Artificial Intelligence in Biomedicine: A Systematic Review from Nanomedicine to Neurology and Hepatology

<b>Background/Objectives:</b> This review evaluates the expanding contributions of artificial intelligence (AI) across biomedicine, focusing on cancer therapy and nanomedicine, cardiology and medical imaging, neurodegenerative disorders, and liver disease. Core AI concepts (machine learning, deep learning, artificial neural networks, model training/validation, and explainability) are introduced to frame application domains. <b>Methods:</b> A systematic search of major biomedical databases (2010-2025) identified English-language original studies on AI in these four areas; 203 articles meeting PRISMA 2020 criteria were included in a qualitative synthesis. <b>Results:</b> In oncology and nanomedicine, AI-driven methods expedite nanocarrier design, predict biodistribution and treatment response, and enable nanoparticle-enhanced monitoring. In cardiology, algorithms enhance ECG interpretation, coronary calcium scoring, automated image segmentation, and noninvasive FFR estimation. For neurological disease, multimodal AI models integrate imaging and biomarker data to improve early detection and patient stratification. In hepatology, AI supports digital histopathology, augments intraoperative robotics, and refines transplant wait-list prioritization. Common obstacles are highlighted, including data heterogeneity, lack of standardized acquisition protocols, model transparency, and the scarcity of prospective multicenter validation. <b>Conclusions:</b> AI is emerging as a practical enabler across these biomedical fields, but its safe and equitable use requires harmonized data, rigorous multicentre validation, and more transparent models to ensure clinical benefit while minimizing bias.