Introduction: Determining the optimal invasive strategy for patients with unstable angina remains challenging, often resulting in unnecessary coronary angiography. Existing risk scores, including the GRACE and TIMI scores, were not designed to predict obstructive coronary artery disease. This study evaluated the predictive performance of a risk factor–weighted clinical likelihood model. Methods: This retrospective analytical cohort study included 150 patients with low-to intermediate-risk unstable angina who underwent coronary angiography at a tertiary hospital. Predictive accuracy was assessed using receiver operating characteristic analysis and compared with the Diamond Forrester, Fladseth, guideline-based criteria, GRACE, and TIMI scores. Obstructive disease was defined as significant stenosis or physiologically relevant lesions. Results: The prevalence of obstructive coronary disease was 60%. The model demonstrated superior discrimination, with an area under the curve of 0.885, which exceeded that of the comparator models. At a threshold score, 42.7% of angiographies were safely deferred, with a negative predictive value of 76.6%. Calibration improved after model adjustment. Conclusion: The risk factor–weighted clinical likelihood model provides a robust prediction of obstructive coronary artery disease in patients with unstable angina. This may support objective decision-making and enable a more selective invasive strategy, thereby reducing unnecessary procedures while maintaining diagnostic safety.