Abstract Background Despite the effectiveness of the retrograde approach for chronic total occlusion (CTO) lesions, there are no standardized tools to predict the success of retrograde percutaneous coronary intervention (PCI). Purpose The objective of this study was to develop a prediction tool to identify CTO lesions that will achieve successful retrograde PCI. Methods This study evaluated data from 2,374 patients who underwent primary retrograde CTO-PCI and were enrolled in the Japanese CTO-PCI Expert Registry between January 2016 and December 2022. All observations were randomly assigned to the derivation and validation cohorts at a 2:1 ratio. The prediction score for guidewire failure in retrograde CTO-PCI was determined by assigning one point for each factor and summing all accrued points. Results The JR-CTO score (moderate–severe calcification, tortuosity, Werner collateral connection grade ≤ 1, and non-septal collateral channel) demonstrated a c statistic for guidewire failure of 0.72 (95% confidence interval: 0.67–0.76) and 0.71 (95% confidence interval: 0.64–0.77) in the derivation and validation cohorts, respectively. Patients with lower scores had higher guidewire and technical success rates and decreased guidewire crossing time and procedural time (P < 0.01). Conclusions The JR-CTO score, a simple four-item score that predicts successful guidewire crossing in patients undergoing retrograde CTO-PCI, has the potential to support clinical decision-making for the retrograde approach.