Horizon CDT Research Highlights

Research Highlights

Diagnosing Disease with Shopping Data

  Elizabeth Dolan (2019 cohort)

The aim:

To create a framework for “Personal Data Donation” by investigating the issues surrounding individuals “donating” personal transactional data to public health research projects.

The question:

How can personal transactional data be collected and analysed for the purposes of health research in a way that is acceptable to society, works for chronic disease, and can be successfully implemented in a clinical setting?

Overview:

This PhD is connected to a wider project by partners ALSPAC at Bristol University(2020) and the Alan Turing Institute(2020): “donating personal transactional data for research: investigating the public acceptability of using commercial transactional data in public health research”.

Personal commercial transactional data is the information stored when an exchange occurs between an individual and a business, including customer shopping data.  This research will connect loyalty card data (customer shopping information held by a retailer) to information from women with ovarian cancer.  Connecting this data will be used to investigate whether women’s shopping data can be used to get women with ovarian cancer diagnosed earlier.

A collection of studies will be done to iteratively create a machine learning (ML) model (a method of programming computers to learn from data) whose analysis could create a screening tool, for use in community pharmacists or GPs, to assess whether a woman needs medical investigations for ovarian cancer.

The methodology to be used is mixed methods collecting and analysing both qualitative data, and quantitative data for integrated interpretation.  The studies will be used to inform the models schema creation, feature engineering, to understand, and validate its outputs and any interpretations made from these.  The iterative design will allow for adjustments to the model for successful implementation in a clinical setting.  

The survival rate for ovarian cancer is low as women are often diagnosed in the late stages of the disease, with no UK national screening programme (Cancer Research UK 2020).  This research aims to get women diagnosed earlier. Creating a framework for “Personal Data Donation”, using this research, will help medical researchers assess the potential of using shopping data to improve public health for other diseases.  This framework, crafted around a ML methodology, will help in investigating the regulations needed for the implementation of AI health systems.

References

Alan Turing Institute. 2020 [Viewed 26 February 2020] Available from: https://www.turing.ac.uk/research/research-projects/donating-personal-transactional-data-research

ALSPAC (Avon Longitudinal Study of Parents and Children) at Bristol University. 2020 [Viewed 26 February 2020] Available from: www.bristol.ac.uk/alspac/

Cancer Research UK. 2020 [Viewed 26 February 2020] Available from:  https://www.cancerresearchuk.org/about-cancer/ovarian-cancer

This author is supported by the Horizon Centre for Doctoral Training at the University of Nottingham (UKRI Grant No. EP/S023305/1).