Artificial Intelligence in Healthcare

Catalog description

This advanced course provides an in-depth exploration of the principles and methodologies of artificial intelligence (AI) and machine learning (ML) in healthcare. Topics include exploratory data analysis (EDA), electronic health record (EHR)-mining, machine learning algorithms, and natural language processing (NLP) techniques such as bag of words (BOW), part-of-speech (POS) tagging, and large language models (LLM). The course also covers advanced topics such as transfer learning (TL) and federated machine learning (FL), explainable AI (XAI), with a focus on their applications in healthcare systems. Students will engage with the AI lifecycle in healthcare, including EHR-based phenotype definition, data processing, model development, validation, and implementation, and monitoring. Ethical, legal, and privacy considerations, along with issues of diversity and inclusion, will be addressed, especially as they relate to the context of precision medicine and personalized care. Case studies and guest lectures will explore real-world applications and state-of-the-art solutions. Through research projects, presentations, and critical discussions, students will develop the skills to lead innovative AI research in healthcare. This course is designed to prepare students for advanced research roles in academia, industry, and healthcare policy. Grading will be based on tests, student presentations, and project milestones.