Background/aim Because type 2 diabetes and obesity are more prevalent in deprived areas, it is crucial to consider environmental features related to healthy lifestyles and health care structures. The aim of our study is to develop technical and methodological algorithms to use Google Maps to extract and discover relevant information on the built environment.

Methods First, we identified neighbourhood characteristics associated with obesity, physical inactivity and health care according to the literature. Second, we assessed relevant environmental factors through geocoding services like Google Maps. We derived and refined intelligent extraction, data cleaning and discovery algorithms that allow processing big data files and identifying pathways and patterns. For three representative sub-areas, we validated the results by comparison with the actual built environment. Finally, we created detailed maps for these characteristics which can be used to monitor spatial and temporal patterns.

Results First results of literature research point to the fact that geocoding services like Google Maps have been shown to provide valid, reliable and low-cost data for the study purpose. This could be further confirmed through real life site inspection for three representative sub-areas.

Conclusion Methods to describe different components of obesogenic environments and health care structures could be potentially integrated in diabetes surveillance programs to improve risk-prediction and to tailor prevention strategies.