基于机器学习的即时护理风险计算器的开发与验证:用于预测ERCP后胰腺炎及选择预防措施
本研究利用12项随机对照试验的7389例患者数据训练梯度提升机模型预测ERCP后胰腺炎风险,模型纳入20个风险因素和5种预防干预,AUC为0.70,阴性预测值95%。在约翰斯·霍普金斯医院为期1个月的前瞻性试点研究中,135例患者验证AUC为0.74,显示该工具具有可行性和实用性。
要点
- 基于12项随机对照试验的7389例患者数据开发了梯度提升机模型,ERCP后胰腺炎发生率为8.6%。
- 模型纳入20个风险因素和5种预防干预,AUC为0.70,特异性65%,敏感性65%,阴性预测值95%,阳性预测值15%。
- 前瞻性试点研究纳入135例患者,AUC为0.74,显示该工具可用于选择预防措施和识别低风险患者。
核心结论
- 本研究表明,一种新型的基于机器学习的ERCP后胰腺炎风险评估工具具有可行性和实用性,其高阴性预测值有助于选择预防措施并识别可能不需要延长术后监测的低风险患者。
研究设计与样本
- 研究利用12项随机对照试验的患者层面数据进行特征选择、模型训练和验证,训练梯度提升机模型估计ERCP后胰腺炎风险,采用5折交叉验证以受试者工作特征曲线下面积(AUC)评估性能。
- 创建了基于网络的临床决策工具,并使用约翰斯·霍普金斯医院为期1个月内的ERCP数据进行了前瞻性试点研究。
主要发现
- 共7389例患者纳入梯度提升机模型,ERCP后胰腺炎发生率为8.6%。
- 模型基于20个ERCP后胰腺炎风险因素和5种预防干预(直肠非甾体抗炎药、积极水化、直肠非甾体抗炎药联合积极水化、胰管支架置入、直肠非甾体抗炎药联合胰管支架置入)进行训练。
- 梯度提升机模型的AUC为0.70,特异性65%,敏感性65%,阴性预测值95%,阳性预测值15%。
- 前瞻性试点研究共纳入135例患者,AUC为0.74。
关键数值与推荐
- 梯度提升机模型纳入的20个ERCP后胰腺炎风险因素和5种预防干预:直肠非甾体抗炎药、积极水化、直肠非甾体抗炎药联合积极水化、胰管支架置入、直肠非甾体抗炎药联合胰管支架置入。
- 模型性能:AUC 0.70,特异性65%,敏感性65%,阴性预测值95%,阳性预测值15%。
- 前瞻性试点研究性能:AUC 0.74。
临床怎么用
- 原文未据此给出推荐。
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 AND AIMS: A robust model of post-ERCP pancreatitis (PEP) risk is not currently available. We aimed to develop a machine learning-based tool for PEP risk prediction to aid in clinical decision making related to periprocedural prophylaxis selection and postprocedural monitoring. METHODS: Feature selection, model training, and validation were performed using patient-level data from 12 randomized controlled trials. A gradient-boosted machine (GBM) model was trained to estimate PEP risk, and the performance of the resulting model was evaluated using the area under the receiver operating curve (AUC) with 5-fold cross-validation. A web-based clinical decision-making tool was created, and a prospective pilot study was performed using data from ERCPs performed at the Johns Hopkins Hospital over a 1-month period. RESULTS: A total of 7389 patients were included in the GBM with an 8.6% rate of PEP. The model was trained on 20 PEP risk factors and 5 prophylactic interventions (rectal nonsteroidal anti-inflammatory drugs [NSAIDs], aggressive hydration, combined rectal NSAIDs and aggressive hydration, pancreatic duct stenting, and combined rectal NSAIDs and pancreatic duct stenting). The resulting GBM model had an AUC of 0.70 (65% specificity, 65% sensitivity, 95% negative predictive value, and 15% positive predictive value). A total of 135 patients were included in the prospective pilot study, resulting in an AUC of 0.74. CONCLUSIONS: This study demonstrates the feasibility and utility of a novel machine learning-based PEP risk estimation tool with high negative predictive value to aid in prophylaxis selection and identify patients at low risk who may not require extended postprocedure monitoring.
引用
- Brenner T, Kuo A, Sperna Weiland CJ, et al. Development and validation of a machine learning-based, point-of-care risk calculator for post-ERCP pancreatitis and prophylaxis selection. Gastrointest Endosc. 2024. PMID: 39147103. doi:10.1016/j.gie.2024.08.009
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。