Scholarlink

<p>Endoscopic interventions are essential for diagnosing and treating gastrointestinal conditions. Accurate and comprehensive documentation is crucial for enhancing patient safety and optimizing clinical outcomes; however, adverse events remain underreported. This study evaluates a machine learning-based approach for systematically detecting endoscopic adverse events from real-world clinical metadata, including structured hospital data such as ICD-codes and procedure timings. Using a random forest classifier detecting adverse events perforation, bleeding, and readmission, we analysed 2490 inpatient cases, achieving significant improvements over baseline prediction accuracy. The model achieved AUC-ROC/AUC-PR values of 0.9/0.69 for perforation, 0.84/0.64 for bleeding, and 0.96/0.9 for readmissions. Results highlight the importance of multiple metadata features for robust predictions. This semi-automated method offers a privacy-preserving tool for identifying documentation discrepancies and enhancing quality control. By integrating metadata analysis, this approach supports better clinical decision-making, quality improvement initiatives, and resource allocation while reducing the risk of missed adverse events in endoscopy.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

How machine learning on real world clinical data improves adverse event recording for endoscopy

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年7月10日

查看全文
  • Stefan Wittlinger,
  • Isabella C. Wiest,
  • Mahboubeh Jannesari Ladani,
  • Jakob Nikolas Kather,
  • Matthias P. Ebert,
  • Fabian Siegel,
  • Sebastian Belle

摘要

Endoscopic interventions are essential for diagnosing and treating gastrointestinal conditions. Accurate and comprehensive documentation is crucial for enhancing patient safety and optimizing clinical outcomes; however, adverse events remain underreported. This study evaluates a machine learning-based approach for systematically detecting endoscopic adverse events from real-world clinical metadata, including structured hospital data such as ICD-codes and procedure timings. Using a random forest classifier detecting adverse events perforation, bleeding, and readmission, we analysed 2490 inpatient cases, achieving significant improvements over baseline prediction accuracy. The model achieved AUC-ROC/AUC-PR values of 0.9/0.69 for perforation, 0.84/0.64 for bleeding, and 0.96/0.9 for readmissions. Results highlight the importance of multiple metadata features for robust predictions. This semi-automated method offers a privacy-preserving tool for identifying documentation discrepancies and enhancing quality control. By integrating metadata analysis, this approach supports better clinical decision-making, quality improvement initiatives, and resource allocation while reducing the risk of missed adverse events in endoscopy.