文献速递消化道出血

基于电子健康记录的机器学习模型与临床风险评分对消化道出血的验证比较

Validation of an Electronic Health Record-Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding.
PubMed 文献 · Gastroenterology · 2024-07-05

本研究的训练队列包含2546例、内部验证850例、外部验证926例于2014至2019年因显性消化道出血就诊于急诊的患者,采用电子健康记录结构化字段构建机器学习模型,并与格拉斯哥-布拉奇福德评分和奥克兰评分比较。机器学习模型预测主要复合结局的曲线下面积为0.92,优于两种评分的0.89,在99%敏感性阈值下识别出更多极低危患者。

要点

  • 机器学习模型曲线下面积0.92,高于格拉斯哥-布拉奇福德评分的0.89和奥克兰评分的0.89(P < .001)。
  • 在99%敏感性阈值下,机器学习模型识别极低危患者37.9%,格拉斯哥-布拉奇福德评分为18.5%,奥克兰评分为11.7%(P < .001)。
  • 模型使用就诊4小时内可获取的电子健康记录结构化字段,无需人工录入数据。

核心结论

  • 基于电子健康记录的机器学习模型表现优于目前推荐的临床风险评分,并识别出更多有资格从急诊出院的极低危患者。

研究设计与样本

  • 训练队列包含2546例患者,内部验证队列为850例于2014至2019年就诊于2家医院急诊的显性消化道出血患者。
  • 外部验证在另一家使用相同电子健康记录的医院进行,纳入2014至2019年的926例患者。
  • 主要结局为红细胞输注、止血干预(内镜、介入放射学或外科手术)和30天全因死亡的复合结局。
  • 使用就诊4小时内可获取的电子健康记录结构化数据字段,比较机器学习模型与指南推荐的格拉斯哥-布拉奇福德评分和奥克兰评分的表现。
  • 主要分析为受试者工作特征曲线下面积,次要分析为99%敏感性下的特异度。

主要发现

  • 机器学习模型的曲线下面积为0.92,格拉斯哥-布拉奇福德评分为0.89,两者比较P < .001。
  • 机器学习模型的曲线下面积为0.92,奥克兰评分为0.89,两者比较P < .001。
  • 在99%敏感性阈值下,机器学习模型识别极低危患者37.9%,格拉斯哥-布拉奇福德评分为18.5%,奥克兰评分为11.7%,两项比较P < .001。

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 & AIMS: Guidelines recommend use of risk stratification scores for patients presenting with gastrointestinal bleeding (GIB) to identify very-low-risk patients eligible for discharge from emergency departments. Machine learning models may outperform existing scores and can be integrated within the electronic health record (EHR) to provide real-time risk assessment without manual data entry. We present the first EHR-based machine learning model for GIB. METHODS: The training cohort comprised 2546 patients and internal validation of 850 patients presenting with overt GIB (ie, hematemesis, melena, and hematochezia) to emergency departments of 2 hospitals from 2014 to 2019. External validation was performed on 926 patients presenting to a different hospital with the same EHR from 2014 to 2019. The primary outcome was a composite of red blood cell transfusion, hemostatic intervention (ie, endoscopic, interventional radiologic, or surgical), and 30-day all-cause mortality. We used structured data fields in the EHR, available within 4 hours of presentation, and compared the performance of machine learning models with current guideline-recommended risk scores, Glasgow-Blatchford Score, and Oakland Score. Primary analysis was area under the receiver operating characteristic curve. Secondary analysis was specificity at 99% sensitivity to assess the proportion of patients correctly identified as very low risk. RESULTS: The machine learning model outperformed the Glasgow-Blatchford Score (area under the receiver operating characteristic curve, 0.92 vs 0.89; P < .001) and Oakland Score (area under the receiver operating characteristic curve, 0.92 vs 0.89; P < .001). At the very-low-risk threshold of 99% sensitivity, the machine learning model identified more very-low-risk patients: 37.9% vs 18.5% for Glasgow-Blatchford Score and 11.7% for Oakland Score (P < .001 for both comparisons). CONCLUSIONS: An EHR-based machine learning model performs better than currently recommended clinical risk scores and identifies more very-low-risk patients eligible for discharge from the emergency department.

来源:Gastroenterology,查看原文。版权归原作者所有。

引用

  1. Shung DL, Chan CE, You K, et al. Validation of an Electronic Health Record-Based Machine Learning Model Compared With Clinical Risk Scores for Gastrointestinal Bleeding. Gastroenterology. 2024. PMID: 38971198. doi:10.1053/j.gastro.2024.06.030

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。