Objective <p>The aim of this study was to meta-analyze published data on the diagnostic performance of PSMA PET/CT in detecting lymph node invasion (LNI) in intermediate-risk prostate cancer (PCa) patients, and to discuss whether pelvic lymph node dissection (PLND) can be spared in patients with negative PSMA PET scan.</p> Patients and methods <p>The PubMed and Embase databases were searched through November 2025 to identify relevant articles. Methodological quality of each study was assessed. Patient-based sensitivity and specificity were pooled using the bivariate random-effects model. Patient-based negative predictive value (NPV) was pooled using the DerSimonian-Laird model. Histopathology from PLND and clinical follow-up served as the reference standard.</p> Results <p>Twelve eligible studies, comprising a total of 1619 patients with intermediate-risk PCa, were included. Overall, the studies were of moderate methodological quality. The sensitivity and specificity of PSMA PET/CT for the detection of LNI ranged from 0% to 100% and from 87% to 99%, respectively, with pooled estimates of 49% [95% confidence interval (CI) 27–72%] and 95% (95% CI 93–97%), respectively. The NPV of PSMA PET/CT for the detection of LNI ranged from 74% to 100%, with pooled estimates of 95% (95% CI 91–98%).</p> Conclusion <p>This meta-analysis of current diagnostic evidence suggests that intermediate-risk PCa patients with negative PSMA PET scan may omit PLND at the time of radical prostatectomy. However, the moderate sensitivity of PSMA PET and the associated risk of missing micrometastatic disease underscore the need for cautious application and shared decision-making. Further large-scale prospective validation studies and future follow-up results focusing on the clinical outcomes of these patients will lend stronger support to this approach.</p>