Type and density of independent takeaway outlets: a geographical mapping study in a low socioeconomic ward, Manchester

Opportunities to improve population health: possibilities for healthier food environments

The recent Covid-19 pandemic highlighted stark social inequalities, notably around access to food, nutrition and to green or blue space (i.e. outdoor spaces with vegetation and water). Consequently, obesity is socio-economically patterned by this inequality; and while the environmental drivers of obesity are widely acknowledged, there is currently little upstream intervention. We know that living with obesity contributes to increasing health inequalities, and places healthcare systems under huge strain. Our environment could broadly be described obesogenic, in the sense of supporting unhealthful eating patterns and sedentary behaviour. Evidence points to the existence of nearly 700 UK obesity policies, all of which have had little success. Obesity prevention and treatment has focused on educational and behavioural interventions targeted at individual consumers. A more sustainable approach would be to try and change the environments that promote less healthy eating and high energy intake as well as sedentary behaviour. Approaches which modify the environment have the potential to assist in the prevention of this complex condition. This review paper focuses on the role of wider food environments or foodscapes. While there is an imperfect evidence base relating to the role of the foodscape in terms of the obesity crisis, policy, practice, civic society and industry must work together and take action now, in areas where current evidence suggests change is required. Despite the current cost-of-living crisis, shaping the foodscape to better support healthful eating decisions has the potential to be a key aspect of a successful obesity prevention intervention.

Social inequities in the food retail patterns around schools in Recife, Brazil

This study aimed to describe the community food environment surrounding schools and its association with territorial socio-environmental vulnerability in the city with the highest intraurban social inequity index in Brazil.

METHODS

this ecological observational study includes data on the presence and type of food retail in a 400 m buffer surrounding public and private schools in Recife. We have also described the Health Vulnerability Index (HVI) of census tracts and conducted multivariate analyses.

RESULTS

through factor analysis, we observed two grouping patterns of food retail. The "diverse food outlets" pattern was positively associated with middle HVI (β 0.14, 95% confidence interval [CI] - 0.11; 0.16) and higher HVI areas (β 0.15, 95%CI - 0.11; 0.17), while "the large food retail chains" pattern was inversely associated with middle HVI (β -0.42, 95% CI - 0.53; -0.30) and high HVI areas (β -0.32, 95%CI - 0.45; -0.18) and positively associated with private schools (β 0.15, 95%CI - 0.030; 0.27).

CONCLUSION

the greatest variety in food retail is in high HVI areas, and large food retail chains prevail around private schools, especially in low HVI areas.

Automatic classification of takeaway food outlet cuisine type using machine (deep) learning

BACKGROUND AND PURPOSE

Researchers have not disaggregated neighbourhood exposure to takeaway ('fast-') food outlets by cuisine type sold, which would otherwise permit examination of differential impacts on diet, obesity and related disease. This is partly due to the substantial resource challenge of manual classification of unclassified takeaway outlets at scale. We describe the development of a new model to automatically classify takeaway food outlets, by 10 major cuisine types, based on business name alone.

MATERIAL AND METHODS

We used machine (deep) learning, and specifically a Long Short Term Memory variant of a Recurrent Neural Network, to develop a predictive model trained on labelled outlets (n = 14,145), from an online takeaway food ordering platform. We validated the accuracy of predictions on unseen labelled outlets (n = 4,000) from the same source.

RESULTS

Although accuracy of prediction varied by cuisine type, overall the model (or 'classifier') made a correct prediction approximately three out of four times. We demonstrated the potential of the classifier to public health researchers and for surveillance to support decision-making, through using it to characterise nearly 55,000 takeaway food outlets in England by cuisine type, for the first time.

CONCLUSIONS

Although imperfect, we successfully developed a model to classify takeaway food outlets, by 10 major cuisine types, from business name alone, using innovative data science methods. We have made the model available for use elsewhere by others, including in other contexts and to characterise other types of food outlets, and for further development.