Using data science to improve the detection of post-stroke dementia

Eugene Tang Final reporting   2024


Recent work has found that machine learning algorithms were superior in their ability to predict incident dementia compared to the more traditional risk prediction tools such as the Cardiovascular Risk Factors, Aging, and Incidence of Dementia Risk Score, and the Brief Dementia Screening Indicator. A similar approach could be used to develop risk prediction models to assess a stroke patient’s risk for future dementia. Such tools could then be used to stratify patients in clinical trial settings which could have the potential to reduce the risk of developing dementia.


This career development award aims to strengthen Eugene’s skills in artificial intelligence (AI) analysis, prognostic research and clinical trials to inform the development of a new program of work.

The award aims to develop mixed-methodological expertise to facilitate a future post-doctoral fellowship application focussed on both the earlier identification of incident dementia post-stroke and the development of interventions in this area. Specific objectives include:

  • Formal data science training and qualification to foster future collaborations within internationals network of dementia researchers
  • Building upon existing prognostic research expertise through short courses
  • Formal training in clinical trials to involve patients at-risk of dementia in future interventional studies and to evaluate risk screening.
  • Mentorship from experts in the field of dementia research.