Robust and interpretable machine learning for biomedicine and healthcare

Lead Research Organisation: University of Oxford
Department Name: Autonom Intelligent Machines & Syst CDT


Context & Potential Impact: Deep learning methods excel at spotting patterns in large datasets. The increasing availability of medical datasets has thus led to many reports of deep learning models performing on par with human physicians in prediction and diagnosis tasks. In my DPhil research, I will develop and apply machine learning models in the context of biomedicine and healthcare, with a particular focus on two topics: interpretability and robustness.

Interpretability: Deep learning models are notoriously opaque: Even if they give highly accurate predictions, it's not easy to figure out how they do so. There would be two major advantages in improving our ability to interpret, explain, and understand neural networks. First, black-box algorithms are unlikely to inspire the required trust in medical decisionmakers and thus unlikely to find their way into clinical practice. Second, the ability to interpret deep neural networks could help us to capitalise on the implicit knowledge captured in these trained models, potentially elucidating the mechanisms that play a role in disease development and progression.

Robustness: Robustness to dataset shift is a central topic in many areas of machine learning. In the medical context, robustness is critical as covariate shifts are ubiquitous. Most notably, different healthcare providers serve different populations, with different demographics, baseline prevalence levels, behaviours and needs. If we ever hope to apply machine learning models in healthcare settings, they need to generalise to these different populations, or at least 'know' when they should be uncertain and be readily adaptable to new populations.

Aims and Objectives:
To develop novel methodology for interpretable and robust machine learning in the medical setting.
To apply these methods to generate new insights about health and disease.

Novelty of the research methodology: While there is a significant body of work on interpretability and robustness, much still needs to be done, for example in defining metrics of interpretability that are valid and useful in the biomedical context. We will improve upon existing methods by drawing from various related subfields in machine learning, such as causality, adversarial robustness, out-of-distribution detection, and Bayesian machine learning). We will work closely with domain experts to identify the most relevant research questions in biomedicine and healthcare.

Alignment to EPSRC's strategies and research areas. This research fits within the following EPSRC research areas: Artificial Intelligence Technologies, Image and Vision Computing, Information Systems, Mathematical Biology, Medical Imaging (including Medical Image and Vision Computing), Digital Signal Processing and Statistics and Applied Probability.

Companies or collaborators involved: None so far


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/S024050/1 01/10/2019 31/03/2028
2242671 Studentship EP/S024050/1 01/10/2019 30/09/2023 Jan Brauner