Methods for identifying health status from routinely collected health data: An overview

The use of routinely collected health data (RCD) is currently helping to accelerate publications that evaluate the effectiveness and safety of medicines and medical devices. One fundamental step in using these data is developing algorithms to identify health status for use in observational studies....

Full description

Saved in:
Bibliographic Details
Main Authors: Mei Liu, Ke Deng, Mingqi Wang, Qiao He, Jiayue Xu, Guowei Li, Kang Zou, Xin Sun, Wen Wang
Format: Article
Language:English
Published: Elsevier 2025-03-01
Series:Integrative Medicine Research
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2213422024000805
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The use of routinely collected health data (RCD) is currently helping to accelerate publications that evaluate the effectiveness and safety of medicines and medical devices. One fundamental step in using these data is developing algorithms to identify health status for use in observational studies. However, the processes and methodologies for determining health status using RCD remain insufficiently understood. While most current methods rely on the World Health Organization’s International Classification of Diseases (ICD) codes, they may not be universally applicable. Although machine learning methods are promising for more accurately identifying health status, they currently remain underutilized in RCD studies. To address these significant methodological gaps, we outline key steps and methodological considerations for identifying health statuses in observational studies using RCD. This review has the potential to reinforce the credibility of findings from observational studies that use RCD.
ISSN:2213-4220