An Introduction to Artificial Intelligence for Pharmacoepidemiologists

Course aim: The aim of this course is to provide guidance around the use of artificial intelligence (AI) in pharmacoepidemiology. Students will gain an insight into how to apply machine learning (ML), deep learning (DL), and generative AI/large language models (LLMs) in their research. The course will educate students on the strengths and weaknesses of different AI/ML approaches, as well as practical concepts, such as the types of data required and software tools commonly used. The content of the course is explicitly tailored to practical pharmacoepidemiology projects and will also include a deep dive into case studies.

Requisites: This is an entry level course. No previous experience of AI/ML is required. A basic understanding of epidemiology concepts will be beneficial for students but is not mandatory.

Course

Objectives:
1. To understand how and when AI/ML can be used for pharmacoepidemiology research
2. To provide a high-level overview of the steps in a project involving ML, including design considerations, data preparation, modelling, model validation, checking for bias, and interpretation of results
3. To review real-world examples of AI/ML in pharmacoepidemiology research and experiment hands-on with a neural network.

Syllabus outline:
● Introduction
● Session 1: The applications of AI in pharmacoepidemiology and when to use ML in pharmacoepidemiology
● Session 2: AI and ML from A to Z: a tour of algorithms and approaches
● Session 3: Steps in applying ML in pharmacoepidemiology: from data to deployment
● Session 4: Case studies and successful examples of AI/ML
● Session 5: Deep learning, GenAI and LLMs
● Interactive session: Putting it all into practice
● Q&A