Dong Jiale, Jin Zhechuan, Li Chengxiang, Yang Jian, Jiang Yi, Li Zeqian, Chen Cheng, Zhang Bo, Ye Zhaofei, Hu Yang, Ma Jianguo, Li Ping, Li Yulin, Wang Dongjin, Ji Zhili
Beijing Institute of Heart, Lung and Blood Vessel Diseases, Beijing Anzhen Hospital, Capital Medical University, Beijing, China.
Department of Acute Abdomen Surgery, Beijing ChaoYang Hospital, Capital Medical University, Beijing, China.
J Med Internet Res. 2025 Mar 6;27:e68509. doi: 10.2196/68509.
Gastrointestinal bleeding is a serious adverse event of coronary artery bypass grafting and lacks tailored risk assessment tools for personalized prevention.
This study aims to develop and validate predictive models to assess the risk of gastrointestinal bleeding after coronary artery bypass grafting (GIBCG) and to guide personalized prevention.
Participants were recruited from 4 medical centers, including a prospective cohort and the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. From an initial cohort of 18,938 patients, 16,440 were included in the final analysis after applying the exclusion criteria. Thirty combinations of machine learning algorithms were compared, and the optimal model was selected based on integrated performance metrics, including the area under the receiver operating characteristic curve (AUROC) and the Brier score. This model was then developed into a web-based risk prediction calculator. The Shapley Additive Explanations method was used to provide both global and local explanations for the predictions.
The model was developed using data from 3 centers and a prospective cohort (n=13,399) and validated on the Drum Tower cohort (n=2745) and the MIMIC cohort (n=296). The optimal model, based on 15 easily accessible admission features, demonstrated an AUROC of 0.8482 (95% CI 0.8328-0.8618) in the derivation cohort. In external validation, the AUROC was 0.8513 (95% CI 0.8221-0.8782) for the Drum Tower cohort and 0.7811 (95% CI 0.7275-0.8343) for the MIMIC cohort. The analysis indicated that high-risk patients identified by the model had a significantly increased mortality risk (odds ratio 2.98, 95% CI 1.784-4.978; P<.001). For these high-risk populations, preoperative use of proton pump inhibitors was an independent protective factor against the occurrence of GIBCG. By contrast, dual antiplatelet therapy and oral anticoagulants were identified as independent risk factors. However, in low-risk populations, the use of proton pump inhibitors (χ=0.13, P=.72), dual antiplatelet therapy (χ=0.38, P=.54), and oral anticoagulants (χ=0.15, P=.69) were not significantly associated with the occurrence of GIBCG.
Our machine learning model accurately identified patients at high risk of GIBCG, who had a poor prognosis. This approach can aid in early risk stratification and personalized prevention.
Chinese Clinical Registry Center ChiCTR2400086050; http://www.chictr.org.cn/showproj.html?proj=226129.
胃肠道出血是冠状动脉旁路移植术的一种严重不良事件，且缺乏用于个性化预防的针对性风险评估工具。
本研究旨在开发并验证预测模型，以评估冠状动脉旁路移植术后胃肠道出血（GIBCG）的风险，并指导个性化预防。
从4个医疗中心招募参与者，包括一个前瞻性队列和重症监护医学信息数据库IV（MIMIC-IV）。在最初的18938例患者队列中，应用排除标准后，16440例被纳入最终分析。比较了30种机器学习算法组合，并根据综合性能指标（包括受试者操作特征曲线下面积（AUROC）和布里尔评分）选择了最佳模型。然后将该模型开发成基于网络的风险预测计算器。使用夏普利值法对预测结果进行全局和局部解释。
该模型使用来自3个中心和一个前瞻性队列（n=13399）的数据开发，并在鼓楼队列（n=2745）和MIMIC队列（n=296）上进行验证。基于15个易于获取的入院特征的最佳模型在推导队列中的AUROC为0.8482（95%CI 0.8328-0.8618）。在外部验证中，鼓楼队列的AUROC为0.8513（95%CI 0.8221-0.8782），MIMIC队列的AUROC为0.7811（95%CI 0.7275-0.8343）。分析表明，该模型识别出的高危患者死亡风险显著增加（优势比2.98，95%CI 1.784-4.978；P<0.001）。对于这些高危人群，术前使用质子泵抑制剂是预防GIBCG发生的独立保护因素。相比之下，双联抗血小板治疗和口服抗凝剂被确定为独立危险因素。然而，在低危人群中，使用质子泵抑制剂（χ=0.13，P=0.72）、双联抗血小板治疗（χ=0.38，P=0.54）和口服抗凝剂（χ=0.15，P=0.69）与GIBCG的发生无显著相关性。
我们的机器学习模型准确识别了GIBCG高危患者，这些患者预后较差。这种方法有助于早期风险分层和个性化预防。
中国临床试验注册中心ChiCTR2400086050；http://www.chictr.org.cn/showproj.html?proj=226129。
