AI in healthcare applies artificial intelligence, including machine learning, deep learning, and generative AI, to clinical, administrative, and research workflows. These systems ingest patient data, electronic health records, medical imaging, and clinical documentation to support diagnosis, treatment planning, and operational efficiency. The guide targets healthcare professionals, health IT leaders, and clinical informatics teams evaluating AI solutions, focusing on clinical use cases, data practices, and regulatory obligations. AI integration in healthcare began in the 1970s with early rule-based expert systems for narrow diagnostic tasks, aiming to use data patterns to support, not replace, clinical judgment. AI models are trained artifacts mapping inputs like patient data to outputs such as risk scores, while AI algorithms are the mathematical procedures used for training. Generative AI produces new content like clinical documentation drafts. Organizations deploy multiple model types, including supervised classification for diagnostic support, time-series models for patient monitoring, natural language processing for clinical documentation, and computer vision for medical imaging. Mature applications cluster around four categories: diagnostic support, administrative automation, drug discovery, and patient monitoring.