Background:
Volunteering support is increasingly recognised as a valuable public health intervention for improving mental health outcomes, but its broader population-level impact remains under-researched. This project seeks to investigate the effects of volunteering on individuals with mental health conditions by utilising large-scale, multimodal data sources. By examining data from electronic health records, through the Clinical Record Interactive Search (CRIS) platform and self-reported and passive data collected through smart-phones, this research will provide key insights into the health and social outcomes influenced by volunteer support.
Novelty and Importance:
This study uses advanced data science techniques, including development of natural language processing (NLP) and machine learning, to analyse large-scale mental health records and smartphone data. It is the first study to integrate NLP in assessing volunteer support, uniquely testing this in a digital healthcare environment within an NHS mental health trust. This approach is crucial for developing next-generation, sustainable healthcare solutions that combine technological advancements with human support to optimise patient outcomes.
Aims and objectives:
This PhD project aims to:
- Evaluate the effectiveness of volunteering support on mental health outcomes using data from electronic health records.
- Analyse the health and social impacts of volunteering using self-reported and passive smartphone data.
- Develop cutting-edge NLP tools to extract volunteering-related data from electronic health records and smartphone data.
- Provide evidence-based recommendations for integrating volunteer support into sustainable healthcare models.

