Public attitudes towards sharing loyalty card data for academic health research: a qualitative study

Overcoming biases of individual level shopping history data in health research

Novel sources of population data, especially administrative and medical records, as well as the digital footprints generated through interactions with online services, present a considerable opportunity for advancing health research and policymaking. An illustrative example is shopping history records that can illuminate aspects of population health by scrutinizing extensive sets of everyday choices made in the real world. However, like any dataset, these sources possess specific limitations, including sampling biases, validity issues, and measurement errors. To enhance the applicability and potential of shopping data in health research, we advocate for the integration of individual-level shopping data with external datasets containing rich repositories of longitudinal population cohort studies. This strategic approach holds the promise of devising innovative methodologies to address inherent data limitations and biases. By meticulously documenting biases, establishing validated associations, and discerning patterns within these amalgamated records, researchers can extrapolate their findings to encompass population-wide datasets derived from national supermarket chain. The validation and linkage of population health data with real-world choices pertaining to food, beverages, and over-the-counter medications, such as pain relief, present a significant opportunity to comprehend the impact of these choices and behavioural patterns associated with them on public health.

Assessing household lifestyle exposures from consumer purchases, the My Purchases cohort

Consumer purchase data (CPD) is a promising instrument to assess the impact of purchases on health, but is limited by the need for manual scanning, a lack of access to data from multiple retailers, and limited information on product data and health outcomes. Here we describe the My Purchases cohort, a web-app enabled, prospective collection of CPD, covering several large retail chains in Denmark, that enables linkage to health outcomes. The cohort included 459 participants as of July 03, 2023. Up to eight years of CPD have been collected, with 2,225,010 products purchased, comprising 223,440 unique products. We matched 88.5% of all products by product name or item number to one generic food database and three product databases. Combined, the databases enable analysis of key exposures such as nutrients, ingredients, or additives. We found that increasing the number of retailers that provide CPD for each consumer improved the stability of individual CPD profiles and when we compared kilojoule information from generic and specific product matches, we found a median modified relative difference of 0.23. Combined with extensive product databases and health outcomes, CPD could provide the basis for extensive investigations of how what we buy affects our health.

Assessing the value of integrating national longitudinal shopping data into respiratory disease forecasting models

The COVID-19 pandemic led to unparalleled pressure on healthcare services. Improved healthcare planning in relation to diseases affecting the respiratory system has consequently become a key concern. We investigated the value of integrating sales of non-prescription medications commonly bought for managing respiratory symptoms, to improve forecasting of weekly registered deaths from respiratory disease at local levels across England, by using over 2 billion transactions logged by a UK high street retailer from March 2016 to March 2020. We report the results from the novel AI (Artificial Intelligence) explainability variable importance tool Model Class Reliance implemented on the PADRUS model (Prediction of Amount of Deaths by Respiratory disease Using Sales). PADRUS is a machine learning model optimised to predict registered deaths from respiratory disease in 314 local authority areas across England through the integration of shopping sales data and focused on purchases of non-prescription medications. We found strong evidence that models incorporating sales data significantly out-perform other models that solely use variables traditionally associated with respiratory disease (e.g. sociodemographics and weather data). Accuracy gains are highest (increases in R2 (coefficient of determination) between 0.09 to 0.11) in periods of maximum risk to the general public. Results demonstrate the potential to utilise sales data to monitor population health with information at a high level of geographic granularity.

Understanding Public Attitudes and Willingness to Share Commercial Data for Health Research: Survey Study in the United Kingdom

BACKGROUND

Health research using commercial data is increasing. The evidence on public acceptability and sociodemographic characteristics of individuals willing to share commercial data for health research is scarce.

OBJECTIVE

This survey study investigates the willingness to share commercial data for health research in the United Kingdom with 3 different organizations (government, private, and academic institutions), 5 different data types (internet, shopping, wearable devices, smartphones, and social media), and 10 different invitation methods to recruit participants for research studies with a focus on sociodemographic characteristics and psychological predictors.

METHODS

We conducted a web-based survey using quota sampling based on age distribution in the United Kingdom in July 2020 (N=1534). Chi-squared tests tested differences by sociodemographic characteristics, and adjusted ordered logistic regressions tested associations with trust, perceived importance of privacy, worry about data misuse and perceived risks, and perceived benefits of data sharing. The results are shown as percentages, adjusted odds ratios, and 95% CIs.

RESULTS

Overall, 61.1% (937/1534) of participants were willing to share their data with the government and 61% (936/1534) of participants were willing to share their data with academic research institutions compared with 43.1% (661/1534) who were willing to share their data with private organizations. The willingness to share varied between specific types of data-51.8% (794/1534) for loyalty cards, 35.2% (540/1534) for internet search history, 32% (491/1534) for smartphone data, 31.8% (488/1534) for wearable device data, and 30.4% (467/1534) for social media data. Increasing age was consistently and negatively associated with all the outcomes. Trust was positively associated with willingness to share commercial data, whereas worry about data misuse and the perceived importance of privacy were negatively associated with willingness to share commercial data. The perceived risk of sharing data was positively associated with willingness to share when the participants considered all the specific data types but not with the organizations. The participants favored postal research invitations over digital research invitations.

CONCLUSIONS

This UK-based survey study shows that willingness to share commercial data for health research varies; however, researchers should focus on effectively communicating their data practices to minimize concerns about data misuse and improve public trust in data science. The results of this study can be further used as a guide to consider methods to improve recruitment strategies in health-related research and to improve response rates and participant retention.