集成机器学习预测90天的结果和分析急性损伤需要透析的风险因素
Tzu-Hao Wang1,2, Chih-Chin Kao3,4,5, Tzu-Hao Chang2,6
1Division of General Medicine, Department of Medical Education, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan, Republic of China.
Journal of multidisciplinary healthcare
|April 17, 2024
概括
机器学习准确地预测了急性损伤需要透析 (AKI-D) 患者的90天预后,确定了透析前肌素作为改善患者结果和临床决策的关键因素.
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
- 临床信息学 临床信息学
背景情况:
- 需要透析的急性损伤 (AKI-D) 在预测患者预后方面存在重大挑战.
- 现实世界的临床数据为开发AKI-D结果的预测模型提供了丰富的来源.
- 整体机器学习算法在分析复杂的临床数据集方面表现有前途.
研究的目的:
- 采用整体机器学习算法来预测AKI-D住院患者的90天预后.
- 确定影响透析依赖和初始透析后死亡率的重要因素.
- 开发一个验证的预测模型,以加强AKI-D患者护理中的临床决策.
主要方法:
- 利用来自台北医科大学临床研究数据库 (TMUCRD) (2008-2020) 的现实临床数据.
- 在谷歌云平台上开发集体机器学习模型,包括feedforward神经网络和渐变增强决策树.
- 分析了1080名透析依赖患者和2358名生存结果患者的数据.
主要成果:
- 组合模型实现了高性能:透析依赖的AUROC为0.846,生存的AUROC为0.865.
- 在初始透析前至少90天评估的基线肌素值被确定为最关键的预测因素.
- 与传统的物流回归相比,这些模型表现出优越的预测能力.
结论:
- 集成机器学习模型有效预测AKI-D患者的90天预后.
- 透析前的肌水平是患者整体预后的重要指标.
- 经过验证的预测模型可以帮助医疗保健提供者改善高风险AKI-D人群的临床决策和患者护理.
更多相关视频
09:16Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
6.9K
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.2K
相关概念视频
Dialysis
307
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...
307
Factors Affecting Renal Clearance: Renal Impairment
91
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...
91
