使用隐性类分析和机器学习对复杂多病症进行分类,以产生对心理和心脏代谢状况集群的见解
Moumita Mukherjee1, Samhita Mukherjee2, Hruthik Reddy Thokala3
1Wissenschaftliche Mitarbeiterin, Institute of International Health, Charité - Universitätsmedizin, Berlin, Germany.
机器学习准确地预测了复杂的多病症,揭示了由心理健康和心脏代谢条件主导的五个集群. 关键因素包括年龄,健康状况和生活方式,为公共卫生干预提供信息.
科学领域:
- 公共卫生 公共卫生
- 计算生物学 计算生物学
- 流行病学 流行病学
背景情况:
- 复杂的多病症,特别是心脏代谢和精神健康状况,构成了重大的公共卫生挑战.
- 机器学习 (ML) 为预测和分类复杂健康状况提供了先进的能力.
研究的目的:
- 使用隐性类分析 (LCA) 定义复杂的多病态性集群.
- 评估各种ML模型在将个人分类到这些集群中的表现.
- 确定影响多发病性的关键风险和保护因素.
主要方法:
- 隐性类分析 (LCA) 应用于CDC BRFSS 2015数据 (n=46,736) 以确定多病症集群.
- 训练了六个ML算法 (MLR,MNB,DT,RF,XGB,ANN) 进行分类.
- 模型性能通过AUROC进行评估,准确性,精度,回忆,F1得分;通过RF,排列和SHAP值来评估特征重要性.
主要成果:
- 确定了五个不同的复杂多重疾病群,其中1个心血管和4个心脏代谢群中普遍存在精神健康状况.
- 随机森林模型显示出优异的分类性能 (AUROC=0.805).
- ML模型之间的显著分歧证实了模型选择的适用性;年龄,健康状况,社会经济因素和生活方式是关键预测因素.
结论:
- 心理健康是塑造多病态模式的关键决定因素.
- 人工智能驱动的分类提高了风险人群的预测准确性.
- 这项研究为将ML整合到公共卫生决策支持系统中提供了一个用例.
更多相关视频
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
相关概念视频
Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
Cardiomyopathy I: Introduction and Classification
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Multicompartment Models: Overview
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...
Coronary Artery Disease I: Introduction
