Clinical trial eligibility automatic surveillance

Insufficient patient enrollment in clinical trials remains a serious and costly problem and is often considered the most critical issue to solve for the clinical trials community. One potential barrier to enrollment is the difficulty to correlate eligibility criteria with patient characteristics in a timely manner. Eligibility criteria specify the characteristics of study participants and provide a checklist for screening and recruiting participants. They are essential to every clinical research study. Computable representations of eligibility criteria can significantly accelerate electronic screening of clinical research study participants and improve research recruitment efficiency. The adoption of Electronic Health Record (EHR) systems is growing at a fast pace in the U.S. This growth results in very large quantities of patient clinical data becoming available in electronic format. Secondary use of clinical data is essential to fulfill the potentials for effective scientific research, high quality healthcare, and improved healthcare management. For clinical trial recruitment support, methods based on natural language processing (NLP) have the potential to automate the extraction of patients’ clinical characteristics from the EHR text notes, adding breadth and depth to the limited coded data available in typical EHRs (i.e., diagnostic and procedure codes).

Our hypothesis is that an automated process based on NLP can detect patients eligible for a specific clinical trial by linking the information extracted from the narrative description of clinical trial eligibility criteria to the corresponding clinical information extracted from an EHR and alerting clinicians caring for the patient. In this project, we focus on assessing the feasibility of automatically detecting a patient’s eligibility for a sample of breast cancer clinical trials by mapping coded clinical trial eligibility criteria to the corresponding clinical information extracted from the EHR.

Funding (so far):

Pilot research funding, Hollings Cancer Center’s Cancer Center Support Grant P30 CA138313 at the Medical University of South Carolina, and NIH/NCATS 5UL1TR001450-03.

Publications (so far):

  • AAlAbdulsalam, A. K., Garvin, J. H., Redd, A., Carter, M., Sweeney, C., & Meystre, S. M. (2018). Automated Extraction and Classification of AJCC TNM Stage Mentions from Unstructured Text Fields in a Central Cancer Registry. AMIA Joint Summits on Translational Science Proceedings, 16–25.
  • Carter, M., AAlAbdulsalam, A. K., Herget, K., McFadden, S., Garvin, J. H., Redd, A., et al. (2018). Automated extraction and assignment of TNM stage to support cancer case consolidation. Presented at the NAACCR annual conference, Pittsburgh, PA.
  • Heider, P., Kim, Y., AAlAbdulsalam, A. K., Kim, C., & Meystre, S. M. (2018). Hybrid Approaches for Automated Clinical Trial Cohort Selection. n2c2 Shared Task and Workshop, San Francisco, CA.