PSMA-negative but FDG-positive (PSMA-/FDG+) lesion in dual-tracer ( Ga-PSMA and F-FDG) positron emission tomography/computed tomography (PET/CT) is associated with an unfavorable response to Lutetium-177 ( Lu)-PSMA-617. This study sought to develop both radiomics and clinical models for the precise prediction of the presence of PSMA-/FDG+ lesions in patients with castration-resistant prostate cancer (CPRC). A cohort of 298 patients who underwent dual-tracer PET/CT with a less than 5-day interval was included. The evaluation of the prognostic performance of the radiomics model drew upon the survival data derived from 40 patients with CRPC treated with Lu-PSMA-617 in an external cohort. Two endpoints were evaluated: (a) prostate-specific antigen (PSA) response rate, defined as a reduction exceeding 50% from baseline and (b) overall survival (OS), measured from the initiation of Lu-PSMA-617 to death from any cause. PSMA-/FDG+ lesions were identified in 56 (18.8%) CRPC patients. Both radiomics (area under the curve AUC, 0.83) and clinical models (AUC, 0.78) demonstrated robust performance in PSMA-/FDG+ lesion prediction. Decision curve analysis revealed that the radiomics model yielded a net benefit over the 'screen all' strategy at a threshold probability of ⩾4%. At a 5% probability threshold, the radiomics model facilitated a 21% reduction in F-FDG PET/CT scans while only missing 2% of PSMA-/FDG+ cases. Patients with a low estimated score exhibited significantly prolonged OS (hazard ratio = 0.49,  = 0.029) and a higher PSA response rate (75% 35%,  = 0.011) compared to those with a high estimated score. This study successfully developed two models with accurate estimations of the risk associated with PSMA-/FDG+ lesions in CRPC patients. These models held potential utility in aiding the selection of candidates for Lu-PSMA-617 treatment and guiding Ga-PSMA PET/CT-directed radiotherapy.