Abstract

BackgroundScreening patients for eligibility for clinical trials is labor intensive. It requires abstraction of data elements from multiple components of the longitudinal health record and matching them to inclusion and exclusion criteria for each trial. Artificial intelligence (AI) systems have been developed to improve the efficiency and accuracy of this process.ObjectiveThis study aims to evaluate the ability of an AI clinical decision support system (CDSS) to identify eligible patients for a set of clinical trials.MethodsThis study included the deidentified data from a cohort of patients with breast cancer seen at the medical oncology clinic of an academic medical center between May and July 2017 and assessed patient eligibility for 4 breast cancer clinical trials. CDSS eligibility screening performance was validated against manual screening. Accuracy, sensitivity, specificity, positive predictive value, and negative predictive value for eligibility determinations were calculated. Disagreements between manual screeners and the CDSS were examined to identify sources of discrepancies. Interrater reliability between manual reviewers was analyzed using Cohen (pairwise) and Fleiss (three-way) κ, and the significance of differences was determined by Wilcoxon signed-rank test.ResultsIn total, 318 patients with breast cancer were included. Interrater reliability for manual screening ranged from 0.60-0.77, indicating substantial agreement. The overall accuracy of breast cancer trial eligibility determinations by the CDSS was 87.6%. CDSS sensitivity was 81.1% and specificity was 89%.ConclusionsThe AI CDSS in this study demonstrated accuracy, sensitivity, and specificity of greater than 80% in determining the eligibility of patients for breast cancer clinical trials. CDSSs can accurately exclude ineligible patients for clinical trials and offer the potential to increase screening efficiency and accuracy. Additional research is needed to explore whether increased efficiency in screening and trial matching translates to improvements in trial enrollment, accruals, feasibility assessments, and cost.

Highlights

  • Patients with cancer treated in multispecialty clinical settings with access to clinical trials may experience better survival and quality of life [1,2,3,4,5]

  • We report the evaluation of a trial-centered matching approach by the clinical decision support system (CDSS) to identify eligible patients for each of 4 different clinical trials from a pool of patients with breast cancer treated at Mayo Clinic (Rochester, MN), a National Cancer Institute–designated comprehensive cancer center

  • We identified patient records suitable for inclusion in this retrospective pilot study from a population of patients with breast cancer treated in the medical oncology clinic at Mayo Clinic in Rochester, Minnesota, between May and June of 2017 with at least one unstructured health record note for processing by the CDSS

Read more

Summary

Introduction

Patients with cancer treated in multispecialty clinical settings with access to clinical trials may experience better survival and quality of life [1,2,3,4,5]. Identifying patients that fit complex protocol eligibility criteria is key to successful trial recruitment and enrollment [7]; most clinics are not optimally staffed for the time-intensive nature of manual patient screening. Screening patients for eligibility for clinical trials is labor intensive It requires abstraction of data elements from multiple components of the longitudinal health record and matching them to inclusion and exclusion criteria for each trial. The overall accuracy of breast cancer trial eligibility determinations by the CDSS was 87.6%. Conclusions: The AI CDSS in this study demonstrated accuracy, sensitivity, and specificity of greater than 80% in determining the eligibility of patients for breast cancer clinical trials. Additional research is needed to explore whether increased efficiency in screening and trial matching translates to improvements in trial enrollment, accruals, feasibility assessments, and cost

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call