提高初级保健的准确性和效率,使用机器学习方法对老年人进行跌倒风险查
Wenyu Song1,2, Nancy K Latham1,2, Luwei Liu1
1Department of Medicine, Brigham and Women's Hospital, Boston, Massachusetts, USA.
Journal of the American Geriatrics Society
|January 13, 2024
概括
使用电子健康记录的机器学习准确地识别了有跌倒风险的老年人,其表现优于传统问卷. 这种方法可以在初级保健中及时,个性化地实施预防跌倒的策略.
科学领域:
- 老年学是一门学科.
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
背景情况:
- 跌倒是老年人受伤和死亡的主要原因,目前初级保健的查方法有局限性.
- 标准落风险查问卷往往缺乏准确性,缺少数据和不一致的格式,阻碍了早期干预.
- 电子健康记录 (EHR) 为开发更有效的跌倒风险预测工具提供了丰富的数据来源.
研究的目的:
- 开发和评估使用EHR数据的机器学习模型,用于预测老年人中与跌倒相关的伤害.
- 为了比较基于EHR的机器学习模型与传统的跌倒风险查问卷的性能.
- 创建一个临床决策支持 (CDS) 工具,将确定的风险与预防性干预联系起来.
主要方法:
- 一项病例控制研究使用来自综合医疗保健系统的患者数据进行.
- 使用纵向EHR数据开发了四种时间机器学习模型,以预测未来的摔倒伤害风险.
- 创建了一个防摔伤害CDS原型,以将干预措施与患者特定的风险联系起来.
主要成果:
- 基于问卷的查显示精度有限 (AUC高达0.59).
- 基于EHR的机器学习模型显著提高了跌伤预测性能 (最佳AUROC=0.76).
- 在6个月和一年的预测模型之间,预测性能一致.
结论:
- 目前基于问卷的老年人跌倒风险查由于冗余和缺乏精确性而不足以达到最佳水平.
- 使用EHR数据的机器学习预测方法为识别跌倒风险提供了更高的准确性和灵敏性.
- 开发的算法和数据科学管道有可能增强常规的初级保健防摔实践.
相关概念视频
01:25Errors occurring during blood pressure monitoring
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
01:15Drug Dosing: Geriatric Patients
Elderly individuals encompass a diverse population with varying degrees of age-related physiological changes. Defining the elderly presents challenges, as the geriatric population is often arbitrarily categorized as individuals older than 65. However, many individuals in this group lead active and healthy lives, with an increasing number surpassing 85 years and falling into the older elderly category. Physiological changes associated with aging impact performance capacity and homeostatic...