图表审查和行政数据的比较,用于开发慢性阻塞性肺病再入院的预测模型
Sukarn Chokkara1, Michael G Hermsen2, Matthew Bonomo3
1Pritzker School of Medicine, University of Chicago, Chicago, Illinois, United States.
Chronic obstructive pulmonary diseases (Miami, Fla.)
|January 28, 2025
概括
机器学习模型可以预测慢性阻塞性肺病 (COPD) 患者的再入院情况. 行政数据为开发这些预测工具提供了一个可行的,不那么劳动密集的替代方案,而不是图表审查.
科学领域:
- 医疗信息学 医疗信息学
- 肺部病理学 肺部病理学
- 医疗保健中的机器学习
背景情况:
- 慢性阻塞性肺病 (COPD) 恶化经常导致重入医院,增加医疗保健成本.
- 预测模型对于识别高风险患者和实现及时干预以降低再入院率至关重要.
- 当前的预测工具通常依赖于劳动密集型图表审查,需要探索更有效的数据源.
研究的目的:
- 评估机器学习模型在预测COPD患者90天再入院的性能.
- 为了比较使用行政数据与图表审查数据开发的模型的预测准确度.
- 评估使用行政数据用于COPD再接收预测的可行性,作为一种不那么劳动密集的替代方案.
主要方法:
- 在芝加哥大学医学院对4327例COPD急性恶化的患者进行了分析.
- 开发和比较两个随机森林预测模型:一个使用行政数据,另一个使用图表审查数据.
- 数据分为70%的培训和30%的内部验证集,以评估模型性能.
主要成果:
- 两种机器学习模型都在预测COPD再入院时表现出可比的准确性.
- 从行政数据中得出的模型实现了曲线下的面积 (AUC) 为0.67.
- 来自图表审查数据的模型实现了0.64的AUC,表明类似的预测性能.
结论:
- 尽管在准确识别COPD入院患者方面存在潜在的局限性,但行政数据可以有效地用于开发患者再入院的预测工具.
- 基于行政数据的机器学习模型提供了一个有希望的,较少劳动密集型的方法,与传统的COPD再入院风险分层的图表审查相比.
- 这些发现支持将行政数据整合到预测分析中,以改善COPD患者的管理并减少医疗保健资源的利用.
相关概念视频
01:27Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
2.5K
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
2.5K
01:20Comparing the Survival Analysis of Two or More Groups
162
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
162
01:15Methods of Documentation VI: Case Management Model
564
The case management model is a multidisciplinary approach that involves healthcare professionals from diverse disciplines, such as physicians, nurses, therapists, social workers, and pharmacists, working collaboratively to address the various needs of patients. Each healthcare professional brings unique expertise and perspectives, contributing to a more comprehensive understanding of the patient's condition and tailoring treatment plans accordingly.
For example, a patient with a chronic...
For example, a patient with a chronic...
564
01:15Receiver Operating Characteristic Plot
101
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
101
01:30Chronic Obstructive Pulmonary Disease-V: Nursing Management
3.7K
Nursing management of Chronic Obstructive Pulmonary Disease (COPD) is crucial for providing thorough care and support to patients. Nurses play an integral role in this process through detailed assessment, careful planning, targeted interventions, and ongoing evaluation. Here's an overview of the critical steps in nursing management for COPD.
Assessment
Assessment
3.7K
01:25Statistical Methods for Analyzing Epidemiological Data
324
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:
324