The electrocardiogram (ECG) is a fundamental tool in cardiovascular evaluation, widely used in clinical settings due to its accessibility, low cost, and ease of application. Recent advances in artificial intelligence (AI) have expanded the potential applications, enabling the estimation of demographic characteristics such as age and sex from ECG signals. This study aims to develop and validate an AI model capable of estimating age and sex from ECG records in a local population, evaluating its performance compared to previous studies and analyzing its potential impact on clinical applications. A convolutional neural network (CNN) was trained using a dataset of 275,000 anonymized ECGs. The model achieved an 87% accuracy in sex classification and an average absolute error of 9 years for age estimation. These results suggest that the predicted age may serve as a biomarker for biological aging and cardiovascular risk. The integration of this AI tool into clinical practice could lead to more efficient patient stratification and optimize healthcare resource allocation.