Abstract: Objective: We investigated the value of a nomogram model using non-contrast computed tomography (NCCT) and clinical quantitative parameters to predict hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). Methods: We retrospectively analyzed 125 patients with sICH who underwent NCCT at our hospital between October 2025 and February 2026. All NCCT images were automatically segmented and quantitative parameters were extracted using artificial intelligence software. Clinical variables were concurrently collected. Patients were randomly divided into training (n=87) and testing (n=38) sets with a 7:3 ratio. Feature selection was performed using SelectKBest, followed by variance inflation factor analysis and stepwise regression, to identify the best variables for constructing a logistic regression model. Model performance was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA), and a nomogram was developed. Results: Seven quantitative variables were used to construct a model. The model achieved respective accuracies of 88.51% and 89.47%, sensitivities of 82.76% and 84.62%, and areas under the ROC curve of 0.94 and 0.95 in the training and testing sets, indicating strong discriminative ability. Calibration curves demonstrated good agreement between predicted and observed probabilities, suggesting favorable model calibration. DCA showed that the model provided improved net clinical benefit across a wide range of threshold probabilities. The nomogram based on this model enabled individualized prediction of HE risk. Conclusions: The nomogram model integrating NCCT and clinical quantitative parameters can effectively predict HE risk in patients with sICH and adds significant value to early clinical risk assessment.