Shannon N Millard

Thesis title: Developing Multimodal Biomarkers and Computational Models for Objective and Subjective Impairments in Altered Cognitive States Using fNIRS, EEG, and Eye-Tracking

Background

First-year PhD student in the Precision Medicine Doctoral Training Program (DTP) at the University of Edinburgh, with co-supervision at the University of Glasgow. My project is centred on building computational approaches to interpret multimodal brain data, integrating EEG, fNIRS, and eye-tracking with machine learning. My broader research interests lie in precision neuropsychiatry, with a background in neurobiology-driven biomarkers for mental health research.

Qualifications

MSci (Hons) Neuroscience with Year in Industry, The University of Nottingham

Research summary

Developing computational frameworks for interpreting multimodal neuroimaging data to characterise different brain states, with applications in transdiagnostic precision neuropsychiatry.

Current research interests

My PhD research will focus on developing a computational approach to interpret multimodal brain data, with the broader aim of building tools that are sensitive on an individual-level and are applicable across a range of neuropsychiatric conditions. As a test case, I am focusing on altered brain states that impact cognition, such as mental fatigue, drowsiness, and brain fog: symptoms that are highly prevalent and clinically important across neuropsychiatric disorders, yet remain difficult to measure objectively. Building on recent work showing that multi-frequency steady-state visual evoked potentials (SSVEPs) provide sensitive markers of attentional modulation, I will use a novel multimodal neuroimaging headset integrating EEG (electrical activity), fNIRS (blood oxygenation, similar to fMRI), and eye-tracking to capture brain activity during visual flicker paradigms and higher-order cognitive tasks targeting attention, working memory, and executive function. Developing and validating this hardware and computational pipeline is itself a core aim of the project. Using machine learning, I will then identify consistent, individualised neural signatures of brain state using longitudinal data under different experimental conditions (e.g., mild sleep deprivation), linked to subjective reports of cognitive function and mental clarity. The ultimate goal of this research is to develop a scalable platform with the potential to inform early detection and personalised interventions in a disease-agnostic manner, with applications spanning long COVID, burnout, traumatic brain injury, multiple sclerosis, and more.

Past research interests

My research training commenced with my MSci degree in Neuroscience, including an industry placement year at P1vital Ltd, a research organisation specialising in digital neuropsychological tasks. This was my first introduction to Precision Medicine through working on the IMI-funded PRISM project, investigating quantitative neurobiological measures for social and cognitive deficits across Alzheimer’s disease, schizophrenia, and depression. After graduating, I worked briefly in business strategy and secondary data studies in healthcare before realising that my true passion remained in mental health and precision neuropsychiatry research. That led me back to P1vital, where I worked on identifying and analysing neuropsychological biomarkers to improve both mechanistic understanding and treatment strategies in over 10 experimental medicine studies across neurodegenerative, mood, and psychotic disorders. I was particularly interested in reward and emotional processing, co-authoring several publications and conference posters in this area.