Non-invasive methods used for PH detection in clinical practice have several limitations. The combination of high spatiotemporal sensitivity magnetocardiography (MCG) and artificial intelligence algorithms may offer an accurate approach for PH detection. In this study, we develop a convolutional neural network (CNN) model based on the 64-channel MCG time-series data. This exploratory study enrolled patients undergoing 64-channel MCG, including right-heart-catheterization confirmed PH patients and symptomatic controls with low echocardiographic probability of PH. After data preprocessing, a temporal CNN integrating MCG signals with age, sex, and body mass index was developed and compared with conventional machine learning models. The CNN model achieved strong discrimination, with area under the curve (AUC) values of 0.939 (95% confidence interval [CI]: 0.913–0.961) in the development out-of-fold evaluation and 0.974 (95% CI: 0.944–0.994) in the hold-out test set, outperforming conventional machine learning models. Decision curve analysis showed the greatest net benefit at clinically relevant thresholds. Attribution analysis indicated that spatial QRS morphology redistribution contributed substantially to PH classification. The temporal CNN model based on raw 64-channel MCG signals showed promising performance for non-invasive PH detection and outperformed conventional machine learning approaches in this exploratory single-center cohort enriched for PAH and CTEPH.