果冻影院

This module will provide you with an introduction to the principles of machine learning in healthcare and biomedicine, covering the key concepts involved in designing and evaluating approaches to machine learning. The module will focus on applied methods for problems in prevention, diagnosis, therapy, aetiology, and prognosis. You will be given a practical introduction to common approaches, offering you experience in using different machine learning algorithms and concepts (including decision trees, logistic regression, support vector machines, artificial neural nets, ensembles and deep learning) in the context of healthcare.

At the end of this module you will be able to:

1) Outline the definition of machine learning and its essential terminology; identify potential areas of its application in healthcare; describe the evaluation of classification models.

2) Describe hyperparameter tuning and evaluation of a machine learning model.

3) Present the foundational concepts of probabilistic learning such as Bayes鈥� theorem.

4) Explain the principles of decision tree learning and apply it to health data.

5) Articulate the underlying concepts of deep neural networks and apply them to a multidimensional feature space of health data.

6) Describe the importance and key concepts of data pre-processing and dimensionality reduction and apply them to a feature space of health data.

7) Define the theoretical principles of support vector machines and apply these methods to health data.

8) Contrast different classifiers and construct an ensemble classifier for decision making.

9) Get informed on the latest developments AI in medicine (e.g., clinical natural language processing, generative AI for biomedicine and deep learning for medical imaging).

10) Understand the caveats of applying machine learning in health including bias and inequalities embedded in the data and/or induced by AI models

The module is delivered through web-based distance learning in the 果冻影院 Virtual Learning Environment plus a 3-day face-to-face teaching session.

• Rajpurkar, Pranav, et al. 鈥淎I in health and medicine.鈥� Nature Medicine 28.1 (2022): 31-38.听
• Ghahramani, Z., 2015. Probabilistic machine learning and artificial intelligence. Nature, 521(7553), pp.452-459.听
• Wiens, J., & Shenoy, E. S. (2018). Machine learning for healthcare: on the verge of a major shift in healthcare epidemiology. Clinical Infectious Diseases, 66(1), 149-153.听
• Thirunavukarasu, Arun James, et al. "Large language models in medicine."听Nature medicine听29.8 (2023): 1930-1940.
• Chen, I. Y., Pierson, E., Rose, S., Joshi, S., Ferryman, K., & Ghassemi, M. (2021). Ethical machine learning in healthcare. Annual review of biomedical data science, 4, 123-144.听
• Vollmer, Sebastian, et al. 鈥淢achine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness.鈥� bmj 368 (2020).听