My research interests lie at the intersection of machine learning, explainability and healthcare; I particularly enjoy close collaboration with clinicians to understand how machine learning and data science can enhance and support the care they give. To achieve this, I utilise my understanding of explainable machine learning, natural language processing and computer vision to produce healthcare machine learning solutions that are effective, fair, transparent, robust and trustworthy.
Selected Publications
- M. Watson, P. Chambers, L. Steventon, J. H. King, A. Ercia, H. Shaw, N. Al Moubayed “From Prediction to Practice: Mitigating Bias and Data Shift in Machine Learning Models for Chemotherapy-Induced Organ Dysfunction Across Unseen Cancers” BMJ Oncology Under Review
- M. Watson, S. Logothetis, D. Green, M. Holland, P. Chambers, N. Al Moubayed “Machine Learning Surpasses the National Early Warning Score in Predicting Patient Deterioration Risk” BMJ Health and Care Informatics Under Review
- M. Watson, B. Hasan, and N. Al Moubayed. “Membership Inference Attacks and Defences Using Deep Learning Model Explanations” Scientific Reports Under Review
- P. Chambers, M. Watson, et al. “Personalising monitoring for chemotherapy patients through predicting deterioration in renal and hepatic function.” Cancer Medicine 2023.
- M. Watson, S. Logothetis, et al. “Using Triage Notes and Machine Learning to Predict Patient Deterioration in Acute Care Settings” Society for Acute Medicine 17th International Conference 2023
- M. Watson, S. Logothetis, et al. “Unplanned Readmission Prediction Using Triage Notes and Electronic Health Records” Society for Acute Medicine 17th International Conference 2023
- M. Watson “Explainable Machine Learning for Robust Modelling in Healthcare” PhD Thesis 2023.
- M. Watson, B. Hasan, and N. Al Moubayed. “Learning How to MIMIC: Using Model Explanations to Guide Deep Learning Training.” Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision. 2023.
- M. Watson, B. Hasan, and N. Al Moubayed. “Using model explanations to guide deep learning models towards consistent explanations for EHR data.” Scientific Reports 12.1 (2022): 1-14.
- M. Watson, B. A. S. Hasan, and N. Al Moubayed, “Agree to disagree: When deep learning models with identical architectures produce distinct explanations,” in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2022, pp. 875–884.
- Z. Zuo, M. Watson, D. Budgen, R. Hall, C. Kennelly, and N. Al Moubayed, “Data anonymization for pervasive health care: Systematic literature mapping study,” JMIR Med Inform, vol. 9, no. 10, p. e29871, Oct 2021.
- M. Watson, P. Chambers, et al., “Using deep learning with demographic and laboratory values from baseline to cycle 2 to predict subsequent renal and hepatic function,” Annals of Oncology, vol. 32, p. S1250, Sep 2021.
- M. Watson and N. Al Moubayed, “Attack-agnostic adversarial detection on medical data using explainable machine learning,” in 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, 2021, pp. 8180–8187.
Invited Talks, Awards & Media
- PI on a successful NIHR Undergraduate Internship Programme grant, 2024
- Contributor and named researcher on a large Innovate UK grant
- Invited to give a talk at the Health Data Research (HDR) UK Conference 2024
- Research included in policy briefings to the Department of Health and Social Care on addressing winter pressures in the NHS
- My work “Using Triage Notes and Machine Learning to Predict Patient Deterioration in Acute Care Settings” was selected for an oral presentation at SAM 2023, and won the Overall Best Poster Award
- Contributor and named researcher on a HDR UK/NIHR Winter Pressures Fund grant
- Won the WACV 2022 Best Paper Award