Integrating 68Ga-PSMA-11 PET/CT with Clinical Risk Factors for Enhanced Prostate Cancer Progression Prediction

TL;DR

This study shows that combining PSMA PET imaging with clinical data improves prostate cancer progression prediction using machine learning.

Contribution

A novel probabilistic graphical model integrating PSMA PET biomarkers and clinical factors outperforms existing risk scores for prostate cancer progression prediction.

Findings

The probabilistic graphical model achieved 73% balanced accuracy in predicting prostate cancer progression.

PSMA SUVmax and CAPRA score were key predictors in the model.

The model outperformed both logistic regression and CAPRA score in predictive performance.

Abstract

In this study, we explored the use of machine learning (ML) to improve the prediction of early prostate cancer (PCa) progression by combining 68Ga-PSMA-11 PET/CT imaging biomarkers with clinical risk factors from 93 high-risk PCa patients. The CAPRA score served as a comparator. We developed a probabilistic graphical model (PGM) and a logistic regression (LR) model. Key predictors used in both models included the CAPRA-based score and SUVmax, followed by bone metastases, seminal vesicle infiltration, and nodal involvement at common iliac bifurcation. The PGM outperformed both the CAPRA score and the LR model, achieving a balanced accuracy of 0.73. Our findings demonstrate that an ML-derived PGM integrating 68Ga-PSMA-11 PET/CT imaging with clinical data significantly enhances early PCa progression prediction.

Background/Objectives: This study evaluates whether combining 68Ga-PSMA-11-PET/CT derived imaging biomarkers with clinical risk factors improves the prediction of early biochemical recurrence (eBCR) or clinical progress in patients with high-risk prostate cancer (PCa) after primary treatment, using machine learning (ML) models. Methods: We analyzed data from 93 high-risk PCa patients who underwent 68Ga-PSMA-11 PET/CT and received primary treatment at a single center. Two predictive models were developed: a logistic regression (LR) model and an ML derived probabilistic graphical model (PGM) based on a naïve Bayes framework. Both models were compared against each other and against the CAPRA risk score. The models’ input variables were selected based on statistical analysis and domain expertise including a literature review and expert input. A decision tree was derived from the PGM to translate its probabilistic reasoning into a transparent classifier. Results: The five key input variables were as follows: binarized CAPRA score, maximal intraprostatic PSMA uptake intensity (SUVmax), presence of bone metastases, nodal involvement at common iliac bifurcation, and seminal vesicle infiltration. The PGM achieved superior predictive performance with a balanced accuracy of 0.73, sensitivity of 0.60, and specificity of 0.86, substantially outperforming both the LR (balanced accuracy: 0.50, sensitivity: 0.00, specificity: 1.00) and CAPRA (balanced accuracy: 0.59, sensitivity: 0.20, specificity: 0.99). The decision tree provided an explainable classifier with CAPRA as a primary branch node, followed by SUVmax and specific PET-detected tumor sites. Conclusions: Integrating 68Ga-PSMA-11 imaging biomarkers with clinical parameters, such as CAPRA, significantly improves models to predict progression in patients with high-risk PCa undergoing primary treatment. The PGM offers superior balanced accuracy and enables risk stratification that may guide personalized treatment decisions.

Figures