Early Detection and Fall‑Risk Stratification in Dementia Using Next‑Generation Wearable Sensor Technology

Project description

People living with dementia are at-high-risk of mobility decline and falls, with risk amplified further by comorbid conditions, such as diabetes. This PhD will test whether continuous, real‑world movement data captured via advanced wearable sensors can improve early detection of dementia‑related mobility decline, refine prognosis, and enhance fall‑risk prediction.

We hypothesise that high‑resolution motion analytics will detect subtle, preclinical gait and balance changes that occur before clear cognitive decline and clinical symptoms. These digital biomarkers are expected to identify mobility change earlier than conventional assessments and to reveal larger impairments in dementia, supporting more personalised, effective fall‑prevention strategies and helping people remain mobile and independent for longer.

This is an inter‑disciplinary PhD at the interface of clinical neuroscience, biomedical engineering, and data science. You will work with preclinical and clinical dementia cohorts, collecting and interpreting high‑granularity movement data using cutting‑edge wearable sensor technology in lab and real‑world settings.

You will gain skills in wearable deployment, signal processing, and machine‑learning approaches for gait/balance analytics, alongside clinical phenotyping of dementia populations and translational research that can influence diagnostics, care pathways, and policy.

We welcome applicants from Engineering, Computer Science/Data Science/AI, Neuroscience or related fields, with strong quantitative skills and enthusiasm for interdisciplinary, patient‑impact research.

The successful candidate is likely to have the following qualifications:

• A 1st or 2:1 degree in a relevant discipline and/or second degree with a related Masters.