机器学习帮助管理一般病房的急性损伤:多中心回顾性研究
Nam-Jun Cho1, Inyong Jeong2, Se-Jin Ahn2
1Department of Internal Medicine, Soonchunhyang University Cheonan Hospital, Cheonan, Republic of Korea.
Journal of medical Internet research
|March 18, 2025
概括
一个新的机器学习框架准确地预测一般病房患者的急性损伤 (AKI) 和急性病 (AKD). 这个AI工具使用了精细的AKI定义,提高了临床相关性,并使早期干预成为可能.
科学领域:
- 腎臟病學 (nephrology) 是一種醫學專業.
- 人工智能的人工智能
- 机器学习 机器学习
- 预测分析是一种预测分析.
背景情况:
- 目前用于急性损伤 (AKI) 预测的AI模型主要是为重症监护病房开发的,限制了它们在一般医院病房的应用.
- 标准化的AKI定义和依赖ICU数据阻碍了现有的预测模型的临床实用性.
- 需要人工智能工具,可以通用到非关键护理环境,并利用精细的诊断标准.
研究的目的:
- 开发和验证机器学习 (ML) 框架,用于预测一般病房患者的AKI和急性病 (AKD).
- 通过使用精细的操作定义来提高AKI模型的临床相关性和预测性能.
- 提供一种工具,以协助在重症监护室以外的AKI和AKD管理.
主要方法:
- 一项回顾性多中心队列研究,涉及来自韩国3家医院的135,068名患者.
- AKI和AKD是使用修改的病:改善全球结果 (KDIGO) 标准来定义的,包括调整的基线肌素和更严格的增加值.
- 机器学习模型被开发用于早期预测AKI (3天前) 和AKD (AKI后7天内没有恢复).
主要成果:
- 与标准KDIGO (5407) 相比,精细的AKI标准发现了较少的病例 (2898),减少了暂时波动的错误分类.
- 对AKI的早期预测模型显示出高精度,AUC为0.9053 (内部) 和0.8860 (外部).
- 对AKD的早期预测模型实现了0.8202 (内部) 和0.7833 (外部) 的AUC,表明强大的预测能力.
结论:
- 开发的ML框架准确地预测了一般病房人口中的AKI和AKD.
- 精确的AKI定义有效地减少了与短暂的肌素变化相关的错误分类错误.
- 在临床工作流程中实施这种ML框架可以促进及时干预,优化资源配置,并改善AKI和AKD患者的治疗结果.
相关概念视频
Dialysis
244
Renal failure occurs when the kidneys lose their ability to filter waste products from the blood effectively. It can be classified into two types: acute renal failure (ARF) and chronic renal failure (CRF).
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
Acute kidney injury develops suddenly and can be caused by pre-renal causes (e.g., hypovolemia, shock), intrinsic renal causes (e.g., acute tubular necrosis), or post-renal causes (e.g., urinary obstruction). In contrast, chronic renal failure progresses gradually over time and is often...
244
Factors Affecting Renal Clearance: Renal Impairment
45
Renal dysfunction significantly impairs the renal clearance of drugs, leading to potential complications in drug therapy. Renal failure, which can be caused by various factors, poses a significant challenge in the elimination of drugs from the body.
One condition associated with renal failure is uremia. Uremia is characterized by impaired glomerular filtration and fluid accumulation in the body. This condition hinders the renal clearance of drugs, resulting in drug accumulation and potential...
One condition associated with renal failure is uremia. Uremia is characterized by impaired glomerular filtration and fluid accumulation in the body. This condition hinders the renal clearance of drugs, resulting in drug accumulation and potential...
45


