no code implementations • 25 Oct 2021 • Weiyao Wang, Aniruddha Tamhane, Christine Santos, John R. Rzasa, James H. Clark, Therese L. Canares, Mathias Unberath
Our method achieves an AUROC of 88. 0% on the patient-level and also outperforms the average of a group of 25 clinicians in a comparative study, which is the largest of such published to date.