Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Mar 26;9(3):e27767.
doi: 10.2196/27767.

Accuracy of an Artificial Intelligence System for Cancer Clinical Trial Eligibility Screening: Retrospective Pilot Study

Tufia Haddad  1 , Jane M Helgeson  1 , Katharine E Pomerleau  1 , Anita M Preininger  2 , M Christopher Roebuck  3 , Irene Dankwa-Mullan  2 , Gretchen Purcell Jackson  2   4 , Matthew P Goetz  1
Affiliations

Accuracy of an Artificial Intelligence System for Cancer Clinical Trial Eligibility Screening: Retrospective Pilot Study

Tufia Haddad et al. JMIR Med Inform. .

Abstract

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.

Keywords: artificial intelligence; breast cancer; clinical decision support system; clinical trial matching; clinical trials; eligibility; machine learning; screening.

PubMed Disclaimer

Conflict of interest statement

Conflicts of Interest: IDM, AMP, and GPJ are employed by IBM Watson. Mayo Clinic has a business collaboration with IBM Watson for Clinical Trial Matching. This activity is not undertaken to allow the company to indicate Mayo Clinic endorsement of a product or service. MPG declares funding acknowledgment to a named professorship (Erivan K Haub Family Professor of Cancer Research Honoring Richard F Emslander, MD) and consulting fees to institution from Eagle Pharmaceuticals, Lilly, Biovica, Novartis, Sermonix, Context Pharm, Pfizer, and Biotheranostics, and grant funding to institution from Pfizer, Sermonix, and Lilly. TCH declares grant funding to Mayo Clinic from Takeda Oncology. There are no conflicts of interest declared by JMH, KEP, and MCR.

References

    1. Trogdon JG, Chang Y, Shai S, Mucha PJ, Kuo T, Meyer AM, Stitzenberg KB. Care Coordination and Multispecialty Teams in the Care of Colorectal Cancer Patients. Medical Care. 2018 May 1;56(5):430–435. doi: 10.1097/MLR.0000000000000906. - DOI - PubMed
    1. Hussain T, Chang H, Veenstra CM, Pollack CE. Collaboration Between Surgeons and Medical Oncologists and Outcomes for Patients With Stage III Colon Cancer. J Oncol Pract. 2015 May;11(3):e388–e397. doi: 10.1200/JOP.2014.003293. http://europepmc.org/abstract/MED/25873063 - DOI - PMC - PubMed
    1. Vinciguerra V, Degnan TJ, Sciortino A, O'Connell M, Moore T, Brody R, Budman D, Eng M, Carlton D. A comparative assessment of home versus hospital comprehensive treatment for advanced cancer patients. J Clin Oncol. 1986 Oct;4(10):1521–8. doi: 10.1200/JCO.1986.4.10.1521. - DOI - PubMed
    1. Hess LM, Pohl G. Perspectives of quality care in cancer treatment: a review of the literature. Am Health Drug Benefits. 2013 Jul;6(6):321–9. http://europepmc.org/abstract/MED/24991367 - PMC - PubMed
    1. Clauser SB, Johnson MR, O'Brien DM, Beveridge JM, Fennell ML, Kaluzny AD. Improving clinical research and cancer care delivery in community settings: evaluating the NCI community cancer centers program. Implement Sci. 2009 Sep 26;4:63. doi: 10.1186/1748-5908-4-63. https://implementationscience.biomedcentral.com/articles/10.1186/1748-59... - DOI - DOI - PMC - PubMed

LinkOut - more resources