A1.3 Where next for Clinical Trials EHR eSource data transfer – and is AI the answer?

This presentation is part of a full breakout session. To add this presentation to your schedule you must add the full breakout session.

70% of data used for clinical trials is duplicated between Electronic Health Records (EHR) and Electronic Data Capture systems (EDC). The potential to save time and cost by replacing manual transcription with electronic data transfer is therefore huge.

This session features case study evidence of regulatory-grade electronic data transfer from EHR-to-Research System. In a collaboration between University College London Hospitals NHS Foundation Trust (UCLH), IgniteData and AstraZeneca, four patients from an AstraZeneca-sponsored phase 3 oncology study were enrolled into a live mirror study; data from the first 5 of their visits was electronically transferred from UCLH’s EHR to a copy of the study database. 100% of Vital Signs and Labs data were successfully mapped and transferred from EHR-to-EDC. Analysis showed that mapping 15% of forms meant that electronic data transfer could account for 50% of all required study data.

As significant strides in the re-use of structured data are being made, we also look at how unstructured data such as diagnoses, clinical procedures, medical imaging, free text notes and some concomitant medications can also be electronically accessed.

We preview a time soon when AI will be trained to recognise data elements and phrases, and to find and learn from variations; how an algorithm could transform multiple unstructured documents and text from the EHR into FHIR-compatible structured data to be passed straight into a study database

We assess the impact of this on the ease and speed of identifying and recruiting patients, getting trials up and running, and completing transfers of all the data elements needed to assess clinical trials.

We also look at the wider challenges beyond writing an algorithm that can make sense of unstructured data, such as accessing the right data in the first place, and ensuring that the data is handled correctly once it has been identified.