机器学习改善了胃肠道手术后术后结果的预测:系统性审查和元分析
Jane Wang1, Francesca Tozzi2, Amir Ashraf Ganjouei1
1Department of Surgery, University of California, San Francisco, San Francisco, California, United States.
概括
机器学习 (ML) 模型在预测胃肠道手术结果方面明显优于逻辑回归 (LR). 这次系统审查强调了ML的ML.
科学领域:
- 手术预测结果的预测.
- 医疗数据分析 医疗数据分析
- 比较有效性研究比较有效性研究
背景情况:
- 机器学习 (ML) 越来越多地用于预测手术结果.
- 机器学习对逻辑回归 (LR) 等传统统计方法的优势仍然不清楚.
- 本研究比较了ML和LR模型在预测胃肠道 (GI) 手术中术后结果方面的表现.
研究的目的:
- 系统地审查和元分析ML与LR模型的性能.
- 为了比较ML和LR模型在预测胃肠道手术患者的术后结果方面的区分能力.
主要方法:
- 在主要的科学数据库 (Embase,MEDLINE,Cochrane,Web of Science,Google Scholar) 进行系统搜索,直到2022年12月.
- 使用随机效应模型进行元分析,以对ML和LR模型的接收器运行特征曲线 (AUC) 下的面积进行比较.
- 包括38项研究,使用62个LR模型和143个ML模型.
主要成果:
- 在ML模型中,平均AUC明显高于LR模型 (ΔAUC = 0.07;P < .001).
- 与LR模型相比,ML模型还显示AUC的平均逻辑值明显高 (Δlogit [AUC] = 0.41;P < .001).
- 这些发现即使在低偏差风险的研究子集分析中仍然具有意义.
结论:
- 与后勤回归相比,机器学习算法在预测胃肠道手术术后术后果方面提供了显著的改进.
- 需要标准化的协议来开发和报告手术研究中的ML模型.
- 进一步的研究应该集中在临床实践中的ML模型的实际实施上.
相关概念视频
Endoscopic Procedures IV: Sigmoidoscopy and Laproscopy
80
Sigmoidoscopy and laparoscopy are distinct medical procedures that enable physicians to internally inspect different parts of the GI tract. Although they serve different purposes, each is essential for diagnosing and, in some cases, treating various medical conditions.
Sigmoidoscopy
Sigmoidoscopy is a diagnostic procedure that uses a flexible sigmoidoscope equipped with a light source and camera to examine the rectum and sigmoid colon. The procedure involves inserting the tube through the anus...
Sigmoidoscopy
Sigmoidoscopy is a diagnostic procedure that uses a flexible sigmoidoscope equipped with a light source and camera to examine the rectum and sigmoid colon. The procedure involves inserting the tube through the anus...
80
Peptic Ulcer Disease V: Surgical Management and Nursing Care
302
Surgical management and nursing care are crucial in treating Peptic Ulcer Disease (PUD). Here is an organized and enhanced overview of the surgical interventions and the associated nursing care for PUD:
Surgical Interventions for Peptic Ulcer Disease
Surgical Interventions for Peptic Ulcer Disease
302


