Search Articles

View query in Help articles search

Search Results (1 to 1 of 1 Results)

Download search results: CSV END BibTex RIS


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

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

No statistically significant differences in assignment were detected (P=.16). Group 1, with attributes verified by humans as described in the Methods section, included 117 breast cancer cases. The CDSS accuracy of trial eligibility determinations for Group 1 (included/excluded) was 90.6% overall. Sensitivity (true positive rate) was 82.1%, and specificity (true negative rate) was 93.3%.

Tufia C Haddad, Jane M Helgeson, Katharine E Pomerleau, Anita M Preininger, M Christopher Roebuck, Irene Dankwa-Mullan, Gretchen Purcell Jackson, Matthew P Goetz

JMIR Med Inform 2021;9(3):e27767