Certificado de Postgrado en Inteligencia Artificial en Salud

Module 1. The Background

• The fourth industrial revolution
• A brief history of the interaction between medicine and artificial intelligence
• What can we use AI algorithms for in the clinical setting?
• Learning systems: A mapping of the AI environment
• Health data: sources and characteristics
• Data Protection: GDPR
• Research and clinical trials
• Ethical implications
• 5Ps Medicine
• Value-based decision
• European/national/regional strategy
• Expected impact of AI in the coming years
• Resource management success cases
• Health care success cases
• Exam

Module 2. The technique

• Rule-based expert systems. The predecessors of AI
• Machine Learning: regression, classification and clustering models
• Neural networks and deep learning
• The learning paradigm. Feature selection and model optimisation
• What is Python? Introduction. Python and data science. Installation and working environment
• Getting started in Python (Theory) Data types, variables, operators, loops and other structures
• Getting started in Python (Practical) Data types, variables, operators, loops and other structures
• Object orientation: classes and instances, attributes and methods. Working with libraries
• Fundamental Python libraries for working with data: Numpy and Pandas
• Introduction to AI in Python. Libraries and levels of abstraction
• Data analysis in Python: Spicy, Matplotlib, Seaborn, statsmodels
• Data structuring: data sets for training, validation and testing. Data augmentation
• Machine Learning in Python: Scikit-learn and practical examples
• Neural Networks in Python: Pytorch, Tensorflow and Keras
• Exam

Module 3. Applications of AI in healthcare

• Types of data in health
• Hospital Information Systems (HIS) and Electronic Health Records (EHR)
• Image Management Systems (PACS and DICOM)
• Data interoperability in healthcare. The FHIR standard
• Text mining and Natural Language Processing (NLP)
• Medical image analysis. U-Nets and GANs
• Robotic Process Automation
• Artificial Intelligence and Cloud Computing
• Decision Support Systems: Diagnosis and Treatment
• AI in Drug Discovery and personalised treatments
• Management improvements
• Patient interaction and telemedicine
• Exam

Module 4. Implementation of AI projects in Healthcare

• Framework evaluation Outcome-Action-Pair (OAP)
• Life cycle of an AI project
• Design and development
• Validation
• Monitoring and maintenance
• Relevant actors IA Health
• Bias, interpretability and fairness
• Privacy and security
• Regulatory environment
• Implementing an AI strategy
• Corporate intrapreneurship and cultural change
• Project management
• Public and private financing tools for innovative projects
• Exam

Major Project

Comprehensive capstone project where students apply all learned concepts to develop a complete AI solution for a healthcare challenge.