I am Ensor Palacios, a research associate at the University of Bath, working in the Healthcare Ecosystem theme of the AI4CI research hub.
I am interested in applying statistical and machine learning techniques for both prediction and causal inference to health-related problems. Although my current focus mainly concerns human health, I’m keen to broaden my research applications.
My background is interdisciplinary: after obtaining a degree in psychology and cognitive neuroscience at the University of Padua, Italy, I moved to the UK to work in computational and experimental neuroscience, first at UCL, within the theoretical neuroscience group lead by Prof. Karl Friston, and subsequently at the University of Bristol, where I completed my PhD under the supervision of Dr. Paul Chadderton and Dr. Conor Houghton. After the PhD, I carried out a transition fellowship in environmental epidemiology based in the MRC Integrative Epidemiology Unit (IEU), Bristol; this project was mentored by Prof. Kate Tilling and involved a multidisciplinary team of experts. Lastly, I moved to the University of Bath, where I am currently working with Dr. Theresa Smith on data analysis applied to health
What are you working on?
I am working on different projects. The first involves predicting bed occupation in two hospitals in Bristol, with the aim of providing early warnings for upcoming hospital capacity saturation. The second project aims to improve personalised condition management for people with Type 1 diabetes, and involves using clustering methods applied to both quantitative (e.g., time-series) and qualitative (e.g., text) data to identify fine-grained groups within this population, which have different characteristics and requirements. The third project aims to improve the long-term outcome of people using NHS mental health talking therapy services, by creating data analytics tools to support clinicians development and workload.
What excites you most about your field of research?
Two things excite me the most about my field of research: first, the diversity of problems I face, which provides the possibility to explore and use a variety of statistical and machine learning tools. Second, the potential for the outcome of my work to have practical applications.
Who has influenced your academic journey the most?
The people who have most influenced me so far have been Prof. Karl Friston and Prof. Kate Tilling. The reason is that both mentored me, in their own way and at different stages of my academic journey, while I was undertaking a career shift, and helped me to consolidate the new trajectory of my research.
Can you recommend a paper you think we should read?
To be consistent with my previous answer, I will suggest a paper by Prof. Karl Friston titled “The free-energy principle: a unified brain theory?”. This paper offers an overview of the Free Energy Principle, a theory of why the brain, the computations it performs (e.g., perception), and the actions it generates (e.g., behaviour), appear as they do. Moreover, this theory allows us to understand in a unified way dynamics that unfold at different spatial scales (e.g., from cellular to system level) and temporal scales (e.g., from milliseconds to days). Finally, this theory can be used to explain any dynamical system, not only the brain, and therefore can be used to understand life as we know it.
What are your ‘Top Tips’ for early career researchers?
Maybe, the only thing that is useful to say here is what I try to do, broadly; that is, I try to seek out projects that I think can excite me, without looking too far ahead into the future and organise my work accordingly. Basically, question yourself as to whether you really enjoy your work, and remain open-minded for new opportunities.