Geographic Targeting Research Articles

GEOGRAPHICALLY WEIGHTED MACHINE LEARNING MODEL FOR ADDRESSING SPATIAL HETEROGENEITY OF PUBLIC HEALTH DEVELOPMENT INDEX IN JAVA ISLAND

Random Forest (RF) machine learning models have emerged as a prominent algorithm, addressing problems arising from the sole use of decision trees, such as overfitting and instability. However, conventional RF has global coverage that may need to capture spatial variations better. Based on the analysis of the level of public health development, the relationship between the level of health development and risk factors can vary spatially. We use a modified RF algorithm called Geographically Weighted Random Forest (GW-RF) to address this challenge. GW-RF, as a tree-based non-parametric machine learning model, can help explore and visualize relationships between the Public Health Development Index (PHDI) as response variables and factors that are indicators at the district level. GW-RF output is compared with global output, which is RF in 2018 using the percentage of the population with access to clean/decent water (X1), consumption of eggs and milk per capita per week (X2), number of healthcare facilities per 1000 people (X3), number of doctors per 1000 people (X4), pure participation rate ratio female/male (X5), percentage of households that have hand washing facilities with soap and water (X6) as independent variables. Our results show that the non-parametric GW-RF model shows high potential for explaining spatial heterogeneity and predicting PHDI versus a global model when including six major risk factors. However, some of these predictions mean little. Findings of spatial heterogeneity using GW-RF show the need to consider local factors in approaches to increasing PHDI values. Spatial analysis of PHDI provides valuable information for determining geographic targets for areas whose PHDI values need to be improved.

Validating claims-based algorithms for a systemic lupus erythematosus diagnosis in Medicare data for informed use of the Lupus Index: a tool for geospatial research

ObjectiveThis study aimed to validate claims-based algorithms for identifying SLE and lupus nephritis (LN) in Medicare data, enhancing the use of the Lupus Index for geospatial research on SLE prevalence...

Mapping fertility rates at national, sub-national, and local levels in Ethiopia between 2000 and 2019.

Fertility rates are key indicators of population health and demographic change, influencing economic development, healthcare planning, and social policies. Understanding subnational variation in fertility rate is important for effective geographical targeting and policy prioritization. This study aimed to identify geographic variation, trends, and determinants of fertility rates in Ethiopia over the past two decades. We estimated total fertility rates (TFRs) and age-specific fertility rates (ASFRs) using five nationally representative cross-sectional Demographic and Health Surveys collected in Ethiopia between 2000 and 2019. ASFRs represent the number of live births per 1,000 women aged 15 to 49 during the 3 years before each survey, while TFRs indicate the average number of children a woman would have by the end of her reproductive years, calculated as the sum of ASFRs over five-year intervals. We developed model-based geostatistics by incorporating demographic and healthcare access data with spatial random fields to produce high-resolution fertility rate maps. These results were then aggregated to produce fertility rate estimates at local, sub-national, and national levels in Ethiopia. The national TFR gradually declined from 4.8 live births in 2000 to 4.2 live births in 2019, but it is still above the replacement level of 2.1 children per woman. There were sub-national and local variations in TFR, ranging from 5.7 live births in Somalia and 5.3 Oromia regions to 2.7 live births in Addis Ababa and 3.6 live births Dire Dawa cities. Geographical areas with high TFR were mostly associated with a high proportion of Muslim women and low access to health facilities. Despite a decline in fertility rates among women of reproductive age over the past two decades, marked spatial variation persists at sub-national and local levels in Ethiopia, with demographic factors determining the spatial distribution and rate of decline, highlighting the need for tailored programs and strategies in high-fertility areas to increase access to family planning.

Digital exclusion as a barrier to accessing healthcare: a summary composite indicator and online tool to explore and quantify local differences in levels of exclusion

AbstractExisting disparities in digital access were exacerbated with the accelerated shift to online provision of services during the COVID-19 pandemic, particularly for already disadvantaged groups. Metrics to quantify relative local differences in levels of digital exclusion are a necessary pre-requisite for the targeting of interventions to address these disparities. In this study we developed a composite indicator and an interactive dashboard ‘The Lincolnshire Digital Health Toolkit’ to explore digital exclusion in Lincolnshire, UK. To develop the indicator, individual variables were normalised and aggregated, intra-variable correlations explored, and factor analysis used to determine variable weightings. Three underlying factors were identified that explained a significant proportion of the variance in the original variables, the first two predominantly related to socioeconomic deprivation and lack of activity. In general, coastal areas in the east of the county had higher levels of digital exclusion, with significant local variation particularly within urban areas. Long travel times to reach medical facilities are an additional barrier in some communities. The toolkit has been used to support the evidence-based geographic targeting of interventions to address barriers to accessing digitally based health information and services. The impact of digital exclusion must be addressed to reduce marginalisation and isolation. The Lincolnshire Digital Health Toolkit provides a novel composite metric tailored to the conditions of this largely rural county and an interactive dashboard to support decisions on resource allocation.

Prevalence of undiagnosed hypertension and associated factors in Ndera sector, Gasabo district of Rwanda: a cross-sectional study

BackgroundHypertension remains a major global health challenge, including in low- and middle-income countries. In Rwanda, a lack of adequate information and healthcare services impacts healthcare-seeking behaviors, contributing to undiagnosed hypertension in rural areas. Therefore, the need to determine its prevalence and associated factors.MethodsA cross-sectional study was conducted with 393 adults in the Ndera Sector, of Rwanda’s Gasabo District, through a multistage sampling technique. Data was gathered using the WHO STEP-wise approach to non-communicable disease risk factor surveillance (STEPS) questionnaire; physical examination was done to determine blood pressure and body-mass index (BMI), after which the data collected was analyzed using SPSS. Newly diagnosed hypertension was determined when on two different intervals, systolic blood pressure readings was > 140 mmHg, and/or the diastolic blood pressure readings was > 90 mmHg, in the absence of previous hypertension diagnosis.ResultsThe overall prevalence of hypertension among patients at Ndera sector was 15%, all of which were newly diagnosed. The mean (SD) age of the participants was 37 (13.7) years and half (53%) were women. The mean systolic blood pressure for men was 124.3 mmHg compared to 120.9 mmHg for women (p = 0.043, 95%CI: 0.12–6.74). Women had a significantly higher mean BMI (26.0) compared to men (22.8) (p < 0.001, 95%CI: -4.18 - -2.31). Age (χ² = 37.400, p < 0.001), residence (χ² = 10.200, p < 0.001), BMI (χ² = 22.1, p < 0.001), and lack of knowledge about hypertension (χ² = 25.1, p < 0.001) were the factors with significantly undiagnosed hypertension.ConclusionsThe high prevalence of undiagnosed hypertension in Ndera Sector is linked to gender, older age, higher BMI, location, and lack of hypertension knowledge. These findings call for multifaceted approaches, combining educational initiatives, geographical targeting, lifestyle modifications, and policy implementations, all aimed at mitigating the burden of undiagnosed hypertension and enhancing community health within the Ndera Sector.

MMHCA: Multi-feature representations based on multi-scale hierarchical contextual aggregation for UAV-view geo-localization

In global navigation satellite system denial environment, cross-view geo-localization based on image retrieval presents an exceedingly critical visual localization solution for Unmanned Aerial Vehicle (UAV) systems. The essence of cross-view geo-localization resides in matching images containing the same geographical targets from disparate platforms, such as UAV-view and satellite-view images. However, images of the same geographical targets may suffer from occlusions and geometric distortions due to variations in the capturing platform, view, and timing. The existing methods predominantly extract features by segmenting feature maps, which overlook the holistic semantic distribution and structural information of objects, resulting in loss of image information. To address these challenges, dilated neighborhood attention Transformer is employed as the feature extraction backbone, and Multi-feature representations based on Multi-scale Hierarchical Contextual Aggregation (MMHCA) is proposed. In the proposed MMHCA method, the multi-scale hierarchical contextual aggregation method is utilized to extract contextual information from local to global across various granularity levels, establishing feature associations of contextual information with global and local information in the image. Subsequently, the multi-feature representations method is utilized to obtain rich discriminative feature information, bolstering the robustness of model in scenarios characterized by positional shifts, varying distances, and scale ambiguities. Comprehensive experiments conducted on the extensively utilized University-1652 and SUES-200 benchmarks indicate that the MMHCA method surpasses the existing techniques, showing outstanding results in UAV localization and navigation.

Environmental Impacts on Behavioral Health Interventions: The Moderating Effect of Neighborhood Deprivation on a Mobile Health Treatment for Depression

Relatively little scholarly attention has been given to incorporating geographic principles into investigations of behavioral health intervention efficacy—where, and why, a behavioral health intervention might be more effective in one place versus another. We address this research gap by leveraging data from a randomized controlled trial in a post-hoc analysis to investigate whether socioeconomic deprivation in the residential neighborhood moderates the efficacy of a text-message-delivered (mHealth) depression intervention targeted toward young adults. Ninety-seven participants were recruited from social media sources, randomly assigned to the treatment or control condition, and assessed for depression symptoms and related outcomes at baseline, one month, two months (immediately following treatment completion), and three months. We find that intervention effects for reducing depression symptoms were stronger among participants residing in neighborhoods with higher, as compared to lower, socioeconomic deprivation (β = −0.208, p = 0.013, 95 percent CI [−0.372, −0.044]). Similarly, stronger intervention effects for enhancing behavioral activation (β = 0.150, p = 0.028, 95 percent CI [0.016, 0.284]) and for reducing cognitive distortion (β = −0.476, p = 0.002, 95 percent CI [−0.777, −0.175]), malleable behaviors and thinking processes intended to lessen depression, were found for residents of higher deprivation neighborhoods. We speculate these results reflect an enhanced ability to intervene in processes of self-regulation among those living in higher deprivation neighborhoods, which might stem from the experience of chronic stress in such settings, thus resulting in greater receptivity to intervention components that reduce depressive symptoms. These findings could facilitate geographic targeting to enhance intervention efficacy and guide geographically informed health interventions tailored to specific environmental conditions.

Geographical targeting of active case finding for tuberculosis in Pakistan using hotspots identified by artificial intelligence software (SPOT-TB): study protocol for a pragmatic stepped wedge cluster randomised control trial

IntroductionPakistan has significantly strengthened its capacity for active case finding (ACF) for tuberculosis (TB) that is being implemented at scale in the country. However, yields of ACF have been lower...

Deep Smooth Random Sampling and Association Attention for Air Quality Anomaly Detection

Real-time monitoring and timely warning of air quality are vital components of building livable cities and implementing the “Healthy China” strategy. Real-time, efficient, and accurate detection of air quality anomalies holds great significance. However, almost all existing methods for air quality anomaly detection often overlook the imbalanced distribution of data. In addition, many traditional methods cannot learn both pointwise representation and pairwise association, so they cannot solve complex features. This study proposes an anomaly detection method for air quality monitoring based on Deep Smooth Random Sampling and Association Attention in Transformer (DSRS-AAT). Firstly, based on the third geographical law, the more similar the geographical environment, the closer the geographical target features are. We cluster sites according to the surrounding geographic features to fully explore latent feature associations. Then, we employ Deep Smooth Random Sampling to rebalance the air quality datasets. Meanwhile, the Transformer with association attention considers both prior associations and series associations to distinguish anomaly patterns. Experiments are carried out with real data from 95 monitoring stations in Haikou City, China. Final results demonstrate that the proposed DSRS-AAT improves the effectiveness of anomaly detection and provides interpretability analysis for traceability, owing to a significant improvement with the baselines (OmniAnomaly, THOC, etc.). The proposed method effectively enhances the effectiveness of air quality anomaly detection and provides a reference value for real-time monitoring and early warning of urban air quality.

Integrating Survey and Geospatial Data for Geographical Targeting of the Poor and Vulnerable: Evidence from Malawi

Integrating Survey and Geospatial Data for Geographical Targeting of the Poor and Vulnerable: Evidence from Malawi

Distributed Multiband Synthetic Aperture Radar Image Fusion Based on Wavelet Transform in the Internet of Things Environment

Abstract In order to improve the detection and recognition capabilities of distributed multiband synthetic aperture radar (SAR) images in the Internet of Things environment, a distributed multiband SAR image fusion algorithm based on wavelet transform is proposed for the Internet of Things environment. The multispectral/hyperspectral imager is used to detect and process the distributed multiband SAR image. The feature extraction method of fast spatial geographic water target range radar signal source is used to extract and segment the distributed multiband SAR image. The wavelet multiscale transform method is used to segment the SAR image, and the linear filtering and nonlinear filtering methods are used to detect the edge contour features. Using the distributed multiband SAR image fusion technology based on the calculation of high-frequency subband edge function and the segmentation of regional gray contour curve, the splitting and broadening of the peak spectrum of the target image of the radar signal source in the fast spatial geographical waters, as well as the radar target positioning parameters, the noise filtering, and anti-jamming detection of the distributed multiband SAR image are realized, and the distributed multiband SAR image fusion is realized combined with wavelet transform. The test results show that the output peak signal-to-noise ratio of distributed multiband SAR image fusion using this method is high, and the performance of detection and recognition of SAR imaging targets and the ability of edge contour feature extraction are good.

Enhanced cholera surveillance to improve vaccination campaign efficiency

Systematic testing for Vibrio cholerae O1 is rare, which means that the world’s limited supply of oral cholera vaccines (OCVs) may not be delivered to areas with the highest true cholera burden. Here we used a phenomenological model with subnational geographic targeting and fine-scale vaccine effects to model how expanding V. cholerae testing affected impact and cost-effectiveness for preventive vaccination campaigns across different bacteriological confirmation and vaccine targeting assumptions in 35 African countries. Systematic testing followed by OCV targeting based on confirmed cholera yielded higher efficiency and cost-effectiveness and slightly fewer averted cases than status quo scenarios targeting suspected cholera. Targeting vaccine to populations with an annual incidence rate greater than 10 per 10,000, the testing scenario averted 10.8 (95% prediction interval (PI) 9.4–12.6) cases per 1,000 fully vaccinated persons while the status quo scenario averted 6.9 (95% PI 6.0–7.8) cases per 1,000 fully vaccinated persons. In the testing scenario, testing costs increased by US$31 (95% PI 25–39) while vaccination costs reduced by US$248 (95% PI 176–326) per averted case compared to the status quo. Introduction of systematic testing into cholera surveillance could improve efficiency and reach of global OCV supply for preventive vaccination.

Socio-spatial equity analysis of relative wealth index and emergency obstetric care accessibility in urban Nigeria

BackgroundBetter geographical accessibility to comprehensive emergency obstetric care (CEmOC) facilities can significantly improve pregnancy outcomes. However, with other factors, such as affordability critical for care access, it is important to explore accessibility across groups. We assessed CEmOC geographical accessibility by wealth status in the 15 most-populated Nigerian cities.MethodsWe mapped city boundaries, verified and geocoded functional CEmOC facilities, and assembled population distribution for women of childbearing age and Meta’s Relative Wealth Index (RWI). We used the Google Maps Platform’s internal Directions Application Programming Interface to obtain driving times to public and private facilities. City-level median travel time (MTT) and number of CEmOC facilities reachable within 60 min were summarised for peak and non-peak hours per wealth quintile. The correlation between RWI and MTT to the nearest public CEmOC was calculated.ResultsWe show that MTT to the nearest public CEmOC facility is lowest in the wealthiest 20% in all cities, with the largest difference in MTT between the wealthiest 20% and least wealthy 20% seen in Onitsha (26 vs 81 min) and the smallest in Warri (20 vs 30 min). Similarly, the average number of public CEmOC facilities reachable within 60 min varies (11 among the wealthiest 20% and six among the least wealthy in Kano). In five cities, zero facilities are reachable under 60 min for the least wealthy 20%. Those who live in the suburbs particularly have poor accessibility to CEmOC facilities.ConclusionsOur findings show that the least wealthy mostly have poor accessibility to care. Interventions addressing CEmOC geographical accessibility targeting poor people are needed to address inequities in urban settings.

The Planetary Child Health & Enterics Observatory (Plan-EO): A protocol for an interdisciplinary research initiative and web-based dashboard for mapping enteric infectious diseases and their risk factors and interventions in LMICs.

Diarrhea remains a leading cause of childhood illness throughout the world that is increasing due to climate change and is caused by various species of ecologically sensitive pathogens. The emerging Planetary Health movement emphasizes the interdependence of human health with natural systems, and much of its focus has been on infectious diseases and their interactions with environmental and human processes. Meanwhile, the era of big data has engendered a public appetite for interactive web-based dashboards for infectious diseases. However, enteric infectious diseases have been largely overlooked by these developments. The Planetary Child Health & Enterics Observatory (Plan-EO) is a new initiative that builds on existing partnerships between epidemiologists, climatologists, bioinformaticians, and hydrologists as well as investigators in numerous low- and middle-income countries. Its objective is to provide the research and stakeholder community with an evidence base for the geographical targeting of enteropathogen-specific child health interventions such as novel vaccines. The initiative will produce, curate, and disseminate spatial data products relating to the distribution of enteric pathogens and their environmental and sociodemographic determinants. As climate change accelerates there is an urgent need for etiology-specific estimates of diarrheal disease burden at high spatiotemporal resolution. Plan-EO aims to address key challenges and knowledge gaps by making and disseminating rigorously obtained, generalizable disease burden estimates. Pre-processed environmental and EO-derived spatial data products will be housed, continually updated, and made publicly available for download to the research and stakeholder communities. These can then be used as inputs to identify and target priority populations living in transmission hotspots and for decision-making, scenario-planning, and disease burden projection. PROSPERO protocol #CRD42023384709.

Alternative targeting methods for social assistance programs: Evidence from Tunisia

AbstractSocial assistance programmes are crucial in alleviating poverty, reducing inequality, and addressing social exclusion. The efficacy of these programmes hinges on the precision and efficiency of their targeting methods. Governments, especially in developing countries, can enhance the impact of social assistance programmes and ensure equitable resource distribution by accurately identifying the right individuals or households. This paper proposes two approaches to targeting beneficiaries of social benefits in Tunisia, including cash transfers and healthcare programmes. The first approach, a Mixed Means Test, extends the Proxy Means Test model by integrating individual/household assessments with explicit geographical targeting methods. The second is a multidimensional targeting strategy that explicitly considers the various deprivations faced by the households. Utilising data from the 2015 National Survey on Household Budget, Consumption, and Standard of Living, our results indicate that the targeting performance of the Mixed Means Test surpasses existing programmes both nationally and regionally, notably minimising inclusion and exclusion errors in the poorest regions of Tunisia. However, the multidimensional targeting approach identifies a higher number of potential beneficiaries compared to the current selection process in Tunisia. Including these households in social programmes may be hindered by limited monetary resources and the country's financial constraints. To address this, the multidimensional targeting approach enables the categorisation of potential beneficiaries into three mutually exclusive and collectively exhaustive groups based on their degree of deprivation.

Absence makes the heart grow fonder: The interactive effect of crowding information and spatial distance on consumers’ patronage intention

Existing research has examined the influence of crowding on consumer behavior from an environmental cue perspective, with less attention given to its information cue function. To address the gap, based on construal level theory, this study investigated the impact of crowding information and geographic location on consumers' patronage intention. Through a pilot study and two experiments (wherein Study 1’s participants were recruited from China and Study 2's participants were recruited from the EU), this research reveals that crowding information and geographic location interactively influence consumers' patronage intention, with perceived scarcity driving this process. These findings contribute to the existing body of research on crowding and location-based service advertisements, and also offer valuable insights to companies on effectively utilizing crowding information and geographical targeting strategies in the design of advertisements.

Targeting Social Safety Nets: Evidence from Nine Programs in the Sahel

This paper analyzes household data from nine programs in the Sahel region using a harmonized approach to compare Proxy-Means Testing (PMT) and Community-Based Targeting (CBT) as conducted in practice, once geographical targeting has been applied. Results show that the targeting performance measured depends critically on the definition of the targeting objectives, share of beneficiaries selected, and indices used to evaluate targeting. While PMT performs better in reaching the poorest households based on per capita consumption, it differs little from CBT, random or universal selection when distribution-sensitive measures are employed, or when food security is used as the welfare metric. Administrative costs associated with targeting represent only a small share of budgets. Results emphasize the importance of studying programs as implemented in practice instead of relying on simulations of targeting performance. They also suggest that PMT and CBT contribute little to poverty or food insecurity reduction efforts in poor and homogeneous settings.

Assessing climate change vulnerability in Canadian marine conservation networks: implications for conservation planning and resilience

Marine protected areas (MPAs) are critical in safeguarding biodiversity and ecosystem functions under climate change. The long-term effectiveness of these static conservation measures will depend on how well they represent current and future ocean changes. Here, we use the Climate Risk Index for Biodiversity to assess the vulnerability representation of marine ecosystems within the Canadian marine conservation network (CMCN) under two divergent emissions scenarios. We found that MPAs best represent climate vulnerability in Atlantic Canada (85% representativity overall, and 93% in the Gulf of Saint Lawrence under low emissions), followed by the Pacific (78%) and Arctic (63%; lowest in the Eastern Arctic (41% under high emissions) regions). Notably, MPAs with lower climate vulnerability are proportionally overrepresented in the CMCN. Broad-scale geographic targets employed in the Scotian Shelf-Bay of Fundy network planning process achieve over 90% representativity of climate vulnerabilities, underscoring the importance of ensuring habitat representativity and geographic distribution in conservation planning to enhance climate resilience, even if not explicitly prioritized. Moving towards Canada’s target to protect 30% of its waters by 2030, prioritizing representativity and designation of MPAs in currently underrepresented climate-vulnerable regions may be crucial to enhancing the resilience of the CMCN amidst an ever-changing climate.

Anti-Toxoplasma gondii Antibodies in European Residents: A Systematic Review and Meta-Analysis of Studies Published between 2000 and 2020.

Toxoplasmosis has a major impact on animal and public health. Information regarding the seroprevalence of human Toxoplasma gondii infections from a European perspective has not yet been compiled to date. Thus, the present review summarized available resident data from the period 2000-2020. The overall seroprevalence of anti-T. gondii IgG was 32.1%, with great variability between countries (n = 30). The subgroup analysis identified different pooled prevalence data depending on the geographic area (p < 0.0001), target population (p = 0.0147), and serological diagnosis assays used (p = 0.0059). A high heterogeneity (I2 = 100%, p < 0.001; Q = 3.5e+05, d.f. = 135, p < 0.001) and degree of publication bias (Egger's test = 6.14, p < 0.001) were observed among the 134 studies considered. The occurrence of anti-T. gondii IgM, which was reported in 64.7% of studies, reached a pooled seroprevalence of 0.6%. In addition, among the eight main risk factors identified, "contact with soil", "consumption of undercooked beef", and "intake of unwashed vegetables" were the most significantly associated with infections. The fact that one-third of the European population has been exposed to T. gondii justifies extra efforts to harmonize surveillance systems and develop additional risk-factor analyses based on detailed source attribution assessment.

Rising food prices and poverty in Pakistan.

An upsurge in global food prices in 2008 led to significantly higher food prices across the developing world. Global commodity prices have since declined but still remain volatile, but at the same time local food prices remain high in many countries. This study examines the potential impacts of the rise in food prices on poverty-income based poverty and calorie-based poverty- focusing on Pakistan, and its rural and urban areas. For this purpose, we used HIES data collected in three waves 2005-06, 2007-08 and 2010-11. Price elasticities are computed using binary Logistic regression method. The study results show that price of wheat, rice, milk, meat, fruit, pulses appear to distinguish the status of a household. Price elasticities shows that urban households are hit harder than rural households in calorie-poverty model. Overall, rising food prices are likely to lead higher poverty in Pakistan, as the negative impact on net consumers outweighs the benefits to producers. Therefore, effective strategy for eliminating poverty is far more concerned with price increases. Safety net programs can be more effective, but geographic targeting and other investments to strengthen safety nets are necessary to ensure that fewer people are affected by future crises. Government policies oriented towards relieving the food price pressure on the Pakistani poor should aim at lowering the prices of wheat, rice, eggs, oil, milk, and chicken.