Jaume Bacardit

Professor of Artificial Intelligence

Newcastle University

Jaume Bacardit is Professor of Artificial Intelligence at the School of Computing of Newcastle University, and co-lead of the Interdisciplinary Computing and Complex BioSystems (ICOS) research group. His research interests include Explainable AI, how to make sense of how machine learning models make decisions, and the application of AI at the interface with the life sciences.

Robust and Interpretable Deep Learning for Biomedical Data

This project focuses on the development, training, and validation of deep learning pipelines for the analysis of biomedical data. Deep Learning is able to obtain state-of-the-art results in many data analysis tasks across a broad range of application areas and data modalities (e.g. tabular data, images, audio, accelerometer data). In their application to biological and biomedical data, special consideration needs to be placed on ensuring the robustness of these models (e.g. in relation to data confounders) and in interpretability (obtaining a precise understanding of how these models make decisions and what knowledge they have captured). This project will focus on the development of computational strategies to tackle these two challenges in biological/biomedical data, e.g. for medical diagnosis/prognosis, forecasting of animal growth data in farms.

Executive summary of project results

Our focus is the development of deep learning methods for their application at the interface with the life sciences. Within this scope, we have used BEDE for a variety of applications: -Tracking monkeys in video footage for behaviour identification - Analysis of longitudinal electronic health records - Analysis of retinal medical imaging for neurological and ophthalmological applications

How has your research benefitted from using Bede?

Having access to powerful GPUs has greatly accelerated the progress of our research.

Has using Bede allowed you to apply for other research funding?

We have chained several projects in part thanks to the research we performed on BEDE, for instance, our Glaucoma care project, funded by the Dunhill Medical Trust, came after our MRC-funded OCTage project.

Publications

The MacqD deep-learning-based model for automatic detection of socially housed laboratory macaques. Moat, Genevieve Jiawei, et al. Scientific Reports 15.1 (2025):11883. https://doi:10.1038/s41598-025-95180-x
Deep learning predicted perceived age is a reliable approach for analysis of facial ageing: A proof of principle study. Turner, Conor, et al. Journal of the European Academy of Dermatology and Venereology 38.12 (2024): 2295-2302. https://doi:10.1111/jdv.20365
Design of Deep Learning Ensembles for Age Prediction from Retinal OCT Scans. Taylor, Christian et al. IEEE Transactions on Medical Imaging (in review).