Artificial intelligence in internal medicine: A Comprehensive review

Abstract

Artificial intelligence (AI) is reshaping the practice of internal medicine by enhancing diagnostic precision, optimizing clinical workflows, and supporting individualized patient care. As digital health technologies mature, AI is increasingly integrated across multiple medical domains, offering new opportunities and challenges for clinicians. This comprehensive review aims to provide an updated overview of the current and emerging applications of AI in internal medicine, highlighting its contributions across major subspecialties such as cardiology, endocrinology, nephrology, gastroenterology, hematology, and oncology. Recent literature demonstrates that AI algorithms, particularly those based on machine learning and deep learning, have achieved notable success in tasks such as medical imaging interpretation, pattern recognition in laboratory and clinical data, and prediction of disease outcomes. In cardiology, AI enhances ECG and echocardiographic analysis; in endocrinology and nephrology, it aids in early detection of diabetic and renal complications; and in oncology and hematology, it supports diagnostic pathology and prognostication. Despite this progress, translation into daily clinical practice remains limited due to challenges related to data quality, model interpretability, generalizability, data safety concerns and ethical considerations. In conclusion, AI holds significant promise to advance internal medicine by augmenting clinical decision making and promoting precision medicine. Real-world integration will require interdisciplinary collaboration, transparent model validation, and regulatory guidance to ensure reliability, safety, and equity. Continued clinical engagement and responsible implementation are essential for transforming AI’s technical potential into perceptible benefits for patient care.