糖尿病前期预测模型的开发,验证和重新校准:基于EHR和NHANES的研究
Nicholas J Casacchia1, Kristin M Lenoir2, Joseph Rigdon2
1Center for Value-Based Care Research, Primary Care Institute, Cleveland Clinic, 9500 Euclid Ave, G10, Cleveland, OH, 44195, USA. casaccn@ccf.org.
BMC medical informatics and decision making
|December 19, 2024
概括
一个新的模型有效地使用电子健康记录 (EHR) 预测糖尿病前期风险,显示与更复杂的方法相似的性能. 这种近似模型适用于使用国家调查数据进行外部验证.
科学领域:
- 医疗信息学 医疗信息学
- 临床预测建模临床预测建模
- 糖尿病研究 糖尿病研究
背景情况:
- 糖尿病前期的鉴定对于预防2型糖尿病至关重要.
- 电子健康记录 (EHR) 为开发预测模型提供了有价值的数据来源.
- 现有的模型可能需要复杂的变量选择,这带来了资源挑战.
研究的目的:
- 内部评估一种新的惩罚性回归模型,用于预测高血糖血红蛋白 (HbA1c) 的水平.
- 为了比较新模型的性能与更简单的糖尿病前期风险逐步近似模型.
- 用国家健康和营养检查调查 (NHANES) 数据对近似模型进行外部验证和重新校准.
主要方法:
- 通过最小绝对缩小和选择运算符 (LASSO) 和渐进近似来使用EHR数据开发了后勤回归模型.
- 使用引导方法进行内部验证,使用Brier分数,C统计和校准指标评估性能.
- 在NHANES数据上对近似模型进行外部验证,评估带有和没有重新校准的性能.
主要成果:
- 拉索和近似模型都显示了EHR队列中类似的歧视 (C统计~0.76).
- 与LASSO (23) 相比,近似模型需要较少的预测变量 (8).
- 在使用NHANES数据 (C-统计=0.787) 的外部验证中,近似模型表现良好.
结论:
- 逐步近似模型提供了一个可行的,资源高效的替代LASSO预测糖尿病前期风险从EHR数据.
- 使用NHANES数据进行的外部验证证明了近似模型对全国代表性样本的概括性.
- 这些发现支持使用来自EHR的预测模型来识别面临风险的人群,并仔细考虑对外部验证的变量调整.
关键词:
校准 校准 校准 校准 校准 校准电子健康记录是电子健康记录.外部验证的验证方法拉索·拉索 (Lasso) 是一个后勤回归的逻辑回归尼汉斯 (NHANES) 是一个名人.糖尿病前期:糖尿病前期.预测模型的预测模型.更多相关视频
相关概念视频
Data Validation
4.9K
Data validation is an essential part of a comprehensive assessment. Validation is confirming or verifying and opening the door to gathering more assessment data as it clarifies vague or unclear data. The process of checking and verifying the collected information is called data validation. The primary purpose of data validation is to ensure data is as free from error, bias, and misinterpretation as possible.
Nursing assessment guides are generally based on holistic models rather than medical...
Nursing assessment guides are generally based on holistic models rather than medical...
4.9K
Errors occurring during blood pressure monitoring
599
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...
599


