Objective: A substantial part of non-traumatic intracerebral haemorrhages (ICH) arises from a macrovascular cause, but there is little guidance on selection of patients for additional diagnostic work-up. We aimed to develop and externally validate a model for predicting the probability of a macrovascular cause in patients with non-traumatic ICH. Methods: The DIagnostic AngioGRAphy to find vascular Malformations (DIAGRAM) study (n=298; 69 macrovascular cause; 23%) is a prospective, multicentre study assessing yield and accuracy of CT angiography (CTA), MRI/magnetic resonance angiography (MRA) and intra-arterial catheter angiography in diagnosing macrovascular causes in patients with non-traumatic ICH. We considered prespecified patient and ICH characteristics in multivariable logistic regression analyses as predictors for a macrovascular cause. We combined independent predictors in a model, which we validated in an external cohort of 173 patients with ICH (78 macrovascular cause, 45%). Results: Independent predictors were younger age, lobar or posterior fossa (vs deep) location of ICH, and absence of small vessel disease (SVD). A model that combined these predictors showed good performance in the development data (c-statistic 0.83; 95% C I 0.78 to 0.88) and moderate performance in external validation (c-statistic 0.66; 95% CI 0.58 to 0.74). When CTA results were added, the c-statistic was excellent (0.91; 95% CI 0.88 to 0.94) and good after external validation (0.88; 95% CI 0.83 to 0.94). Predicted probabilities varied from 1% in patients aged 51-70 years with deep ICH and SVD, to more than 50% in patients aged 18-50 years with lobar or posterior fossa ICH without SVD. Conclusion: The DIAGRAM scores help to predict the probability of a macrovascular cause in patients with nontraumatic ICH based on age, ICH location, SVD and CTA.