Skip to main content
. 2021 Feb 4;28(6):1259–1264. doi: 10.1093/jamia/ocaa341

Table 4.

Model evaluation results—ProstateX challenge dataset

ProstateX (n =343)

Private

models

NCI 0.872 ± 0.062*
SUNY 0.838 ± 0.043*
UCLA 0.812 ± 0.136*
FL Model 0.889 ±0.036
*

Significantly lower than FL model (P < .001).