Machine learning and patterns of primary care use in cancer diagnosis and outcomes

This project seeks to apply novel analytical and machine learning methods to the large-scale linked data sources. This will generate new hypotheses and further characterise how people with cancer engage with primary care services.

The project aims to identify patterns in various aspects of primary cancer attendances prior to a definitive cancer diagnosis. These could include:

• prescribing
• test requests and results
• semi-coded fields such as ‘reason for encounter’
• co-morbidities or other conditions captured in primary care management systems.

The project will identify a specific cancer type (i.e. Upper Gastrointestinal) with sufficient linkages between hospital diagnosis and primary care data.  It will also apply tools and algorithms to detect patterns present within specific timeframes of diagnosis or treatment.