Multivariable Model for Prostate Cancer Prediction from PSMA PET/CT and mpMRI

A study of 1305 consecutive patients with suspected prostate cancer who underwent both mpMRI and 18F-PSMA PET/CT with biopsy at Peking University First Hospital. The dataset supports a model combining PRIMARY score, PI-RADS score, and PSAD to predict clinically significant prostate cancer, developed and validated by Chaojian Yu, last updated in 2026.

Use Cases

• Developing risk stratification models for prostate cancer based on combined imaging parameters.
• Comparing the predictive performance of PSMA PET/CT and mpMRI for clinically significant prostate cancer.
• Training machine learning models to optimize biopsy decisions using clinical and imaging predictors.

Strengths

• Model was developed and validated on a cohort of 1305 patients, providing a substantial sample size.
• The final model achieved an AUC of 0.916 in training and 0.837 in temporal validation, indicating strong predictive performance.
• Data is licensed under CC-BY-4.0, facilitating open reuse and sharing.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic bias inherent to a single hospital in China.

Provenance

Source

Peking University First Hospital

Collection Method

Retrospective study of consecutive patients undergoing mpMRI, 18F-PSMA PET/CT, and biopsy.

Freshness

Last updated 2026-05-18 05:43:06; freshness should be verified.

Geography

China