Wang Lin, Bao Pei, Wang Xiaochen, Xu Banglong, Liu Zeyan, Hu Guangquan
Department of Cardiology, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
Department of Emergency Internal Medicine, The Second Affiliated Hospital of Anhui Medical University, Hefei, China.
Cardiovasc Diagn Ther. 2024 Aug 31;14(4):547-562. doi: 10.21037/cdt-24-83. Epub 2024 Aug 8.
No-reflow (NRF) phenomenon is a significant challenge in patients with ST-segment elevation myocardial infarction (STEMI) undergoing primary percutaneous coronary intervention (pPCI). Accurate prediction of NRF may help improve clinical outcomes of patients. This retrospective study aimed at creating an optimal model based on machine learning (ML) to predict NRF in these patients, with the additional objective of guiding pre- and intra-operative decision-making to reduce NRF incidence.
Data were collected from 321 STEMI patients undergoing pPCI between January 2022 and May 2023, with the dataset being randomly divided into training and internal validation sets in a 7:3 ratio. Selected features included pre- and intra-operative demographic data, laboratory parameters, electrocardiogram, comorbidities, patients' clinical status, coronary angiographic data, and intraoperative interventions. Post comprehensive feature cleaning and engineering, three logistic regression (LR) models [LR-classic, LR-random forest (LR-RF), and LR-eXtreme Gradient Boosting (LR-XGB)], a RF model and an eXtreme Gradient Boosting (XGBoost) model were developed within the training set, followed by performance evaluation on the internal validation sets.
Among the 261 patients who met the inclusion criteria, 212 were allocated to the normal flow group and 49 to the NRF group. The training group consisted of 183 patients, while the internal validation group included 78 patients. The LR-XGB model, with an area under the curve (AUC) of 0.829 [95% confidence interval (CI): 0.779-0.880], was selected as the representative model for logistic regression analyses. The LR model had an AUC slightly lower than XGBoost model (AUC 0.835, 95% CI: 0.781-0.889) but significantly higher than RF model (AUC 0.731, 95% CI: 0.660-0.802). Internal validation underscored the unique advantages of each model, with the LR model demonstrating the highest clinical net benefit at relevant thresholds, as determined by decision curve analysis. The LR model encompassed seven meaningful features, and notably, thrombolysis in myocardial infarction flow after initial balloon dilation (TFAID) was the most impactful predictor in all models. A web-based application based on the LR model, hosting these predictive models, is available at https://l7173o-wang-lyn.shinyapps.io/shiny-1/.
A LR model was successfully developed through ML to forecast NRF phenomena in STEMI patients undergoing pPCI. A web-based application derived from the LR model facilitates clinical implementation.
无复流（NRF）现象是接受直接经皮冠状动脉介入治疗（pPCI）的ST段抬高型心肌梗死（STEMI）患者面临的一项重大挑战。准确预测NRF可能有助于改善患者的临床结局。这项回顾性研究旨在创建一个基于机器学习（ML）的优化模型，以预测这些患者的NRF，另外一个目标是指导术前和术中决策，以降低NRF发生率。
收集了2022年1月至2023年5月期间接受pPCI的321例STEMI患者的数据，数据集以7:3的比例随机分为训练集和内部验证集。选择的特征包括术前和术中的人口统计学数据、实验室参数、心电图、合并症、患者临床状况、冠状动脉造影数据和术中干预措施。经过全面的特征清理和工程处理后，在训练集中开发了三个逻辑回归（LR）模型[LR-经典模型、LR-随机森林（LR-RF）和LR-极限梯度提升（LR-XGB）]、一个随机森林（RF）模型和一个极限梯度提升（XGBoost）模型，随后在内部验证集上进行性能评估。
在符合纳入标准的261例患者中，212例被分配到正常血流组，49例被分配到NRF组。训练组由183例患者组成，而内部验证组包括78例患者。LR-XGB模型的曲线下面积（AUC）为0.829[95%置信区间（CI）：0.779-0.880]，被选为逻辑回归分析的代表性模型。LR模型的AUC略低于XGBoost模型（AUC 0.835，95%CI：0.781-0.889），但显著高于RF模型（AUC 0.731，95%CI：0.660-0.802）。内部验证突出了每个模型的独特优势，决策曲线分析确定，LR模型在相关阈值下显示出最高的临床净效益。LR模型包含七个有意义的特征，值得注意的是，初始球囊扩张后的心肌梗死溶栓血流（TFAID）是所有模型中最具影响力的预测因素。基于LR模型的网络应用程序托管这些预测模型，可在https://l7173o-wang-lyn.shinyapps.io/shiny-1/上获取。
通过机器学习成功开发了一个LR模型，用于预测接受pPCI的STEMI患者的NRF现象。基于LR模型的网络应用程序便于临床实施。
