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

Abstract

Routinely collected health data (RCD) are currently accelerating publications that evaluate the effectiveness and safety of medicines and medical devices. One of the fundamental steps in using these data is developing algorithms to identify health status that can be used for observational studies. However, the process and methodologies for identifying health status from RCD remain insufficiently understood. While most current methods rely on International Classification of Diseases (ICD) codes, they may not be universally applicable. Although machine learning methods hold promise for more accurately identifying the health status, they 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 boost the credibility of findings from observational studies that use RCD.

Keywords: Health status; Machine learning algorithms; Routinely collected health data; Rule-based algorithms.

Fig. 1

illustration of key steps for identifying health statuses from RCD. Rule-based approaches involve the use of expert-defined logic rules, such as those based on specific indicators like ICD codes, medication prescription, or specific laboratory test results. These rules often utilize Boolean logic (e.g., AND, OR, NOT) and other logical criteria to identify and classify features. The machine learning approaches may involve models such as random forest, decision trees, regression, naïve bayes, which are trained on a dataset to learn patterns and make classification predictions.