Course

Unit 1:
Introduction to Artificial Intelligence in Medicine, Definition and scope of AI in healthcare, Historical perspective and milestones in AI research, Applications of AI in clinical practice and biomedical research
Unit 2:
Fundamentals of Machine Learning, Supervised, unsupervised, and reinforcement learning, Feature engineering and model evaluation, Bias-variance tradeoff and model interpretability
Unit 3:
Deep Learning Architectures, Neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs), Deep learning frameworks (e.g., TensorFlow, PyTorch), Transfer learning and pre-trained models
Unit 4:
AI in Medical Imaging, Image classification, segmentation, and registration, Radiomics and quantitative imaging biomarkers, Applications of AI in radiology, pathology, and ophthalmology
Unit 5:
AI in Diagnostics and Disease Prediction, Predictive modeling for disease risk assessment, Diagnostic decision support systems, Early detection of diseases using AI algorithms
Unit 6:
Natural Language Processing (NLP) in Healthcare, Text mining and information extraction from clinical notes, Clinical language understanding and medical coding, Applications of NLP in electronic health records (EHR) analysis and clinical documentation
Unit 7:
AI in Personalized Medicine and Treatment Planning, Pharmacogenomics and precision medicine, Treatment recommendation systems, Drug discovery and repurposing using AI approaches
Unit 8:
Ethical, Legal, and Social Implications (ELSI) of AI in Medicine, Bias and fairness in AI algorithms, Privacy and security of healthcare data, Regulation and policy considerations for AI in healthcare

Preamble
Artificial Intelligence (AI) in Medicine is a graduate-level course designed to provide students with an advanced understanding of how AI and machine learning techniques are transforming healthcare delivery, clinical decision-making, and biomedical research. The course will cover topics such as machine learning algorithms, deep learning architectures, natural language processing, and computer vision, with a focus on their applications in medical imaging, diagnostics, patient management, and personalized medicine. Through lectures, case studies, hands-on exercises, and guest speakers, students will explore the opportunities and challenges of integrating AI into healthcare systems.

Course outcome

CO1: To understand the fundamentals of artificial intelligence and machine learning and their applications in medicine.
CO2: To explore advanced AI techniques, including deep learning, reinforcement learning, and natural language processing.
CO3: To learn about the use of AI in medical imaging, diagnostics, disease prediction, and treatment planning.
CO4: To examine the ethical, legal, and social implications of AI in medicine, including issues of bias, privacy, and equity.
CO5: To gain hands-on experience with AI tools and platforms through practical exercises and projects.
CO6: To critically evaluate research studies and applications of AI in healthcare.

Program outcome (PO)

PO1: Utilize scientific principles and methodologies to design innovative solutions for data analysis, experimentation, and product development for challenges in translational research.
PO2: Recognize the importance of environmental sustainability in translational research and strive to minimize adverse environmental impacts.
PO3: Engage in ethical conduct, leadership, active listening, constructive feedback, and interpersonal communication to facilitate productive collaborations and knowledge exchange.
PO4: Acquire fundamental and advanced knowledge and skills in project management, financial planning, and entrepreneurship relevant to translational research ventures and initiatives.
3 = High Affinity, 2 = Medium Affinity, 1 = Low Affinity, – = No Affinity

Program Specific Outcome (PSO)

PSO1: Addresses the complexity of interdisciplinary sciences in biological and medical contexts.
PSO2: Deals with regulatory affairs in medicine, covering topics such as ethical considerations and regulatory frameworks.
PSO3: Covers compounds as drugs and their efficacy, involving pharmacology and drug development.
PSO4: Explores the intersection of bioinformatics and artificial intelligence in biology and medicine.
PSO5: Deals with technology in personalizing medicine, involving precision medicine approaches.
PSO6: Focuses on communicating and disseminating science and medicine to the public, involving science communication and public outreach efforts.

Mesko, B., 2017. A guide to artificial intelligence in healthcare. Budapest, Hungary: The Medical Futurist. leanpub. com.