In the evolving landscape of precision medicine, oncology clinical trial curation has become a cornerstone for connecting patients with life-saving research. Digital platforms like LookUpTrials are designed to assist clinicians in navigating complex trial landscapes. However, the manual effort required to keep these platforms updated often poses a sustainability challenge. A recent study published in JMIR Formative Research explores a "human-in-the-loop" model where supervised trainees maintain high-quality trial data. This approach ensures that the platform remains a reliable tool for point-of-care navigation.

The study evaluated a ten-month training program involving undergraduate students. These trainees processed information from ClinicalTrials.gov and various institutional portals. Surprisingly, even individuals without prior clinical trials experience successfully managed the workload. This was possible because the program utilized a structured onboarding process and peer support. Consequently, the team curated 2,503 trial entries across five academic medical centers. Furthermore, their processing rates increased over time, demonstrating the feasibility of the workflow.

Benefits of Oncology Clinical Trial Curation

Effective oncology clinical trial curation provides several advantages for both clinicians and researchers. Specifically, it transforms raw, unstructured data into actionable insights for site-specific trial matching. Additionally, human-in-the-loop systems mitigate the errors often found in fully automated AI summarization. Because humans oversee the final output, the data integrity remains high. Therefore, this model supports a scalable and durable content pipeline for digital health platforms. It also offers a blueprint for other institutions looking to implement similar data stewardship programs.

Frequently Asked Questions

What is "human-in-the-loop" data curation?

Human-in-the-loop curation is a workflow that combines the speed of artificial intelligence with the accuracy of human oversight. In this study, AI assisted with search and summarization, while human trainees verified and refined the trial data.

Can non-experts curate oncology trial data?

Yes. The study demonstrated that with structured training, standardized workflows, and quality assurance protocols, individuals without prior clinical experience can effectively curate complex trial information.

How does this program help oncology patients?

By ensuring that trial databases are up-to-date and accurate, the program helps oncologists identify the best possible clinical trials for their patients during consultations, potentially improving access to novel treatments.

Disclaimer: This content is for informational and educational purposes only and does not constitute medical advice or a professional recommendation. Healthcare professionals should exercise their clinical judgment and verify information with primary research sources. Refer to the latest local and national guidelines for clinical practice.

References

Issa M et al. Development and Evaluation of a Human-in-the-Loop Data Curation Training Program to Support a Digital Clinical Trial Platform: Descriptive Feasibility Study. JMIR Form Res. 2026 Mar 25. doi: 10.2196/81257. PMID: 41880602.

Haggstrom DA et al. The My Cancer Genome clinical trial data model and trial curation workflow. J Am Med Inform Assoc. 2020 Jun 1;27(6):893-901. doi: 10.1093/jamia/ocaa033.

Leister S. Advanced Training for CRCs. CITI Program. 2025.