机器学习模型用于预测非心脏手术患者的术后妄想 - 系统性审查和元分析
Oishika Das1, Linda Y Tang1, Esther S Oh2
1Department of Neurosurgery, Johns Hopkins University School of Medicine, 1800 Orleans St, Baltimore, MD, 21287, USA.
GeroScience
|November 14, 2025
概括
机器学习模型在预测老年手术患者手术后妄想症 (POD) 的准确度中等至高. 然而,它们的临床适用性有限,需要进一步的验证和整合努力.
科学领域:
- 老年医学 老年医学
- 医疗信息学 医疗信息学
- 手术瘤学手术瘤学
背景情况:
- 手术后妄 (POD) 显著影响老年手术患者,需要早期诊断才能进行有效的干预.
- 使用机器学习 (ML) 的风险预测模型 (RPM) 对POD预测具有前景,但其实际性能和质量需要评估.
研究的目的:
- 在接受非心脏手术的老年人中系统地审查POD的RPM的预测准确性和质量.
- 评估2014年至2024年间开发的基于ML的RPM.
主要方法:
- 在PubMed和EMBASE的系统文献搜索中,寻找开发POD预测模型的研究.
- 使用PROBAST工具对298项研究进行了独立选和质量评估.
- 对性能指标 (AUROC,灵敏度,特异性,精度) 的聚合分析.
主要成果:
- 22项研究符合标准,主要使用ML技术,如梯度增强和随机森林.
- 聚合的AUROC为0.82 (95% CI:0.79-0.85),表明预测准确度中等至高.
- 灵敏度,特异性和精度分别为0.78,0.83和0.55. 这三种特异性和精度分别为0.78,0.83和0.55. 更复杂的模型并不总是超过更简单的模型.
结论:
- 虽然新的基于ML的POD的RPM显示出良好的预测准确性,并且更有可能得到验证,但它们的解释性和临床适用性仍然受到限制.
- 需要大力将这些模型纳入临床实践,重点是外部验证,减少假阳性,并将预测转化为行动.
相关概念视频
01:28Cardiomyopathy VII: Pre and Post Operative Nursing Management
268
Patients with hypertrophic cardiomyopathy (HCM) and left ventricular outflow tract (LVOT) obstruction who remain symptomatic despite optimal medical therapy may undergo a septal myectomy (Morrow procedure). This procedure involves excising a portion of the hypertrophied septum below the aortic valve using a heart-lung machine to improve blood flow through the LVOT. Effective preoperative and postoperative nursing management ensures successful patient outcomes, minimizes complications, and...
268
01:22Stages of General Anesthesia
1.4K
Various sedation levels offer significant advantages in facilitating procedural interventions for patients undergoing medical or invasive surgical procedures. These levels span from anxiolysis to general anesthesia, providing a spectrum of sedative effects to cater to specific patient needs. Anxiolysis reduces anxiety and is achieved through minimal sedation, enabling patients to remain awake and responsive while feeling more at ease during the procedure. This level can benefit minor...
1.4K