Parsimonious logistic model using age, PHI, and PHID predicts clinically significant prostate cancer in PI-RADS 3 lesions

A logistic regression model using age, prostate health index (PHI), and PHI density (PHID) predicted clinically significant prostate cancer in men with PI-RADS 3 lesions with an AUROC of 0.840 (95% CI: 0.754–0.916) on internal validation.

• The model numerically outperformed PSA and PSAD, but the incremental AUROC over PHI or PHID alone did not reach statistical significance.
• Exploratory risk stratification identified low-, intermediate-, and high-risk groups with CSPCa detection rates of 8.1%, 38.5%, and 83.3%, respectively.
• External validation is required before clinical implementation.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.