Automatic Estimation of the Most Likely Drug Combination in Electronic Health Records Using the Smooth Algorithm: Development and Validation Study

Abstract

Background: Since the use of electronic health records (EHRs) in an automated way, pharmacovigilance or pharmacoepidemiology studies have been used to characterize the therapy using different algorithms. Although progress has been made in this area for monotherapy, with combinations of 2 or more drugs the challenge to characterize the treatment increases significantly, and more research is needed.

Objective: The goal of the research was to develop and describe a novel algorithm that automatically returns the most likely therapy of one drug or combinations of 2 or more drugs over time.

Methods: We used the Information System for Research in Primary Care as our reference EHR platform for the smooth algorithm development. The algorithm was inspired by statistical methods based on moving averages and depends on a parameter Wt, a flexible window that determines the level of smoothing. The effect of Wt was evaluated in a simulation study on the same data set with different window lengths. To understand the algorithm performance in a clinical or pharmacological perspective, we conducted a validation study. We designed 4 pharmacological scenarios and asked 4 independent professionals to compare a traditional method against the smooth algorithm. Data from the simulation and validation studies were then analyzed.

Results: The Wt parameter had an impact over the raw data. As we increased the window length, more patient were modified and the number of smoothed patients augmented, although we rarely observed changes of more than 5% of the total data. In the validation study, significant differences were obtained in the performance of the smooth algorithm over the traditional method. These differences were consistent across pharmacological scenarios.

Conclusions: The smooth algorithm is an automated approach that standardizes, simplifies, and improves data processing in drug exposition studies using EHRs. This algorithm can be generalized to almost any pharmacological medication and model the drug exposure to facilitate the detection of treatment switches, discontinuations, and terminations throughout the study period.