Department of Thoracic Surgery, West China Hospital, Sichuan University, Chengdu, 610041, China.
Wuxi Lung Transplant Center, Wuxi People's Hospital affiliated to Nanjing Medical University, Wuxi, 214023, China.
BMC Med Inform Decis Mak. 2024 Aug 19;24(1):229. doi: 10.1186/s12911-024-02635-8.
Patients with airway stenosis (AS) are associated with considerable morbidity and mortality after lung transplantation (LTx). This study aims to develop and validate machine learning (ML) models to predict AS requiring clinical intervention in patients after LTx.
Patients who underwent LTx between January 2017 and December 2019 were reviewed. The conventional logistic regression (LR) model was fitted by the independent risk factors which were determined by multivariate LR. The optimal ML model was determined based on 7 feature selection methods and 8 ML algorithms. Model performance was assessed by the area under the curve (AUC) and brier score, which were internally validated by the bootstrap method.
A total of 381 LTx patients were included, and 40 (10.5%) patients developed AS. Multivariate analysis indicated that male, pulmonary arterial hypertension, and postoperative 6-min walking test were significantly associated with AS (all P < 0.001). The conventional LR model showed performance with an AUC of 0.689 and brier score of 0.091. In total, 56 ML models were developed and the optimal ML model was the model fitted using a random forest algorithm with a determination coefficient feature selection method. The optimal model exhibited the highest AUC and brier score values of 0.760 (95% confidence interval [CI], 0.666-0.864) and 0.085 (95% CI, 0.058-0.117) among all ML models, which was superior to the conventional LR model.
The optimal ML model, which was developed by clinical characteristics, allows for the satisfactory prediction of AS in patients after LTx.
肺移植（LTx）后气道狭窄（AS）患者的发病率和死亡率相当高。本研究旨在开发和验证机器学习（ML）模型，以预测 LTx 后需要临床干预的 AS。
回顾了 2017 年 1 月至 2019 年 12 月期间接受 LTx 的患者。通过多元逻辑回归（LR）确定的独立风险因素来拟合传统的 LR 模型。根据 7 种特征选择方法和 8 种 ML 算法确定最佳 ML 模型。通过自举法对内部分别评估模型性能，使用曲线下面积（AUC）和布莱尔得分。
共纳入 381 例 LTx 患者，其中 40 例（10.5%）患者发生 AS。多变量分析表明，男性、肺动脉高压和术后 6 分钟步行试验与 AS 显著相关（均 P<0.001）。传统 LR 模型的 AUC 为 0.689，布莱尔得分为 0.091。共开发了 56 个 ML 模型，最优 ML 模型是使用随机森林算法和确定系数特征选择方法拟合的模型。最优模型的 AUC 和布莱尔得分最高，分别为 0.760（95%CI，0.666-0.864）和 0.085（95%CI，0.058-0.117），优于传统 LR 模型。
由临床特征开发的最优 ML 模型可满意预测 LTx 后 AS 的发生。
