一个基于机器学习的预测模型提高了对非癌症相关肝硬化患者早期肝脑病的预测:台湾多中心纵向队列研究
Hsin-Yu Chen1, Yiu-Hua Cheng1,2, Wei-Chung Yeh1,2
1Department of Family Medicine, Keelung Chang Gung Memorial Hospital, Keelung, Taiwan.
JMIR medical informatics
|August 6, 2025
概括
一个新的机器学习模型准确地预测肝硬化患者的肝脑病变 (HE). 这种工具有助于临床决策,并减少HE并发症.
科学领域:
- 肝病学和胃肠道学
- 人工智能在医学中的应用
- 生物统计学 生物统计学
背景情况:
- 肝硬化症 (HE) 显著增加肝硬化患者的死亡率.
- 早期的HE预测至关重要,但具有挑战性,特别是在由于不可预测的进展而导致的非癌性肝硬化.
研究的目的:
- 开发和验证一种新的机器学习 (ML) 模型,用于在非癌性肝硬化中早期预测HE.
- 为了提高临床决策和患者管理的HE.
主要方法:
- 一个多中心的回顾性队列研究,涉及5888名肝硬化患者从2010-2017年.
- 应用和比较各种ML模型,包括极端梯度增强,神经网络和支持向量机器.
- 使用AUC,灵敏度,特异性和Youden指数进行性能评估;通过Shapley添加解释解释模型解释.
主要成果:
- 极端梯度增强模型在测试数据集中实现了最高的预测准确度,AUC为0.86,超过了其他ML模型和MELD得分.
- 该模型在0.25.5的概率值下显示了72%的灵敏度和80%的特异性.
- 发现的关键预测因素包括血清氨,AST,ALT,前列血时间和血清.
结论:
- 一个新的ML模型有效地预测非癌性肝硬化患者的HE.
- 这个模型提供了一个实用的工具,用于医生和患者之间的共享决策.
- 其目标是改善临床护理并减轻与健康相关的发病率.
相关概念视频
Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test
271
In clinical practice, the direct measurement of hepatic blood flow to evaluate liver function presents significant challenges due to the intricate and specialized nature of the necessary techniques. Consequently, healthcare professionals often rely on empirical estimates derived from thorough patient examinations and liver function tests to gauge liver health. Among the tools at their disposal, the Child–Pugh and MELD scoring systems stand out for their ability to categorize and assess...
271
Hepatic Encephalopathy
53
DefinitionHepatic encephalopathy is a reversible neurologic syndrome that results from advanced liver dysfunction or portosystemic shunting. It leads to disturbances in cognition, behavior, and motor function due to the brain’s exposure to gut-derived toxins that the liver fails to detoxify.EtiologyThis condition develops either in the setting of acute fulminant hepatitis or progressively during chronic liver disease, such as cirrhosis and portal hypertension. Portosystemic...
53


