As healthcare becomes increasingly data-driven, the ability to harness artificial intelligence (AI) and machine learning (ML) for improving health outcomes is more vital than ever. The Artificial Intelligence and Machine Learning for Health module offers a dynamic introduction to the powerful Python ecosystem for data science and equips students with the skills to build, evaluate, and critically assess sophisticated machine learning models tailored to real-world health challenges.
You will explore how to work with rich, multidimensional health data—including medical images, clinical text, and physiological signals—and apply cutting-edge machine learning techniques. From classical approaches like support vector machines and regression to advanced deep learning models such as convolutional neural networks and transformers, the module covers a wide spectrum of ML strategies.
Through hands-on coding sessions and interactive tutorials, you will gain practical experience not just in model development, but also in understanding key issues such as interpretability, bias, and clinical relevance. You will learn how to assess when and how AI systems can (and should) be applied in healthcare.
By the end of the module, you will have a solid foundation in both the theory and practical application of AI and ML in health data science. You will be equipped with the skills to critically evaluate research and confidently implement solutions across a range of public health scenarios.
The course is delivered over 12 weeks through engaging lectures, practical coding tutorials, and a guest speaker session that connects academic insight with real-world AI applications in healthcare. This module prepares you for future roles in health data science, combining technical expertise, research fluency, and communication skills.
Assessments for this module include an oral presentation, critiquing contemporary AI/ML research in public health (analysing methodology, findings, and limitations); and development of a complete ML pipeline using a real-world public health dataset (using both shallow and deep learning approaches), supported by a written report covering your methodology, results, and reflections.
With a focus on authentic, active learning, this module empowers you to confidently apply AI and ML in healthcare, making a meaningful impact on public health through data science.