Fig. 6: Precision–recall curve for DL-binary predictions on the validation set. | npj Digital Medicine

Fig. 6: Precision–recall curve for DL-binary predictions on the validation set.

From: Deep learning based phenotyping of medical images improves power for gene discovery of complex disease

Fig. 6

Precision–recall curve for the ResNet-101 binary classifier. The curve illustrates the trade-off between precision and recall at varying classification thresholds. The classifier achieved an area under the precision-recall curve (AUPRC) of 0.96, highlighting its ability to effectively separate OA cases from controls.

Back to article page