Predicting postoperative complications after pneumonectomy using machine learning: a 10-year study

Reducing postoperative cardiovascular and neurological complications (PCNC) during thoracic surgery is the key to improving postoperative survival. We aimed to investigate independent predictors of PCNC, develop machine learning models, and construct a predictive nomogram for PCNC in patients undergoing thoracic surgery for lung cancer. This study used data from a previous retrospective study of 16,368 patients with lung cancer (training set: 11,458; validation set: 4,910) with American Standards Association physical statuses I–IV who underwent surgery. Postoperative information was collected from electronic medical records to help build models based on cause-and-effect and statistical data, potentially revealing hidden dependencies between factors and diseases in a big data environment. The optimal model was analyzed and filtered using multiple machine-learning models (Logistic regression, eXtreme Gradient Boosting, Random forest, Light Gradient Boosting Machine and Naïve Bayes). A predictive nomogram was built and receiver operating characteristics were used to assess the validity of the model. The discriminative power and clinical validity were assessed using calibration and decision-making curve analyses. Multivariate logistic regression analysis revealed that age, surgery duration, intraoperative intercostal nerve block, postoperative patient-controlled analgesia, bronchial blocker use and sufentanil use were independent predictors of PCNC. Random forest was identified as the optimal model with an area under the curve of 0.898 in the training set and 0.752 in the validation set, confirming the excellent prediction accuracy of the nomogram. All the net benefits of the five machine-learning models in the training and validation sets demonstrated excellent clinical applicability, and the calibration curves showed good agreement between the predicted and observed risks. The combination of machine-learning models and nomograms may contribute to the early prediction and reduction in the incidence of PCNC.

降低胸外科手术期间的术后心血管与神经系统并发症（postoperative cardiovascular and neurological complications, PCNC）是提升术后生存率的核心目标。本研究旨在探究胸外科肺癌手术患者PCNC的独立预测因素，构建机器学习模型，并搭建针对该人群的PCNC预测列线图。本研究使用一项既往回顾性研究的数据，纳入16368例美国标准协会（American Standards Association）体格状态分级I~IV级、接受手术治疗的肺癌患者，其中训练集11458例，验证集4910例。研究通过电子病历采集术后相关信息，基于因果关联与统计数据构建模型，以期在大数据环境中揭示各因素与疾病间潜在的依存关系。本研究采用逻辑回归、极限梯度提升、随机森林、轻量梯度提升机与朴素贝叶斯等多种机器学习模型，对最优模型进行分析与筛选。随后构建预测列线图，并通过受试者工作特征曲线评估模型的有效性；同时采用校准曲线与决策曲线分析，评估模型的区分效能与临床实用性。多因素logistic回归分析结果显示，年龄、手术时长、术中肋间神经阻滞、术后患者自控镇痛、支气管封堵器应用以及舒芬太尼应用均为PCNC的独立预测因素。随机森林被确定为最优模型，其训练集曲线下面积为0.898，验证集曲线下面积为0.752，证实该列线图具备优异的预测准确度。五种机器学习模型在训练集与验证集的净获益均展现出良好的临床适用性，校准曲线显示预测风险与实际观测风险具有良好的一致性。综上，机器学习模型与列线图的结合，可为PCNC的早期预测及发病率降低提供重要助力。