.4%和3.7%。使用集成梯度进行的模型解释突出了基于术前变量重要性的关键风险因素。
我们先进的表征学习框架surgVAE在预测术后并发症以及应对数据复杂性、小队列规模和低频阳性事件等挑战方面表现出出色的辨别性能。surgVAE能够进行数据驱动的患者风险和预后预测，同时增强患者风险概况的可解释性。
