Automatic Population of the Case Report Forms for an International Multifactorial Adaptive Platform Trial Amid the COVID-19 Pandemic

Abstract

Objectives: To automatically populate the case report forms (CRFs) for an international, pragmatic, multifactorial, response-adaptive, Bayesian COVID-19 platform trial.

Methods: The locations of focus included 27 hospitals and 2 large electronic health record (EHR) instances (1 Cerner Millennium and 1 Epic) that are part of the same health system in the United States. This paper describes our efforts to use EHR data to automatically populate four of the trial's forms: baseline, daily, discharge, and response-adaptive randomization.

Results: Between April 2020 and May 2022, 417 patients from the UPMC health system were enrolled in the trial. A MySQL-based extract, transform, and load pipeline automatically populated 499 of 526 CRF variables. The populated forms were statistically and manually reviewed and then reported to the trial's international data coordinating center.

Conclusions: We accomplished automatic population of CRFs in a large platform trial and made recommendations for improving this process for future trials.

Figure 1.

Trial data reporting requirements were categorized broadly as structured and unstructured data. Unstructured data elements were captured with electronic forms integrated into either research coordinator or clinician workflows. Structured data were collected from the EHRs relational databases. AE, adverse event; SAE, serious adverse event.

Figure 2.

Information flow for automatic population of a clinical trial’s case report forms: part 1. This figure shows how source tables containing raw EHR data and manually curated support tables are combined to create a series of curated tables that harmonize and standardize participant data. These tables are then combined to create a series of derived tables. Note, temporary tables, such as those needed to support temporal joins of different rows of the same table, are not shown.

Figure 3.

Information flow for automatic population of a clinical trial’s case report forms: part 2. This figure shows how support tables, curated tables, and derived tables are joined to populate the four tables corresponding to the CRFs for baseline characteristics, daily outcomes, discharge outcomes, and response-adaptive randomization characteristics and outcomes.