机器学习模型预测特发性胃十二指肠溃疡出血病史患者复发性溃疡出血
基于2007-2016年22 854例消化性溃疡病患者回顾性队列构建IPU-ML模型,预测复发性溃疡出血,并在2008-2015年不同人群的1265例消化道出血患者中独立验证。训练队列中位随访2.7年,4772例(19.5%)发生复发性溃疡出血;模型基于六项参数,1年内出血复发AUROC为0.648,验证队列AUROC为0.775、总体准确率84.3%。
要点
- 训练队列复发性溃疡出血发生率为19.5%(4772/22 854),中位随访2.7年。
- IPU-ML基于年龄、基线血红蛋白及胃溃疡、胃肠道疾病、恶性肿瘤、感染六项参数。
- 验证队列1年内复发性溃疡出血AUROC为0.775,总体准确率84.3%。
核心结论
- 开发了机器学习模型IPU-ML,用于识别有特发性胃十二指肠溃疡出血病史且非复发性溃疡出血高危的患者。
研究设计与样本
- 回顾性队列研究,训练队列为2007-2016年诊断消化性溃疡病的22 854例患者。
- 独立验证队列为2008-2015年来自不同人群的1265例消化道出血患者。
- 预测因子纳入标准为在研究人群中发生率超过1%的合并症。
主要发现
- 训练队列中位随访2.7年期间,4772例(19.5%)发生复发性溃疡出血。
- IPU-ML基于六项参数(年龄、基线血红蛋白、胃溃疡、胃肠道疾病、恶性肿瘤和感染)预测1年内出血复发,AUROC为0.648。
- IPU-ML截断值设为0.20时,27.5%的患者被归类为再出血高风险,敏感度41.4%,特异度74.6%,阴性预测值91.1%。
- 验证队列中,IPU-ML预测1年内复发性溃疡出血的AUROC为0.775,总体准确率84.3%。
关键数值与推荐
- IPU-ML截断值0.20:高风险患者占27.5%,敏感度41.4%,特异度74.6%,阴性预测值91.1%。
- 训练队列AUROC 0.648,验证队列AUROC 0.775,验证队列总体准确率84.3%。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Patients with a history of Helicobacter pylori-negative idiopathic bleeding ulcers have an increased risk of recurring ulcer complications. AIM: To build a machine learning model to identify patients at high risk for recurrent ulcer bleeding. METHODS: Data from a retrospective cohort of 22 854 patients (training cohort) diagnosed with peptic ulcer disease in 2007-2016 were analysed to build a model (IPU-ML) to predict recurrent ulcer bleeding. We tested the IPU-ML in all patients with a diagnosis of gastrointestinal bleeding (n = 1265) in 2008-2015 from a different catchment population (independent validation cohort). Any co-morbid conditions which had occurred in >1% of study population were eligible as predictors. RESULTS: Recurrent ulcer bleeding developed in 4772 patients (19.5%) in the training cohort, during a median follow-up period of 2.7 years. IPU-ML model built on six parameters (age, baseline haemoglobin, and presence of gastric ulcer, gastrointestinal diseases, malignancies, and infections) identified patients with bleeding recurrence within 1 year with an area under the receiver operating characteristic curve (AUROC) of 0.648. When we set the IPU-ML cutoff value at 0.20, 27.5% of patients were classified as high risk for rebleeding with a sensitivity of 41.4%, specificity of 74.6%, and a negative predictive value of 91.1%. In the validation cohort, the IPU-ML identified patients with a recurrence ulcer bleeding within 1 year with an AUROC of 0.775, and 84.3% of overall accuracy. CONCLUSION: We developed a machine-learning model to identify those patients with a history of idiopathic gastroduodenal ulcer bleeding who are not at high risk for recurrent ulcer bleeding.
引用
- Wong GL, Ma AJ, Deng H, et al. Machine learning model to predict recurrent ulcer bleeding in patients with history of idiopathic gastroduodenal ulcer bleeding. Aliment Pharmacol Ther. 2019. PMID: 30761584. doi:10.1111/apt.15145
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。