Niall Taylor
CDT Student
I have a background in experimental psychology, with a Bachelors from the University of Plymouth, followed by a Masters by Research at the University of Bristol. Whilst in Bristol I also worked on the famous ALSPAC (Avon Longitudinal Study of Parents and Children) project, for which I am actually an original cohort member. For a time I worked as a freelance science writer and data scientist before starting a bioinformatics research assistant position at the University of Oxford in the department of psychiatry. There I worked on a number of digital phenotyping studies on Bipolar Disorder and depression, including True Colours, a remote symptom monitoring service hosted by the Oxford NHS trust. Throughout my time in that position, I handled a number of data ethics applications, and have grown to enjoy the discussions around ethical use of patient data, especially the methods of protecting patients’ rights, whilst maintaining the richness of population health data.
My overarching interests focus on the application and uptake of machine and deep learning in the realm of mental health, with the aid of big data and wearable devices. Moreover, I’d like to explore the acceptability and efficacy of using ML models in real clinical applications, and how patients themselves can benefit from information produced by these methods.
Recent publications
-
Developing healthcare language model embedding spaces.
Taylor N. et al, (2024), Artificial intelligence in medicine, 158
-
Efficiency at scale: Investigating the performance of diminutive language models in clinical tasks.
Taylor N. et al, (2024), Artificial intelligence in medicine, 157
-
Optimising the use of electronic medical records for large scale research in psychiatry.
Newby D. et al, (2024), Translational psychiatry, 14
-
Clinical Prompt Learning With Frozen Language Models.
Taylor N. et al, (2023), IEEE transactions on neural networks and learning systems, PP
-
Rationale production to support clinical decision-making
TAYLOR N., (2021)