TY - JOUR
T1 - Accuracy of an artificial intelligence system for cancer clinical trial eligibility screening
T2 - Retrospective pilot study
AU - Haddad, Tufia
AU - Helgeson, Jane M.
AU - Pomerleau, Katharine E.
AU - Preininger, Anita M.
AU - Roebuck, M. Christopher
AU - Dankwa-Mullan, Irene
AU - Jackson, Gretchen Purcell
AU - Goetz, Matthew P.
N1 - Publisher Copyright:
©Tufia Haddad, Jane M Helgeson, Katharine E Pomerleau, Anita M Preininger, M Christopher Roebuck, Irene Dankwa-Mullan, Gretchen Purcell Jackson, Matthew P Goetz.
PY - 2021/3
Y1 - 2021/3
N2 - Background: 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. Artificial intelligence (AI) systems have been developed to improve the efficiency and accuracy of this process. Objective: This study aims to evaluate the ability of an AI clinical decision support system (CDSS) to identify eligible patients for a set of clinical trials. Methods: This 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. Results: In 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%. 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. 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.
AB - Background: 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. Artificial intelligence (AI) systems have been developed to improve the efficiency and accuracy of this process. Objective: This study aims to evaluate the ability of an AI clinical decision support system (CDSS) to identify eligible patients for a set of clinical trials. Methods: This 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. Results: In 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%. 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. 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.
KW - Artificial intelligence
KW - Breast cancer
KW - Clinical decision support system
KW - Clinical trial matching
KW - Clinical trials
KW - Eligibility
KW - Machine learning
KW - Screening
UR - http://www.scopus.com/inward/record.url?scp=85105051261&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85105051261&partnerID=8YFLogxK
U2 - 10.2196/27767
DO - 10.2196/27767
M3 - Article
AN - SCOPUS:85105051261
SN - 2291-9694
VL - 9
JO - JMIR Medical Informatics
JF - JMIR Medical Informatics
IS - 3
M1 - e27767
ER -