使用机器学习和传统的统计方法,基于药物治疗的COPD死亡率预测
Ana Paula Bruno Pena-Gralle1, Amélie Forget2, Yohann Moanahere Chiu3
1Faculty of Pharmacy, Université de Montréal, Montréal, QC, Canada.
International journal of medical informatics
|November 7, 2025
概括
药物数据可以预测慢性阻塞性肺病 (COPD) 患者的五年死亡率. 机器学习模型,特别是深层人工神经网络,在使用药物声明来预测COPD死亡率方面显示出有希望的结果.
科学领域:
- 肺部医学 肺部医学
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
背景情况:
- 预测慢性阻塞性肺病 (COPD) 的死亡率对于患者护理和资源管理至关重要.
- 传统的预测模型通常需要在临床实践中不经常收集的数据.
- 药物声明数据为COPD患者的死亡率预测提供了一个可访问的替代方案.
研究的目的:
- 评估基于药物的预测因子对预测COPD患者5年全因死亡率的有效性.
- 为了比较物流回归的性能与各种机器学习 (ML) 方法进行死亡率预测.
- 确定作为COPD死亡率的重要预测剂的关键药物类别.
主要方法:
- 一项回顾性队列研究,涉及179,168名40岁及以上的慢性肺炎患者.
- 分析包括社会人口统计数据,COPD药物使用,以及其他慢性疾病的药物.
- 将后勤回归与六种ML方法进行比较,包括深度人工神经网络 (D-ANN),用于5年死亡率预测.
主要成果:
- 在研究队列中,五年死亡率为24.3%.
- 后勤回归模型的AUC-ROC达到0.749 (仅使用COPD药物) 到0.778 (添加其他药物).
- 深度人工神经网络 (D-ANN) 显示出最高的预测性能,AUC-ROC为0.787,略高于物流回归.
结论:
- 基于药物的预测模型可以有效估计COPD患者5年全因死亡率.
- 当临床,生理或成像数据不可用时,这些模型可以作为一个可行的代理.
- 机器学习,特别是D-ANN,在预测准确度方面比传统方法对COPD死亡率略有改善.
相关概念视频
01:26COPD: Management Using Bronchodilators and Corticosteroids
709
Chronic obstructive pulmonary isease (COPD) involves a group of progressive lung disorders characterized by persistent airflow limitation and chronic respiratory symptoms. Asthma-COPD Overlap Syndrome (ACOS), encompassing features of both asthma and Chronic obstructive pulmonary disease (COPD), is a group of progressive lung disorders that includes chronic bronchitis, emphysema, and refractory (non-reversible) asthma. ACOS leads to complex clinical presentations that combine the inflammatory...
709
01:25Statistical Methods for Analyzing Epidemiological Data
888
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
888
01:29Chronic Obstructive Pulmonary Disease-V: Management
3.1K
Managing Chronic Obstructive Pulmonary Disease (COPD) involves a multifaceted approach to reduce symptoms, prevent exacerbations, improve overall health status, and slow disease progression. Key strategies include lifestyle modifications, pharmacotherapy, supportive therapies, and, in some cases, surgery. Here is an overview of the primary COPD management strategies:
Smoking Cessation
Smoking Cessation
3.1K
01:23Mechanistic Models: Compartment Models in Individual and Population Analysis
235
Mechanistic models are utilized in individual analysis using single-source data, but imperfections arise due to data collection errors, preventing perfect prediction of observed data. The mathematical equation involves known values (Xi), observed concentrations (Ci), measurement errors (εi), model parameters (ϕj), and the related function (ƒi) for i number of values. Different least-squares metrics quantify differences between predicted and observed values. The ordinary least...
235
01:27Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
3.1K
Assessing and diagnosing Chronic Obstructive Pulmonary Disease (COPD) involves a detailed approach that includes a comprehensive review of medical history, physical examination, and a variety of diagnostic tests. This thorough evaluation is essential to ensure an accurate diagnosis and guide effective management strategies.
Medical History
Medical History
3.1K
01:24Kaplan-Meier Approach
547
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
547