Research
New research highlights that over 80% of clinical information remains unstructured, particularly in oncology, where critical trial-relevant data is often found in narrative formats. The study emphasizes the need for AI integration and shared standards to unlock this data and enhance eSource adoption in clinical trials.
New research finds that while eSource adoption is advancing through EHR-to-EDC workflows, scaling its impact will depend on integrating unstructured clinical data using AI, shared standards, and collaborative validation models across sites, sponsors, and vendors. Across healthcare systems, roughly 80% of clinical information remains unstructured, typically found in free-text notes, diagnostic reports, and imaging files.4-6 In data-intensive domains such as oncology, much of the trial-relevant information still resides exclusively in narrative form—within pathology narratives, radiology findings, and clinician observations that rarely appear in coded EHR fields. Unless these sources are captured and linked to structured datasets, eSource adoption risks plateauing at partial coverage. Unstructured data hold critical contextual detail that can clarify eligibility, disease stage, and treatment response. More than 80% of healthcare information remains unstructured, locked in free-text notes, pathology and radiology reports, or imaging files.4,5 In oncology and rare-disease trials, between 45-70% of trial-relevant variables exist only in unstructured formats.6 Unless these sources are incorporated, eSource adoption risks plateauing at partial coverage. This fragmentation limits reusability, slows trial start-up, and sustains reliance on manual abstraction—one of the largest hidden costs in clinical research. Unstructured data, comprising over 80% of healthcare information, is critical for comprehensive eSource adoption in clinical trials, especially in oncology and rare diseases. Recruitment remains one of the largest cost drivers in clinical research, and unstructured data can help identify patients meeting complex eligibility criteria not captured in structured fields. Chris Harrison explained, “Anything that can help satisfy qualification for patients on trial is really important. Eligibility is clearly one of the immediate priorities for us.” · By surfacing comorbidities, prior treatments, and disease status in clinical notes, investigators can broaden recruitment pools and reduce screening failures.
Original title: “Unlocking Unstructured Health Data: Scaling eSource-Enabled Clinical Trials | Applied Clinical Trials Online”