Nanostics Publishes Study Validating ClarityDX Prostate AI Models

In a press release, Nanostics announced the publication of a peer-reviewed study in npj Digital Medicine validating its ClarityDX Prostate models for predicting aggressive prostate cancer. The models use clinical and laboratory data to provide risk scores that help patients and physicians make biopsy decisions more accurately.

The study evaluated four versions of the ClarityDX Prostate model: the base model, versions incorporating digital rectal exam (DRE), magnetic resonance imaging (MRI), and both. All configurations achieved high accuracy, with area under the curve (AUC) scores ranging from 0.81 for the base model to 0.88 for the DRE plus MRI version. The models were developed and validated using data from six institutions across Canada, the United States, and Europe.

According to Nanostics, the models can reduce unnecessary biopsies by up to 47 percent while maintaining detection of more than 94 percent of aggressive cancers. The study also found that while MRI data improved performance, the model maintained strong accuracy even without MRI or DRE inputs, making these optional for clinical use.

The research was supported by the Alberta Cancer Foundation, Bird Dogs, NRC-IRAP, Alberta Innovates, Ride for Dad, and Prostate Cancer Canada.