Considering spatial accessibility of health services is a critical part in the planning and management of health services. There is evidence that poor geographical locations can obstruct prompt basic health care services to some population sections. We developed a location-allocation P-median model for health centres after analysing their sites, demand location of health services and the road network in Jeddah, Saudi Arabia. This model attempts to optimize health care services network and to put forward location recommendations to maximise service coverage. Our model is shown to be useful as it provides a robust evidence base to urban planners and policymakers responsible for making spatial decisions for the development of the health sector. Besides, it follows the paradigm of new urbanism that encourages decentralisation of essential facilities including basic healthcare in cities, where emphasis is on offering all basic services within walkable distances of 15 min. or less.

The state of Mississippi has the highest colorectal cancer (CRC) mortality rate in the USA. The geographic distribution of CRC screening resources and geographic- and population-based CRC characteristics in Mississippi are investigated to reveal the geographic disparity in CRC screening. The primary practice sites of licensed gastroenterologists and the addresses of licensed medical facilities offering on-site colonoscopies were verified via telephone surveys, then these CRC screening resource data were geocoded and analyzed using Geographic Information Systems. Correlation analyses were performed to detect the strength of associations between CRC screening resources, CRC screening behavior and CRC outcome data. Age-adjusted colorectal cancer incidence rates, mortality rates, mortality-to-incidence ratios, and self-reported endoscopic screening rates from the years 2006 through 2010 were significantly different for Black and White Mississippians; Blacks fared worse than Whites in all categories throughout all nine Public Health Districts. CRC screening rates were negatively correlated with CRC incidence rates and CRC mortality rates. The availability of gastroenterologists varied tremendously throughout the state; regions with the poorest CRC outcomes tended to be underserved by gastroenterologists. Significant population-based and geographic disparities in CRC screening behaviors and CRC outcomes exist in Mississippi. The effects of CRC screening resources are related to CRC screening behaviors and outcomes at a regional level, whereas at the county level, socioeconomic factors are more strongly associated with CRC outcomes. Thus, effective control of CRC in rural states with high poverty levels requires both adequate preventive CRC screening capacity and a strategy to address fundamental causes of health care disparities.

Type-2 diabetes is a growing lifestyle disease mainly due to increasing physical inactivity but also associated with various other variables. In Saudi Arabia, around 58.5% of the population is deemed to be physically inactive. Against this background, this study attempts explore the spatial heterogeneity of Type-2 diabetes prevalence in Jeddah and to estimate various socio-economic and built environment variables contributing to the prevalence of this disease based on modelling by ordinary least squares (OLS), weighted regression (GWR) and multi-scale geographically weighted (MGWR). Our OLS results suggest that income, population density, commercial land use and Saudi population characteristics are statistically significant for Type-2 diabetes prevalence. However, by the GWR model, income, commercial land use and Saudi population characteristics were significantly positive while population density was significantly negative in this model for 70.6%, 9.1%, 26.6% and 58.7%, respectively, out of 109 districts investigated; by the MGWR model, the corresponding results were 100%, 22%, 100% and 100% of the districts. With the given data, the corrected Akaike information criterion (AICc), the adjusted R2, the log-likelihood and the residual sum of squares (RSS) indices demonstrated that the MGWR model outperformed the GWR and OLS models explaining 29% more variance than the OLS model, and 10.2% more than the GWR model. These results support the development of evidence-based policies for the spatial allocation of health associated resources for the control of Type-2 diabetes in Jeddah and other cities in the Arabian Gulf.

Human health is part of an interdependent multifaceted system. More than ever, we have increasingly large amounts of data on the body, both spatial and non-spatial, its systems, disease and our social and physical environment. These data have a geospatial component. An exciting new era is dawning where we are simultaneously collecting multiple datasets to describe many aspects of health, wellness, human activity, environment and disease. Valuable insights from these datasets can be extracted using massively multivariate computational techniques, such as machine learning, coupled with geospatial techniques. These computational tools help us to understand the topology of the data and provide insights for scientific discovery, decision support and policy formulation. This paper outlines a holistic paradigm called Holistics 3.0 for analyzing health data with a set of examples. Holistics 3.0 combines multiple big datasets set in their geospatial context describing as many areas of a problem as possible with machine learning and causality, to both learn from the data and to construct tools for data-driven decisions.

GeoMedStat: an integrated spatial surveillance system to track air pollution and associated healthcare events