Artificial intelligence is moving from experimental models into tools that support diagnosis, image interpretation, risk assessment, and clinical monitoring. Its value in medicine depends not only on predictive performance, but also on reliability, interpretability, appropriate validation, and the ability to complement professional judgment across different specialties and care settings.

This theme issue brings together recent Medical Research Archives articles examining that clinical transition. The collection considers interpretable heart-disease risk prediction, deep-learning applications in pulmonary and coronary imaging, automated cellular segmentation, artificial intelligence in thalassemia diagnosis and monitoring, and intelligent hearing technology. Together, the articles show how computational methods can contribute to practical clinical decisions while keeping accuracy, transparency, and patient needs at the center of implementation.