Division of Health Services Research, Department of Foundations of Medicine New York University Long Island School of Medicine Mineola NY.
Department of Otolaryngology-Head and Neck Surgery, Bill Wilkerson Center Vanderbilt University Medical Center Nashville TN.
J Am Heart Assoc. 2022 Oct 18;11(20):e026987. doi: 10.1161/JAHA.122.026987. Epub 2022 Oct 10.
Background Peripheral artery disease (PAD) affects >10 million people in the United States. PAD is associated with poor outcomes, including premature death. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to develop ML models to predict in-hospital mortality in patients hospitalized for PAD based on a national database. Methods and Results Inpatient hospitalization data were obtained from the 2016 to 2019 National Inpatient Sample. A total of 150 921 inpatients were identified with a primary diagnosis of PAD and PAD-related procedures using codes of the () and . Four ML models, including logistic regression, random forest, light gradient boosting, and extreme gradient boosting models, were trained to predict the risk of in-hospital death based on a selection of variables, including patient characteristics, comorbidities, procedures, and hospital-related factors. In-hospital mortality occurred in 1.8% of patients. The performance of the 4 models was comparable, with the area under the receiver operating characteristic curve ranging from 0.83 to 0.85, sensitivity of 77% to 82%, and specificity of 72% to 75%. These results suggest adequate predictability for clinical decision-making. In all 4 models, the total number of diagnoses and procedures, age, endovascular revascularization procedure, congestive heart failure, diabetes, and diabetes with complications were critical predictors of in-hospital mortality. Conclusions This study demonstrates the feasibility of ML in predicting in-hospital mortality in patients with a primary PAD diagnosis. Findings highlight the potential of ML models in identifying high-risk patients for poor outcomes and guiding personalized intervention.
外周动脉疾病（PAD）影响美国超过 1000 万人。PAD 与不良结局相关，包括过早死亡。机器学习（ML）已越来越多地应用于大数据，以预测临床结局。本研究旨在基于国家数据库，开发用于预测因 PAD 住院患者院内死亡率的 ML 模型。
从 2016 年至 2019 年国家住院患者样本中获取住院患者住院数据。使用（）和 ）的代码，共确定了 150921 名因 PAD 及其相关程序而初次诊断为 PAD 的住院患者。使用包括患者特征、合并症、程序和医院相关因素在内的变量集，使用逻辑回归、随机森林、轻梯度增强和极端梯度增强模型等 4 种 ML 模型训练来预测住院期间死亡风险。1.8%的患者发生院内死亡。4 种模型的性能相当，受试者工作特征曲线下面积在 0.83 至 0.85 之间，敏感性在 77%至 82%之间，特异性在 72%至 75%之间。这些结果表明对临床决策具有足够的可预测性。在所有 4 种模型中，总诊断和程序数量、年龄、血管内血运重建程序、充血性心力衰竭、糖尿病和糖尿病合并症是院内死亡率的关键预测因素。
本研究证明了 ML 预测 PAD 初诊患者院内死亡率的可行性。研究结果突出了 ML 模型在识别预后不良的高危患者和指导个性化干预方面的潜力。
