传统的基于机器学习的预测模型没有超过国际IgA脏病预测工具的表现
Sehoon Park1, Yisak Kim2,3, Chung Hee Baek4
1Department of Internal Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
Kidney research and clinical practice
|October 9, 2024
概括
机器学习模型在预测IgA脏病 (IgAN) 患者病进展方面表现有前途. 然而,这些先进的模型并没有超过现有的国际IgA脏病预测工具.
科学领域:
- 腎臟病學 (nephrology) 是一種醫學專業.
- 医疗信息学 医疗信息学
- 生物统计学 生物统计学
背景情况:
- 免疫球蛋白A脏病 (IgAN) 是末期脏病 (ESKD) 的主要原因之一.
- 国际IgA脏病预测工具 (IIgAN-PT) 目前可以预测IgAN的预后.
- 需要使用机器学习 (ML) 方法来提高预测性能.
研究的目的:
- 开发和评估基于ML的模型,用于预测Igan患者病进展.
- 将ML模型的性能与现有的IIgAN-PT进行比较.
主要方法:
- 来自九家韩国医院的4425名活检确认的Igan患者的分析.
- 开发了四种ML模型:CatBoost,优化的CatBoost与Cox,深层Cox危险和深层Cox混合模型.
- 使用曲线下的面积 (AUC) 和校准图表评估模型性能,与IIgAN-PT相比.
主要成果:
- 该IIgAN-PT完整模型表现出色 (AUC为5年结果为0.896).
- 基于ML的模型在外部验证中显示出良好的预测性能 (AUC从0.823到0.847).
- 在外部验证队列中,ML模型略低估计了外部验证队列中的风险;整体性能不低于IIgAN-PT.
结论:
- 基于ML的模型在IGAN中预测脏不良结果方面表现良好.
- 在这项研究中,开发的ML模型的性能并没有超过已建立的IIgAN-PT.
- 可能需要进一步的研究来完善IGAN预后的ML方法.
相关概念视频
01:30Acute Kidney Injury IV: Diagnostic Studies and Prevention
2
Accurate diagnosis and effective prevention are critical in managing Acute Kidney Injury (AKI), which is linked to high mortality rates ranging from 10% to 80%. Timely recognition of at-risk patients and careful monitoring can significantly reduce the likelihood of kidney damage.Diagnostic Assessments:The diagnostic process starts with a comprehensive medical history to identify prerenal, intrarenal, and postrenal causes.Prerenal causes, such as dehydration, hypotension, or blood loss, should...
2
01:26Nephrotic Syndrome II : Assessment and Medical Management
2
IntroductionNephrotic syndrome is a kidney disorder marked by excessive protein loss in the urine, leading to various systemic complications. This condition often results from damage to the glomeruli—the kidney's filtering units—causing proteinuria, low blood protein levels, and fluid retention. Understanding the assessment, diagnosis, and management of nephrotic syndrome is essential for effective treatment and prevention of further kidney damage.AssessmentPatient History: Document...
2