Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning

Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning Valentine Golden Ghanem This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6745789/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background: Despite the national decline in cases, Ghana continues to experience significant regional disparities in HIV/AIDS incidence due to inequities in social factors, including education, stigma, HIV awareness, and access to ART. Such inequalities are often hidden in national statistics, which reduce the accuracy of public health measures. Methods: A unified regional dataset was created using GHS, GAC, MoH, GSS, UNAIDS, and World Bank data from 2000 to 2022, which combined sociobehavioral and health infrastructure factors. Using spatial clustering and choropleth mapping, high-incidence areas were identified and regional vulnerability was assessed. Random Forest and XGBoost analyzed key structural features via SHAP values, PDPs, and counterfactual simulations. Results: Spatial clustering and choropleth mapping revealed a spike in HIV incidence in the Greater Accra, Ashanti, and Central regions. This pattern was linked to factors such as high urbanization, social stigma, and unequal access to ART. Clustering identified three main regional typologies based on the health indicators. SHAP and PDP analyses indicated that HIV incidence declined abruptly when educational access exceeded 60%, or ART coverage surpassed 45%. Residual mapping suggested possible under -reporting of HIV incidence or latent socio-structural buffers in rural areas. A 10% increase in education or awareness reduced the incidence by up to 16% in the high-burden regions . Conclusions: In Ghana, HIV/AIDS incidence is influenced by access to healthcare and various spatial and social disparities. This study revealed the importance of creating policies that support education, reduce stigma, and ensure equal access to ART across different regions. Through explainable machine learning, the influence of behavioral and geographic factors on Ghana’s HIV incidence was examined. HIV/AIDS Ghana spatial epidemiology sociobehavioral determinants explainable machine learning public health disparities ART coverage stigma education SHAP Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 BACKGROUND The incidence of HIV/AIDS in Ghana exhibits heterogeneous impacts across regions and populations rather than a uniform distribution. Although the national HIV prevalence is less than 2% [ 1 ], regional disparities in the number of cases and access to healthcare services remain. While the national Human Immunodeficiency Virus (HIV) prevalence dropped from 3.1% in 2004 to 2.4% in 2016 [ 1 ], some districts, such as Lower Manya Krobo Municipality (LMKM), still have high incidence rates, as shown by the 5.64% reported in 2018 [ 2 ]. Despite being highly urbanized, the Greater Accra and Ashanti regions still have an unusually high HIV prevalence [ 3 ], implying that long-term public health interventions did not yield uniform regional epidemic outcomes. Many researchers in sub-Saharan Africa (SSA) have found that HIV vulnerability is influenced by complex socio-behavioral factors such as education, awareness, stigma, and gender roles. Higher educational attainment among Ghanaian women correlates with increased HIV testing and treatment uptake, whereas young rural men remain persistently underserved in diagnosis rates, underscoring demographic disparities in healthcare access [ 4 ]. The stigma and legal barriers faced by Men who have Sex with Men (MSM) in Ghana prevent them from accessing services, thus exacerbating regional disparities in HIV outcome [ 5 ]. These discrepancies emphasize the need for spatially targeted interventions to address granular inequities. A recent analysis of Demographic and Health Survey (DHS) data using spatial interpolation found that subregional testing in the western region was as low as 5% in some places and over 30% in others [ 6 ]. Regional variations in disease prevalence are often obscured by national averages, which may result in inappropriate policies and resource misuse . Spatial epidemiology helps to uncover and target areas where HIV risk is hidden. Ghana’s HIV surveillance system still relies on administrative reports that lack detailed geographic information and exclude s behavioral factors. Traditional regression models used in HIV policy forecasting often assume spatial independence and are poorly suited for capturing the multidimensional, nonlinear interactions that drive regional epidemics. Therefore, many high-risk populations remain underserved, whereas programmatic responses continue to be overly centralized. New developments in spatial analysis and interpretable Machine Learning (ML) can help solve these issues. SHapley Additive exPlanations (SHAP) and Partial Dependence Plot (PDPs) can be used to study the role of factors such as education, ART coverage, and stigma in HIV incidence and transmission. When paired with clustering and choropleth techniques, the ML results can make interventions more equitable by tailoring them to different areas. Few studies in Ghana have attempted to combine these approaches to examine how both geography and behavior influence HIV incidence. Moreover, few studies have examined how policy changes in HIV awareness or education may disproportionately affect regions. This study aimed to address this issue by directing its analysis to the spatial and behavioral factors that impact the incidence of HIV/AIDS. Using ecological modeling, this study merges spatial analysis with explainable ML to guide precise public health strategies for combating HIV/AIDS incidence in Ghana. METHODS 3.1 Study Design and Rationale This study used a retrospective ecological cross-sectional approach to analyze how socioeconomic and spatial factors affect the incidence of HIV/AIDS in Ghana between 2000 and 2022. The framework focuses on explaining HIV incidence through spatial, structural, and behavioral factors using machine learning models to support, but does not replace this explanation. 3.2 Study Area and Units of Analysis The study was conducted across ten legacy administrative regions to maintain consistency in the data before and after the 2018 redistricting. Monthly data were gathered from 2000 to 2022 , providing a panel dataset of 9,792 observations (12 months × 23 years × 10 regions). 3.3 Data Sources and Variable Construction Data were collected from national and international organizations. The Ghana Health Service (GHS) and Ghana AIDS Commission (GAC) provided data on HIV incidence, Antiretroviral Therapy (ART) coverage, and HIV testing coverage. The Ghana Statistical Service (GSS), Demographic and Health Surveys (DHS), and UNAIDS provided data on educational access, stigma index, awareness index, condom use rate, female literacy, and youth unemployment. Regional boundaries in GeoJSON format were obtained from geoboundaries.org. The outcome variable was the number of new HIV/AIDS cases per month per 100,000 individuals. The explanatory variables were divided into four categories: socio-behavio ral (education access, awareness, stigma), demographic (female literacy, unemployment, urbanization), biomedical (ART coverage, testing coverage, TB incidence), and spatial (region ID, centroids, and clusters). 3.4 Spatial Data Harmonization The new 16 administrative regions of Ghana were consolidated with the original ten using a region-code linking approach. A GeoJSON file from the geoboundaries.org database was used to link each of the ten regions to its matching spatial polygon. The geographic center of each region was found using GeoPandas in the Python programming language, enabling subsequent clustering and mapping. In addition, a spatial adjacency matrix was built using the Python Spatial Analysis Library (PySAL) Queen contiguity algorithm, which identifies neighbors based on common boundaries. This spatial weight matrix was then used to assess spatial autocorrelation using Global Moran’s I and Local Indicators of Spatial Association (LISA). These techniques enable region-level boundaries to be linked with epidemiological data by matching the ISO-coded region IDs. 3.5 Spatial and Behavioral Analysis HIV incidence and ART coverage maps were developed using Folium and Altair to identify places where social stigma and illiteracy overlap. Using K-means clustering with three clusters, this study identified different patterns across the country for education al access, ART coverage, stigma, and awareness. The elbow method was used to determine the optimal number of clusters, while hierarchical clustering with Ward’s linkage was used to ensure that the results were robust. Global Moran’s I was used to identify the overall clustering pattern, while Local Moran’s I (LISA) was used to identify hotspots and coldspots of HIV incidence. Model residuals were mapped to identify regions that perform ed better or worse than expected, with values exceeding ± 1.5 indicating potential structural inconsistencies. The relationship between HIV infection and key variables (HIV awareness, ART coverage, educational access, stigma index, and condom use) was explored using boxplots and scatterplots. 3.6 Data Preprocessing Temporal filtering of retained data from 2000 to 2022. Missing values were imputed using the K-nearest neighbor method (K = 5) based on correlated variables such as urbanization and facility density. Indicators for condom use and HIV awareness were smoothed using 3-month rolling averages. To mitigate the effect of outliers, the winsorizing technique was applied at the 1st and 99th percentiles. All variables were normalized using Z-scores for the modeling and clustering steps. 3.7 Interpretable Machine Learning Analysis An 80/20 temporal split was used to train the model. Data from 2000 to 2019 were used for training, whereas data from 2020 to 2022 were used for testing. Random Forest and XGBoost regressor models were mainly used for explanatory analysis rather than for outcome prediction. SHAP values were used to interpret the importance of each predictor, and PDPs were used to identify any nonlinear changes in the data. A counterfactual simulation demonstrated that a 10% increase in education and HIV awareness could significantly reduce HIV incidence. The Grid Search with Cross-Validation (GridSearchCV) method was used for hyperparameter tuning, and the model performance was evaluated using R², RMSE, MAE, and MAPE. 3.8 Streamlit Dashboard Deployment A dashboard app was developed using Python with HyperText Markup Language (HTML) and Cascading Style Sheet (CSS) elements. The app was deployed via Streamlit to enable the interactive exploration of HIV incidence maps, SHAP scores, cluster patterns, and counterfactual forecasts. The app is version controlled through GitHub and archived on Zenodo under DOI: 10.5281/zenodo.15292209 . The app can be publicly accessed at https://dashboardapppy-3ryuuaxnlmrsrrkqoxpcfw.streamlit.app . RESULTS 4.1 Geographic distribution of HIV incidence Choropleth mapping revealed pronounced spatial disparities in HIV incidence across the ten administrative regions of Ghana. Regions such as Greater Accra, Ashanti, and Central consistently recorded the highest incidence rates , surpassing 220 new HIV cases per 100,000 people annually (Figure 1 ). In contrast, the Upper East, Northern, and Volta regions had lower incidence levels, averaging below 140 per 100,000, although recent data indicate increasing trends in some of these areas. These geographic variations persisted over the period 2000–2022 , suggesting that structural and behavioral inequities have remained entrenched. Figure 1 illustrates this trend through a regional choreopleth map of the average incidence rates over the study period, thereby capturing the temporal stability of these disparities. 4.2 Regional Clustering by Sociobehavioral Profiles To better understand the heterogeneity in the incidence patterns, unsupervised machine learning (K-means clustering, K = 3) was employed to classify regions into three socioepidemiological clusters on the basis of the tandardized values of education access, ART coverage, HIV awareness, and stigma index. The clustering algorithm grouped Greater Accra, Ashanti, and Central into Cluster A, characterized by a high HIV burden alongside high urbanization, ART coverage, access to education, and relatively elevated stigma index scores. Cluster B, composed of the Brong-Ahafo, Western, and Eastern regions, presented intermediate incidence rates and a mixture of socio-behavio ral profiles, and was hence classified as transitional. Cluster C, which included the northern, upper -east, and upper-west regions, was characterized by a lower incidence, but also lower levels of ART access, education, and HIV awareness, combined with higher stigma indices. These observations are supported by Table 1 , which details the regional-level HIV and TB averages, and Table 2 , which summarizes the regional levels of education access and urbanization. Regional typologies are shown in Fig. 2 . 4.3 Sociobehavioral Correlations with HIV Incidence Bivariate correlation analysis demonstrated strong and statistically significant associations between HIV incidence and several key socio -behavio ral predictors. Access to education was positively correlated with HIV incidence (r = 0.71), indicating a higher incidence in regions with greater coverage of formal education. This seemingly paradoxical correlation may be explained by differential case detection ; better-educated regions are likely to have higher testing penetration, case ascertainment, and surveillance infrastructure, which can inflate the reported incidence despite potentially lower actual transmission. While counterintuitive at first glance, further analysis suggests that this relationship may be driven by higher levels of testing, urbanization, and surveillance intensity in better-educated regions. Similarly, both the urbanization level and the HIV awareness index were positively correlated with incidence (r = 0.65 and r = 0.59, respectively), reinforcing the notion that areas with more infrastructure and outreach services are more likely to detect and report cases. Condom use rates and the regional stigma index showed complex patterns. While condom use was moderately associated with reduced incidence, stigma appeared to correlate with underreporting and reduced service uptake, especially in lower-burden regions where disclosure remains a challenge. These patterns became particularly salient when urban and rural geographies were compared. Urbanized regions, such as Greater Accra and Ashanti, despite having high education access and ART coverage, also recorded the highest incidence rates. This paradox may be explained by intensified surveillance, elevated partner concurrency, transactional sex, and increased network density. In contrast, rural settings, such as the Lower Manya Krobo Municipality (LMKM) in the Eastern Region, demonstrated localized hyperendemicity. Agormanya, a sentinel site within the LMKM, reported an HIV prevalence of 19.2% , among the highest in Ghana, despite the region’s relatively modest health infrastructure (Ocran, 2022; Dias, 2021). These rural–urban contrasts align with the SHAP and PDP outputs from the predictive models, which ranked urbanization, education al access, and stigma among the most influential variables ( Figs. 4 – 5 ). Evidence suggests that regional differences in the HIV burden are not binary but instead shaped by layered contextual factors, including behavioral norms, population mobility, stigma gradients, and access visibility. Figure 3 presents scatterplots illustrating the relationships between HIV incidence and selected predictors, and Table 3 summarizes the strength and direction of these associations using Pearson correlation coefficients. Table 4 provides the background on the quality and transformation of these variables. 4.4 SHAP-Based Interpretation of Structural Predictors To further explore the drivers of HIV incidence, random forest and XGBoost models were trained on the harmonized dataset and interpreted by Shapley Additive Explanations (SHAP) values. The SHAP summary plot ranks the features based on their mean absolute contribution to the model predictions. ART coverage, educational access, HIV awareness, urbanization, and TB co-infection were the most significant predictors. Several threshold effects were observed. Notably, regions with an education index above 0.6 experienced a steep increase in the observed incidence, possibly reflecting increased detection due to improved health literacy and testing uptake. Conversely, ART coverage exceeding 45% was associated with a substantial decline in the incidence, highlighting the preventive impact of treatment-as-prevention approaches. HIV awareness levels above 70% exhibited diminishing returns, suggesting that beyond a certain threshold, increased awareness alone did not yield further reductions in transmission. Figure 4 displays the global SHAP summary plot, whereas Fig. 5 offers detailed SHAP dependence plots illustrating how changes in education and ART coverage influenced the predicted incidence across regions. Table 5 summarizes the SHAP-based rankings and explanations. 4.5 Counterfactual Simulation: Impact of Modifying Key Predictors A counterfactual analysis was performed using the trained XGBoost model to simulate the potential effects of policy interventions. A hypothetical 10% increase in either HIV awareness or educational access was applied uniformly across all regions. The results revealed that high-burden regions such as Greater Accra, Ashanti, and Western benefitted the most, with projected reductions in incidence ranging from 13–16.3%. The transitional and lower-access regions demonstrated modest projected declines between 7% and 10%. Notably, the simulations revealed that regions with lower baseline levels of education or awareness experienced the greatest relative gains, indicating greater elasticity of response. These findings support the idea that targeted structural improvements, particularly in educational access and public health awareness, can yield meaningful reductions in HIV burden when directed toward vulnerable regions. These counterfactual results highlight the policy sensitivity of behavioral determinants in Ghana’s HIV response. Importantly, they illustrate that the effectiveness of interventions such as education and awareness is not uniform but context-dependent, amplified in transitional zones with mid-level infrastructure, and underutilized testing. This confirms a “diminishing returns” pattern, where high-incidence urban centers with saturated services gain less from blanket messaging, whereas transitional or underresourced regions respond more elastically to marginal investment. Thus, counterfactual simulation does not merely estimate statistical change; it functions as a strategic tool for public health targeting, guiding scalable, cost-efficient investments, where they are likely to yield the greatest marginal benefit. These findings are grounded in the predictor distributions described in Table 2 and SHAP simulation logic outlined in Table 5 . Figure 6 shows the projected changes in incidence across regions. 4.6 Residual Mapping and Latent Factors Residual analysis comparing the predicted and observed incidence revealed spatial patterns, suggesting that latent factors were not captured in the model. The central and eastern regions exhibited systematic underprediction, possibly indicating the presence of protective community norms, localized prevention programs, or reporting gaps that were not accounted for in the dataset. This discrepancy may reflect unmeasured behavioral resilience or underdocumented public health interventions. Conversely, the Greater Accra and Western regions showed consistent overprediction, which could signal higher-than-expected transmission dynamics or limitations of the model in capturing highly mobile populations, transactional sexual behaviors, or complex social and sexual network dynamics. These insights are visualized in Fig. 7 , which maps the regional distribution of the average residuals. Thus, residual analysis serves as a diagnostic tool, guiding future efforts to refine both surveillance and predictive modeling. DISCUSSION 5.1 Principal findings and interpretations The study applied ecological machine learning and spatial clustering to investigate the socio -behavio ral and structural determinants of HIV incidence across ten administrative regions of Ghana. According to the findings, HIV incidence is highest in Greater Accra, Ashanti, and some areas in the Central and Eastern regions, which have more schools, larger towns, and greater access to ART. In addition , these results mirror a broader phenomenon in sub-Saharan Africa (SSA), where highly urbanized areas tend to have a higher rate of HIV among youth and young women, despite having better healthcare [ 7 , 8 ]. These urban "hotspots" often align with zones of heightened economic activity and risky sexual behavior [ 8 ]. Paradoxically, these urban areas still had high incidence rates. SHAP and PDP visualization s in this study suggest that while ART coverage of over 45% is negatively correlated with HIV incidence rates (Figs. 4 – 5 ), this trend was not significant in urban areas. ART saturation may reduce marginal gains unless accompanied by behavioral shifts [ 9 ]. This is in agreement with studies showing that biomedical interventions alone are insufficient without complementary behavioral or structural shifts, especially among high-risk female populations, such as bar workers [ 10 ]. Figure 2 (Cluster A: high burden, high access; Cluster B: transitional; Cluster C: low burden, low access) reflects the ideas proposed by previous studies [ 6 , 11 ], demonstrating that HIV outcomes are shaped not only by infrastructure but also by layered behavioral, economic, and spatial inequalities. 5.2 Urban–Rural Inequities and Behavioral Dynamics Although urban areas such as Accra demonstrate higher ART coverage and testing rates, they paradoxically sustain an elevated incidence. This urban-rural paradox mirrors broader regional findings where urban youth, particularly girls aged 15–24, face higher HIV risks due to mobility, economic survival strategies, and social vulnerabilities [ 7 , 8 ]. SHAP outputs (Figs. 5 A- 5 D) revealed that this mismatch arises from high-risk behaviors, population mobility, and structural gaps such as inconsistent education programming. In contrast, rural zones such as Lower Manya Krobo (LMKM) report hyper-local epidemics—Agormanya’s 19.2% prevalence [ 2 ]—despite the regional averages being lower. Such local disparities reflect "micro-epidemic" dynamics observed across Eastern and Southern Africa, where high-prevalence pockets are not necessarily aligned with broader regional averages [ 8 ]. Tables 1 , 2 , and 4 provide supporting evidence of these structural differences. This spatial vulnerability reflects the underlying behavioral and structural vulnerabilities. Male reluctance toward HIV testing and under-targeted adolescents have been observed as drivers of under-diagnosis in rural zones [ 6 ]. Similarly, Gu et al. (2021) found that peer influence and risk perception were critical barriers to adolescent HIV testing, even in well-serviced urban zones [ 12 ]. These findings are consistent with our model residuals (Fig. 7 ), which were under -predicted in the Eastern and Central Regions, potentially because of stigma-suppressed disclosure [ 13 ] or local resilience factors. Educational access and HIV awareness (SHAP dependence plots, Fig. 5 A & 5 D) only reduced the incidence above the 0.6 threshold, This resonates with findings that general awareness rarely leads to preventive action unless paired with structural empowerment, particularly among populations such as female bar workers, who often report high HIV awareness but lack negotiating power for condom use [ 10 ]. Moreover, some scholars argue that general awareness (~ 98%) often does not translate into comprehensive knowledge [ 1 ]. This supports a threshold-based policy: boost ing access in undeserved areas, where gains would be exponential. 5.3 Simulation of Structural Levers and Policy Impacts Counterfactual modeling demonstrated that a + 10% increase in HIV awareness or education al access can yield incidence reductions of up to 16.3% in high-burden regions ( Fig. 6 ). This observation aligns with real-world results from initiatives such as the Determined, Resilient, Empowered, AIDS-free, Mentored, and Safe (DREAMS) program, which showed up to a 40% reduction in HIV incidence in targeted adolescent groups when structural and behavioral components were integrated [ 7 ]. The observed responsiveness of the model to education-based interventions underscores the need for structural tailoring. For instance, Dambach et al. (2020) highlighted that, in bar settings, even moderate wage improvements or access to sexual health counseling could shift behavior away from transactional sex. These are scalable levers that can complement national awareness campaigns [ 10 ]. The SHAP simulations (Figs. 5 – 6 ) also demonstrated that this effect (education boost reduces HIV in hotspots) is most pronounced in transitional regions, where the baseline indicators are moderate. These m odel-derived insights correspond with the feature importance results in Table 5 and data validation metrics in Table 3 , and support the case for a paradigm shift toward non-biomedical drivers in HIV prevention. These simulations reinforce d the need for differentiated programming. Regions such as Ashanti and Western responded sharp ly to educational improvements. These findings echo those of a 2021 study that linked female education and literacy programs to durable HIV prevention outcomes [ 14 ]. Such evidence also support s the findings of previous research from 2021, which advocated for region-targeted interventions in SSA, highlighting that one-size-fits-all strategies are inefficient and ethically problematic in heterogeneous epidemics [ 11 ]. These findings suggest that public health investments in educational infrastructure and awareness campaigns could have the greatest impact when strategically allocated to transitional or undeserved regions. In effect, simulations serve as policy scenario-testing tools, enabling decision-makers to visualize tangible returns on specific structural reforms. 5.4 Comparison with Prior Literature The findings from this investigation are broadly aligned with those of prior studies, but introduce new granularity. While past studies [ 1 , 6 ] have highlighted spatial disparities in HIV testing, this study quantifies behavioral thresholds and identifies saturation effects. Notably, the nonlinear impact of education—initial increases in incidence due to testing bias, followed by later declines—has not been previously modeled in Ghana. A policy on abstinence-only education in LMKM contradicts the Ministry of Health’s comprehensive messaging, creating mixed narratives that impede behavioral change [ 2 ]. These contradictory curricula are rarely captured in national datasets, but they significantly shape the local epidemic trajectories. Unlike traditional regression-based models [ 15 ], The SHAP-driven ML analysis (Figs. 5 A– 5 D) in this study uncovered nonlinear and threshold effects across the structural predictors. While it does not model spatial lag explicitly, the feature behavior patterns provide richer insight than models that assume linear, independent effects. 5.5 Study Limitations This study has several limitations that should be considered when interpreting the findings . First, the use of an ecological design based on region-level aggregates introduces the risk of an ecological fallacy. As a result, the associations observed between regional predictors and HIV incidence cannot be assumed to apply to individuals within th ese regions [ 16 ]. While this is valid, recent spatial studies such as Bulstra et al. (2020) used similar regional aggregation techniques and were still able to identify robust patterns of micro-epidemics, suggesting that the method retains analytical value even if individual-level inferences are limited [ 8 ]. Although K-Nearest Neighbors (KNN) imputation was employed to address missing data (Table 3 ), the assumption that data were missing at random may not hold for certain variables, particularly sensitive behavioral indicators such as condom use. Previous studies [ 17 , 18 ] underscore d the potential for social desirability bias in such self-reported b ehaviors, which could distort the accuracy of the imputed values. F urthermore, t his limitation is well justified, especially in light of studies such as Dambach et al. (2020), who documented social desirability bias in self-reporting among female bar workers, resulting in significant under-reporting of risky sexual behaviors [ 10 ]. Furthermore, the spatial aggregation process, in which Ghana’s 16 newly demarcated regions were merged into the ten legacy administrative zones, may have obscured intraregional disparities. This could result in the underestimation of localized epidemics, especially in emerging high-risk zones not historically identified as hotspots [ 6 ]. The study also lacked the ability to control for latent confounders, such as transactional sex, economic migration, and displacement due to infrastructure development, such as dam construction. These factors, although not captured in the current dataset, are known to influence HIV transmission patterns, particularly in high-burden districts, such as Agormanya [ 2 ]. Moreover, this limitation is critical, as other studies have highlighted how mobility and economic factors drive risk, particularly among informal labor sectors such as market traders and bar workers [ 10 , 12 , 19 ]. In regions with infrastructure-induced displacement, HIV burden may be significantly underestimated if these transient populations are excluded. Furthermore,the omission of key populations, such as sex workers and mobile traders, may lead to a structural under-diagnosis in high-burden zones. Several studies have reported that these groups often operate outside routine surveillance systems and require targeted outreach strategies [ 12 , 20 ]. Their exclusion weakens the generalizability of the current findings and limits their predictive sensitivity for areas experiencing rapid urban growth or seasonal migration. 5.6 Policy and Programmatic Implications The se findings highlight the urgent need for a more granular, equity-focused approach to HIV prevention and control in Ghana. Moving beyond national averages, the regional stratification observed in this study calls for precis e public health strategies that are responsive to the unique sociostructural profiles of each region. First, there is a clear need to expand community-based HIV testing services, particularly for men and adolescents who continue to exhibit lower testing rates. Gu et al. (2021) showed that adolescent testing uptake can be significantly improved through school-based and peer-driven interventions, particularly when stigma and peer influence are addressed simultaneously [ 12 ]. Mobile testing units, home-based testing kits, and self-testing options may help close this diagnostic gap between under-served northern and rural zones [ 6 ]. These interventions should be prioritized in areas where the testing prevalence is below the threshold values identified in the SHAP modeling framework (Fig. 5 D). Second, policy realignment is necessary in regions in wh ich abstinence-only education continues to dominate. In Lower Manya Krobo Municipality, for example, policy contradictions between the Ghana Education Service and the Ministry of Health have led to mixed messaging between educators and students [ 2 ]. This mirrors the structural misalignment reported by Sambah et al. (2020), where conflicting institutional narratives on youth sexuality undermined HIV prevention among female students [ 21 ]. Integrating comprehensive, evidence-based sex education, which includes condom use, partner reduction, and biomedical prevention, is essential for curbing localized epidemics. Moreover, cross-border trading corridors—identified as risk zones for mobile women traders—should incorporate livelihood support with HIV prevention messaging and services [ 11 ]. However, Cane et al. (2021) argue d that livelihood support is insufficient unless paired with efforts to address gendered power imbalances that sustain women's vulnerability to coercion and HIV risk [ 7 ]. Resource allocation decisions should also be informed by SHAP-guided clustering (Fig. 2 ) and partial dependence plots (Fig. 4 ), which help to identify “transitional” regions with moderate coverage but high responsiveness to interventions. This data-driven targeting aligns with the calls for fine-scale geospatial mapping seen in Bulstra et al. (2020), who emphasized that localized epidemic zones often escape national policy radar and require precision prevention approaches [ 8 ]. Finally, implementing SHAP-informed or AI-assisted programming assumes a digital infrastructure and analytic capacity , which may be lacking in rural health systems. As Owusu et al. (2020) highlight ed, the gap in digital literacy and uneven access to data platforms could hinder the practical integration of these tools, reinforcing existing inequities if not addressed through training and decentralization efforts [ 22 ]. CONCLUSION 6.1 Conclusion This study analyzed the influence of spatial and socio -behavioral factors on HIV/AIDS incidence in Ghana using a combination of ecological modeling, spatial clustering, and explainable machine learning techniques. It was shown that both biomedical factors , such as ART availability, and socio-structural characteristics, such as education, awareness, stigma, and urban density, contribute to regional variations in HIV incidence. The results revealed three distinctive region-level groups (Fig. 2 ) characterized by varying levels of HIV risk and available resources. These analyses collectively reveal that HIV risk in Ghana exhibits distinct spatial and contextual variations. Areas with high HIV prevalence, such as the Greater Accra, enjoy better access to resources but are also exposed to greater behavioral risk. The lower incidence in rural areas could be attributed to either genuine safety or lack of reporting (Fig. 1 ). The simulations reveal ed that targeted social policy interventions could substantial ly impact HIV incidence. Increasing education or awareness by 10% in high-incidence areas could reduce new infections by as much as 16% (Fig. 6 ). These results highlight the importance of structural interventions for tackling HIV epidemic s. Investing in education and awareness, particularly in areas experiencing a transition from low to moderate risk, has been shown to have a greater impact on reducing the incidence than increasing biomedical interventions. These findings support the reorientation of policies to address the root causes of HIV infections. This study presents a methodology that enables researchers and policymakers to analyze spatial disparities, tailor interventions to specific regions, and predict the public health benefits of evidence-based social policies. This advocates the adoption of regionally specific, evidence-based, and socially responsive interventions. 6.2 Policy Recommendations The results highlight the importance of regionally specific HIV policies in Ghana. Improving education and awareness by small margins could lead to a 16% decrease in HIV incidence in areas undergoing economic and demographic transformation s (Fig. 6 ). Eastern, and Brong-Ahafo. These regions are particularly amenable to behavioral interventions, indicating that efforts such as HIV education, peer support, and school-based initiatives should receive greater attention. Communication should be culturally sensitive and should address misunderstandings and social barriers. Areas such as Greater Accra and Ashanti face a conundrum as they have high ART coverage, but persistently high HIV incidence. The incidence of HIV remains elevated despite high ART uptake. SHAP dependence plots ( Fig. 5 A- 5 D) suggest that this may be due to persistent behavioral risks and saturation effects. Addressing behavioral factors, stigma, and network-based transmission is necessary to improve HIV control in these areas. Outreach to mobile youth, MSM, and sex workers should be a crucial component of prevention efforts. Approaches could include expanding Pre-Exposure Prophylaxis (PrEP) availability, conducting mobile testing, and running digital campaigns that leverage behavioral science to encourage participation and compliance. Tools such as SHAP and geospatial clustering (Figs. 4 – 5 and Fig. 2 ) should be formally integrated into the decision-making processes of regional health directorates. These dashboards help inform planning and enable timely identification of the increasing risk. Integrating transparent ML outputs into district-level decisions improves transparency and responsiveness. HIV services should be closely linked to maternal health, TB, and gender-based violence programs, particularly in under-resourced cluster C areas (Fig. 2 ). A coordinated effort involving public, private, and donor resources is required to address geographical disparities and ensure lasting reforms. Applying preemptive, data-driven, and tailored approaches in each region is crucial for achieving an equitable HIV reduction. Abbreviations AIC: Akaike Information Criterion AIDS: Acquired Immunodeficiency Syndrome AI: Artificial Intelligence API: Application Programming Interface ART: Antiretroviral Therapy CI: Confidence Interval CSS - Cascading Style Sheets CSV: Comma-Separated Values CV: Cross-Validation DAG: Directed Acyclic Graph DHS: Demographic and Health Survey DREAM: Determined, Resilient, Empowered, AIDS-free, Mentored, and Safe GAC: Ghana AIDS Commission GHS: Ghana Health Service GIS: Geographic Information System GridSearchCV: Grid Search with Cross-Validation GSS: Ghana Statistical Service HDX: Humanitarian Data Exchange HIV: Human Immunodeficiency Virus HTML - HyperText Markup Language KNN: K-Nearest Neighbors LISA: Local Indicators of Spatial Association LMKM: Lower Manya Krobo Municipality LSTM: Long Short-Term Memory MAE: Mean Absolute Error MAPE: Mean Absolute Percentage Error MAR: Missing At Random ML: Machine Learning MoH: Ministry of Health MSM: Men who have Sex with Men OR: Odds Ratio ORCID: Open Researcher and Contributor ID PCA: Principal Component Analysis PDP: Partial Dependence Plot PrEP: Pre-Exposure Prophylaxis PySAL: Python Spatial Analysis Library QGIS: Quantum Geographic Information System R²: Coefficient of Determination RMSE: Root Mean Square Error SDG: Sustainable Development Goal SHAP: SHapley Additive exPlanations SHAP-ML: SHAP-based Machine Learning SSA: Sub-Saharan Africa STROBE: Strengthening the Reporting of Observational Studies in Epidemiology SVR: Support Vector Regressor SVM: Support Vector Machine TB: Tuberculosis UNAIDS: Joint United Nations Programme on HIV/AIDS WHO: World Health Organization Zenodo: Open-access data repository platform Declarations Ethical approval or consent was not required as this study used only publicly available data. Publicly available aggregated data were analyzed. Personally identifiable information and samples collected from individuals were excluded. Consent for publication: Not applicable. This study did not include any personal information. Availability of data and materials: All materials used in this study were made openly accessible at the Zenodo repository under a CC-BY 4.0 license. The Zenodo archive contains detailed documentation, metadata, and replicability-verification files. There were no limitations to the use of the data provided. All necessary files and information required for reproducing the analysis are included in the Zenodo repository. Cleaned regional-level dataset (ghana_infectious_disease_model_dataset_cleaned.csv) Geospatial boundary files (GHA_10regions_merged_final.geojson) Model code and forecasting Script Documentation and SHA-256 verification Data were gathered from publicly available national reports and statistical summaries provided by organizations such as the GHS, GAC, MoH, GSS, UNAIDS, and the World Bank. The data were carefully cleaned, organized, and prepared for forecasting. This study did not use individual-level human data. The analysis employed regional-level data for forecasting. Competing interests: The author declares no competing interests. Funding: The author did not receive any financial support for this study. Authors' contributions: VG contributed to all aspects of the study, including the conceptualization, methodology, data collection and analysis, software development, validation, visualization, and drafting and editing of the manuscript. Acknowledgments: The authors gratefully acknowledge the contributions of the Ghana Health Service, Ghana AIDS Commission, Ghana Statistical Service, and the Humanitarian Data Exchange (HDX) platform for sharing valuable epidemiological and demographic datasets that enabled the advancement of this research. I acknowledge the efforts of individuals who share open geospatial data through the geoboundaries’ platform. This research was dedicated to the memory of my sister, Imelda Farr, who motivated me to pursue this academic goal. Authors' information: VG is a Biomedical Scientist working at the Medical Department of the Cocoa Clinic in Accra, Ghana. He earned an MSc in Data Science from the University of East London and is currently pursuing an MSc in Public Health through distance learning at the University of Suffolk. He is interested in developing models for infectious diseases, making predictions using epidemiological data, and using machine-learning techniques to inform public health strategies. References Fenny AP, Crentsil AO, Asuman D. Determinants and distribution of comprehensive HIV/AIDS knowledge in Ghana. Glob J Health Sci . 2017;9(12):106–17. https://doi.org/10.5539/gjhs.v9n12p32. Ocran B, Talboys S, Shoaf K. Conflicting HIV/AIDS sex education policies and mixed messaging among educators and students in the Lower Manya Krobo Municipality, Ghana. Int J Environ Res Public Health . 2022;19(23):15487. https://doi.org/10.3390/ijerph192315487. Ba DM, Ssentongo P, Sznajder KK. Prevalence, behavioral and socioeconomic factors associated with human immunodeficiency virus in Ghana: a population-based cross-sectional study. J Glob Health Rep . 2019;3:e2019092. https://doi.org/10.29392/joghr.3.e2019092. Dey NEY, Ansah K, Norman QY, Manukure J, Brew AB, Dey E, et al. HIV testing among sexually active Ghanaians: an examination of the rural‒urban correlates. AIDS Behav . 2022;26(11):4063–4081. https://doi.org/10.1007/s10461-022-03731-4. Fiorentino M, Coulibaly B, Couderc C, Keita B, Anoma C, Dah E, et al. Men Who Have Sex with Both Men and Women in West Africa: Factors Associated with a High Behavioral Risk of Acquiring HIV from Male Partners and Transmission to Women. Arch Sex Behav . 2023;53:757–69. https://doi.org/10.1007/s10508-023-02715-2. Nutor JJ, Duah HO, Duodu PA, Agbadi P, Alhassan RK, Darkwah E. Geographical variations and factors associated with recent HIV testing prevalence in Ghana: spatial mapping and complex survey analyses of the 2014 demographic and health surveys. BMJ Open. 2021;11(2):e045458. https://doi.org/10.1136/bmjopen-2020-045458. Cane RM, Melesse DY, Kayeyi N, Manu A, Wado YD, Barros AJD, et al. HIV trends and disparities by gender and urban–rural residence among adolescents in sub-Saharan Africa. Reproductive Health . 2021;18(1):99. https://doi.org/10.1186/s12978-021-01118-7 Bulstra CA, Hontelez JAC, Giardina F, Steen R, Nagelkerke N, Bärnighausen T, et al. Mapping and characterizing areas with high levels of HIV transmission in sub-Saharan Africa: A geospatial analysis of national survey data. PLoS Med . 2020;17(3):e1003042. https://doi.org/10.1371/journal.pmed.1003042 Jahagirdar D, Walters MK, Novotney A, Brewer ED, Frank TD, Carter A, et al. Global, regional, and national sex-specific burden and control of the HIV epidemic, 1990–2019, for 204 countries and territories: the Global Burden of Diseases Study 2019. Lancet HIV . 2021;8(10):e633–51. https://doi.org/10.1016/S2352-3018(21)00152-1. Dambach P, Mahenge B, Mashasi I, Muya A, Barnhart DA, Bärnighausen T, et al. Sociodemographic characteristics and risk factors for HIV transmission in female bar workers in sub-Saharan Africa: a systematic literature review. BMC Public Health . 2020;20(1):697. https://doi.org/10.1186/s12889-020-08838-8 Dias BRL, Rodrigues TB, Botelho EP, de Oliveira MFV, Feijão AR, Polaro SHI. Integrative review on the incidence of HIV infection and its socio-spatial determinants. Rev Bras Enferm [Internet]. 2021;74(2). Available from: https://pubmed.ncbi.nlm.nih.gov/34037150/. Gu L, Zhang N, Mayer KH, McMahon J, Nam S, Conserve DF, et al. Autonomy-Supportive Healthcare Climate and HIV-Related Stigma Predict Linkage to HIV Care in Men Who Have Sex With Men in Ghana. J Int Assoc Provid AIDS Care. 2021;20:2325958220978113. https://doi.org/10.1177/2325958220978113 Adam A, Fusheini A, Ayanore MA, Amuna N, Agbozo F, Kugbey N, et al. HIV stigma and status disclosure in three municipalities in Ghana. Ann Glob Health [Internet]. 2021 Jun 18;87(1):49. Available from: https://pubmed.ncbi.nlm.nih.gov/34164262/. Mannoh I, Amundsen D, Turpin G, Lyons CE, Viswasam N, Hahn E, et al. A systematic review of HIV testing implementation strategies in Sub-Saharan African countries. AIDS Behav [Internet]. 2021;26(5):1660–71. https://pubmed.ncbi.nlm.nih.gov/34797449/. Adetokunboh OO, Are EB. Spatial distribution and determinants of HIV high burden in the Southern African sub-region. PLoS ONE . 2024 Apr 26;19(4):e0301850. https://doi.org/10.1371/journal.pone.0301850 Ibrahim NK, Asghari A. Ecological fallacy and individual risk. Front Public Health . 2016;4:46. https://doi.org/10.3389/fpubh.2016.00046. Sevugu JT. Socio-demographic, behavioural and biomedical factors contributing to HIV spread among adults in Ghana: a case-control study. Texila Int J Acad Res . 2021 Jul;8(3):64–79. doi:10.21522/TIJAR.2014.08.03.Art006 18. Koomson F, Teye-Kwadjo E. How much do we really know about sociosexuality in Ghana? Sex Cult . 2021;25:167–188. Available from: https://doi.org/10.1007/s12119-020-09764-y. Giguère K, Eaton JW, Marsh K, Johnson LF, Johnson CC, Ehui E, et al. Trends in knowledge of HIV status and efficiency of HIV testing services in sub-Saharan Africa, 2000–20: a modeling study using survey and HIV testing programme data. Lancet HIV. 2020;8(5):e284–93. https://doi.org/10.1101/2020.10.20.20216283 Wand H, Morris N, Reddy T. Temporal and spatial monitoring of HIV prevalence and incidence rates using geospatial models: Results from South African women. Spatial Spatio-Temporal Epidemiol. 2021;37:100413. https://doi.org/10.1016/j.sste.2021.100413. Sambah F, Baatiema L, Appiah F, Ameyaw EK, Budu E, Ahinkorah BO, et al. Educational attainment and HIV testing and counseling service utilization during antenatal care in Ghana: Analysis of Demographic and Health Surveys. PLoS One. 2020;15(1):e0227576. https://doi.org/10.1371/journal.pone.0227576 Owusu AY. A gendered analysis of living with HIV/AIDS in the Eastern Region of Ghana. BMC Public Health. 2020;20(1):1114. https://doi.org/10.1186/s12889-020-08702-9 Tables Table 1 Spatial Analysis – HIV & TB Summary Region HIV Incidence (Mean) Std _ Dev Min Max TB Incidence (Mean) Ashanti 224.1 33.71 154.35 288.78 159.89 Brong-Ahafo 199.97 29.76 140.46 260.1 147.87 Central 231.78 35.44 163.72 298.04 152 Eastern 207.73 31.01 148.43 267.18 144.06 Greater Accra 254.44 35.92 184.7 300.98 167.26 Northern 144 21.41 97.13 188.14 136.07 Upper East 120.46 17.44 94.77 155.66 128.23 Upper West 120.27 17.53 94.77 154.8 128.29 Volta 191.92 28.69 132.32 251.86 148.01 Western 200.04 29.74 138.11 259.86 151.99 Table 2 Spatial Analysis – Malaria, Education, Urbanization Summary Region Malaria Incidence (Mean) Education Access Index (Mean) Urbanization Level (Mean) Ashanti 199.64 56.84 62.94 Brong-Ahafo 216.1 53.38 50.76 Central 207.88 54.21 48.15 Eastern 199.9 58.66 56.87 Greater Accra 129.12 65.6 78.71 Northern 304.14 43.76 39.34 Upper East 359.51 48.11 34.98 Upper West 367.21 45.52 36.72 Volta 216.06 52.49 45.47 Western 224.07 55.16 52.52 Table 3 Key Feature Importance and SHAP Summary for hiv_incidence Fetures Data Type Missing Values Missing % Unique Values Outliers Detcted Post Winsorisation region object 0 0 10 64 0 date object 0 0 612 9 0 tb_outlier bool 0 0 1 0 0 malaria_outlier bool 0 0 2 379 0 urban_rural_sum_pct float64 0 0 1 0 0 age_sum_pct float64 0 0 3 57 0 migration_rate float64 0 0 9261 N/A 0 regional_stigma_index float64 0 0 6579 0 0 urbanization_level float64 0 0 9792 112 0 health_facility_density float64 0 0 9761 N/A 0 testing_coverage_pct float64 0 0 9792 N/A 0 access_to_art_pct float64 0 0 9792 0 0 hiv_awareness_index float64 0 0 9792 0 0 youth_unemployment_rate float64 0 0 9792 0 0 female_literacy_rate float64 0 0 9792 52 0 condom_use_rate float64 0 0 9792 69 0 education_access_index float64 0 0 9792 45 0 region_fixed object 0 0 10 0 0 population_rural_pct float64 0 0 9531 52 0 population_urban_pct float64 0 0 9531 N/A 0 population_15_64_pct float64 0 0 9792 334 0 population_65_plus_pct float64 0 0 9781 N/A 0 population_0_14_pct float64 0 0 9751 0 0 population_total float64 0 0 9631 44 0 hiv_incidence float64 0 0 9598 53 0 tb_incidence float64 0 0 9598 0 0 malaria_incidence float64 0 0 9598 59 0 month int64 0 0 12 N/A 0 year int64 0 0 51 92 0 hiv_outlier bool 0 0 1 2 0 Feature Name Description education_access_index % of population with secondary education or higher condom_use_rate Percentage consistently using condoms female_literacy_rate Literacy among women aged 15+ youth_unemployment_rate Youth (15–24) unemployment rate hiv_awareness_index Composite score measuring HIV knowledge and awareness access_to_art_pct % of HIV-positive individuals receiving ART testing_coverage_pct % of population tested for HIV health_facility_density Number of health facilities per 10,000 people regional_stigma_index 0–1 index quantifying HIV-related stigma in regions urbanization_level % of population living in urban areas migration_rate Net migration rate per 1,000 people Table 4 Correlation coefficients between HIV incidence and key predictor Predictor HIV Incidence Malaria Incidence TB Incidence Education Access Condom Use Rate Female Literacy Youth Unemployment HIV Awareness ART Coverage HIV Testing Coverage Facility Density Urbanization Level HIV Incidence 1 -0.41 0.85 0.92 0.88 0.91 -0.31 0.91 0.91 0.91 0.2 0.87 Malaria Incidence -0.41 1 0.08 -0.31 -0.25 -0.27 0.86 -0.18 -0.25 -0.21 -0.1 -0.53 TB Incidence 0.85 0.08 1 0.83 0.82 0.84 0.12 0.89 0.86 0.87 0.17 0.68 Education Access 0.92 -0.31 0.83 1 0.95 0.97 -0.29 0.95 0.96 0.96 0.21 0.89 Condom Use Rate 0.88 -0.25 0.82 0.95 1 0.95 -0.26 0.95 0.95 0.95 0.21 0.89 Female Literacy 0.91 -0.27 0.84 0.97 0.95 1 -0.25 0.93 0.94 0.95 0.2 0.85 Youth Unemployment -0.31 0.86 0.12 -0.29 -0.26 -0.25 1 -0.19 -0.26 -0.2 -0.09 -0.48 HIV Awareness 0.91 -0.18 0.89 0.95 0.95 0.93 -0.19 1 0.97 0.96 0.21 0.88 ART Coverage 0.91 -0.25 0.86 0.96 0.95 0.94 -0.26 0.97 1 0.96 0.21 0.9 HIV Testing Coverage 0.91 -0.21 0.87 0.96 0.95 0.95 -0.2 0.96 0.96 1 0.21 0.87 Facility Density 0.2 -0.1 0.17 0.21 0.21 0.2 -0.09 0.21 0.21 0.21 1 0.22 Urbanization Level 0.87 -0.53 0.68 0.89 0.89 0.85 -0.48 0.88 0.9 0.87 0.22 1 Table 5 Key Feature Importance and SHAP Summary for hiv_incidence Feature SHAP Score Key Interaction Highlighted SHAP for condom_use_rate 0.127 Positive effect increases with literacy SHAP for education_access_index 0.241 Nonlinear jump effect around score ~55 SHAP for hiv_awareness_index 0.198 Steep increase above awareness ~65 SHAP for tb_incidence 0.113 Moderate rise, esp. with higher urbanization Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-6745789","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":461625639,"identity":"179c10f9-03cf-4184-8431-5ef74149fee5","order_by":0,"name":"Valentine Golden Ghanem","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIiWNgGAWjYFAC5gYgIQHEPGCuHIg48ACvFkaglgSEFmOwlgTCWhjgWhJBljLg02Jw/GDj48IfFnn8/GsPfi6o2JY+P+zwQ6AtdnK6DTi0nElsNp6RIFEsOeNdsvSMM7dzN95OMwBqSTY2O4Bdi2RDYps0T4JE4oYbZwykeduAWmYngLQcSNyGS0v/w/bfIC37b5wx/s3773a64ez0D3i18EsktjGDbeHvMZPmbbidIC+dg98WfomHzdI8aRKJM27wmFnzHLttuEE6p+BAggFuv7DxJx/8zGNTl9jff8b4Nk/NbXn52embP3yosJPDpQUBJBIgtAFYpQEh5WAnQg2VbyBG9SgYBaNgFIwkAACV4WPWctVeaAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Suffolk Ipswich","correspondingAuthor":true,"prefix":"","firstName":"Valentine","middleName":"Golden","lastName":"Ghanem","suffix":""}],"badges":[],"createdAt":"2025-05-25 22:08:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6745789/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6745789/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83608992,"identity":"efb0cadf-32bf-44b4-9350-06823ef69e8a","added_by":"auto","created_at":"2025-05-29 11:50:34","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":798670,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eChoropleth Map of Average HIV Incidence\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/a80d7cda464e96f39cc69f2f.png"},{"id":83608986,"identity":"d13f9d0a-b51a-4e2c-8342-eaa57c04086c","added_by":"auto","created_at":"2025-05-29 11:50:34","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":131037,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eK-Means Cluster Map of Ghana's Ten Region\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/f4778f0cc30ce280691e748d.png"},{"id":83609682,"identity":"e32ef7c5-b1b5-415e-9ad8-32f26beb563d","added_by":"auto","created_at":"2025-05-29 11:58:34","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":1170494,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eScatterplots of HIV incidence vs. sociobehavioral variables\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/5d6bb73f51999ea1f3bcb6de.png"},{"id":83608988,"identity":"b3150886-1227-4488-b04a-a741a9c0c5a7","added_by":"auto","created_at":"2025-05-29 11:50:34","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":237927,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003ePatial Dependency Plots (Top 4 Figures)\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/ab8cdac1721d7db85dc3e93b.png"},{"id":83608989,"identity":"8754e494-9a2a-43f6-8ae9-4b39f02fd9e2","added_by":"auto","created_at":"2025-05-29 11:50:34","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":2330651,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend\u003c/p\u003e","description":"","filename":"51.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/ac01c90900a9065ab7abbd27.png"},{"id":83609683,"identity":"b6b391b8-623f-4c15-9776-cb0d8eed0fbe","added_by":"auto","created_at":"2025-05-29 11:58:34","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":204066,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eSHAP Dependence for HIV Awareness\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"6.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/ddd2203e0285f7eb29ae45c6.png"},{"id":83608993,"identity":"4329c6b5-33ff-494a-a285-c4f063b67032","added_by":"auto","created_at":"2025-05-29 11:50:34","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":156186,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cem\u003e\u003cstrong\u003eAverage Residuals by Region\u003c/strong\u003e\u003c/em\u003e\u003c/p\u003e","description":"","filename":"7.png","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/98ff15fddf93558503726188.png"},{"id":89391048,"identity":"4d16cbbc-e1f2-43fa-bf4b-a53041b2dad4","added_by":"auto","created_at":"2025-08-19 13:01:57","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7524222,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6745789/v1/59f72440-d576-473d-9641-385fb6549043.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning","fulltext":[{"header":"BACKGROUND","content":"\u003cp\u003eThe incidence of HIV/AIDS in Ghana exhibits heterogeneous impacts across regions and populations rather than a uniform distribution. Although the national HIV prevalence is less than 2% [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e], regional disparities in the number of cases and access to healthcare services remain. While the national Human Immunodeficiency Virus (HIV) prevalence dropped from 3.1% in 2004 to 2.4% in 2016 [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e], some districts, such as Lower Manya Krobo Municipality (LMKM), still have high incidence rates, as shown by the 5.64% reported in 2018 [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Despite being highly urbanized, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe Greater Accra and Ashanti\u003c/span\u003e regions still have \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ean unusually high\u003c/span\u003e HIV prevalence [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e], implying that long-term public health interventions did not yield uniform regional epidemic outcomes.\u003c/p\u003e \u003cp\u003eMany researchers in sub-Saharan Africa (SSA) have found that HIV vulnerability is influenced by complex socio-behavioral factors such as education, awareness, stigma, and gender roles. Higher educational attainment among Ghanaian women correlates with increased HIV testing and treatment uptake, whereas young rural men remain persistently underserved in diagnosis rates, underscoring demographic disparities in healthcare access [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. The stigma and legal barriers faced by Men who have Sex with Men (MSM) in Ghana prevent them from accessing services, thus exacerbating regional disparities in HIV outcome [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThese discrepancies emphasize the need for spatially targeted interventions to address granular inequities. \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eA recent analysis of\u003c/span\u003e Demographic and Health Survey\u003c/p\u003e \u003cp\u003e(DHS) data using spatial interpolation found that subregional testing in the western region was as low as 5% in some places and over 30% in others [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Regional variations in disease prevalence are often obscured by national averages, which may result in inappropriate policies and \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eresource misuse\u003c/span\u003e. Spatial epidemiology helps to uncover and target areas where HIV risk is hidden.\u003c/p\u003e \u003cp\u003eGhana\u0026rsquo;s HIV surveillance system still relies on administrative reports that lack detailed geographic information and exclude\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003es behavioral factors.\u003c/span\u003e Traditional regression models used in HIV policy forecasting often assume spatial independence and are poorly suited for capturing the multidimensional, nonlinear interactions that drive regional epidemics. Therefore, many high-risk populations remain underserved, whereas programmatic responses continue to be overly centralized.\u003c/p\u003e \u003cp\u003eNew developments in spatial analysis and interpretable Machine Learning (ML) can help solve these issues. SHapley Additive exPlanations (SHAP) and Partial Dependence Plot (PDPs) can be used to study the role of factors such as education, ART coverage, and stigma in HIV incidence and transmission. When paired with clustering and choropleth techniques, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe ML\u003c/span\u003e results can make interventions more equitable by tailoring them to different areas.\u003c/p\u003e \u003cp\u003eFew studies in Ghana have attempted to combine these approaches to examine how both geography and behavior influence HIV incidence. Moreover, few studies \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ehave examined how policy changes in HIV awareness or\u003c/span\u003e education may disproportionately affect regions. This study aimed to address this issue by directing its analysis to the spatial and behavioral factors that impact the incidence of HIV/AIDS. Using ecological modeling, this study merges spatial analysis with explainable ML to guide precise public health strategies for combating HIV/AIDS incidence in Ghana.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"METHODS","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Study Design and Rationale\u003c/h2\u003e \u003cp\u003eThis study used a retrospective ecological cross-sectional approach to analyze how socioeconomic and spatial factors affect the incidence of HIV/AIDS in Ghana between 2000 and 2022. The framework focuses on explaining HIV incidence through spatial, structural, and behavioral factors using machine learning models to support, but \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003edoes not replace\u003c/span\u003e this explanation.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003e3.2 Study Area and Units of Analysis\u003c/h3\u003e\n\u003cp\u003eThe study \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ewas\u003c/span\u003e conducted across ten legacy administrative regions to maintain consistency in the data before and after the 2018 redistricting. Monthly data were gathered \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003efrom 2000 to 2022\u003c/span\u003e, providing a panel dataset of 9,792 observations (12 months \u0026times; 23 years \u0026times; 10 regions).\u003c/p\u003e\n\u003ch3\u003e3.3 Data Sources and Variable Construction\u003c/h3\u003e\n\u003cp\u003eData were collected from national and international organizations. The Ghana Health Service (GHS) and Ghana AIDS Commission (GAC) provided data on HIV incidence, Antiretroviral Therapy (ART) coverage, and HIV testing coverage. The Ghana Statistical Service (GSS), Demographic and Health Surveys (DHS), and UNAIDS provided data on educational access, stigma index, awareness index, condom use rate, female literacy, and youth unemployment. Regional boundaries in GeoJSON format were obtained from geoboundaries.org. The outcome variable was the number of new HIV/AIDS cases per month per 100,000 individuals. \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eThe\u003c/span\u003e explanatory \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003evariables were divided into four categories: socio-behavio\u003c/span\u003eral \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e(education access, awareness, stigma), demographic (female literacy, unemployment, urbanization), biomedical (ART coverage, testing coverage, TB incidence), and spatial (region ID, centroids, and clusters).\u003c/span\u003e\u003c/p\u003e\n\u003ch3\u003e3.4 Spatial Data Harmonization\u003c/h3\u003e\n\u003cp\u003eThe new 16 administrative regions of Ghana were consolidated with the original ten using a region-code linking approach. A GeoJSON file from the geoboundaries.org database was used to link each of the ten regions to its matching spatial polygon. The geographic center of each region was found using GeoPandas in \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe Python\u003c/span\u003e programming language, enabling subsequent clustering and mapping. In addition, a spatial adjacency matrix was built using \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe\u003c/span\u003e Python Spatial Analysis Library (PySAL) Queen contiguity algorithm, which identifies neighbors based on common boundaries. This spatial weight matrix was then used to assess spatial autocorrelation using Global Moran\u0026rsquo;s I and Local Indicators of Spatial Association\u003c/p\u003e \u003cp\u003e(LISA). These techniques enable region-level boundaries to be linked with epidemiological data by matching the ISO-coded region IDs.\u003c/p\u003e\n\u003ch3\u003e3.5 Spatial and Behavioral Analysis\u003c/h3\u003e\n\u003cp\u003eHIV incidence and ART coverage maps were developed using Folium and Altair to identify places where social stigma and illiteracy overlap. Using K-means clustering with three clusters, this study identified different patterns across the country for education\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eal access, ART coverage, stigma, and awareness. The elbow method was used to determine the\u003c/span\u003e optimal number of clusters, while hierarchical clustering with Ward\u0026rsquo;s linkage was used to ensure that the results were robust. Global Moran\u0026rsquo;s I was used to identify the overall clustering pattern, while Local Moran\u0026rsquo;s I (LISA) was used to identify hotspots and coldspots of HIV incidence. Model residuals were mapped to identify regions \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethat perform\u003c/span\u003eed better or worse than expected, with values exceeding\u0026thinsp;\u0026plusmn;\u0026thinsp;1.5 indicating potential structural inconsistencies. The relationship between HIV \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003einfection\u003c/span\u003e and key variables (HIV awareness, ART coverage, educational access, stigma index, and condom use) was explored using boxplots and scatterplots.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e3.6 Data Preprocessing\u003c/h2\u003e \u003cp\u003eTemporal filtering \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eof retained\u003c/span\u003e data from 2000 to 2022. Missing values were imputed using the K-nearest neighbor method (K\u0026thinsp;=\u0026thinsp;5) based on correlated variables such as urbanization and facility density. Indicators for condom use and HIV awareness were smoothed using 3-month rolling averages. To mitigate the effect of outliers, the winsorizing technique was applied at the 1st and 99th percentiles. All variables were normalized using Z-scores for the modeling and clustering steps.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003e3.7 Interpretable Machine Learning Analysis\u003c/h3\u003e\n\u003cp\u003eAn 80/20 temporal split was used to train the model. Data from 2000 to 2019 were used for training, whereas data from 2020 to 2022 were used for testing. Random Forest and XGBoost regressor models were mainly used for explanatory analysis rather than \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003efor outcome prediction.\u003c/span\u003e SHAP values were used to interpret the importance of each predictor, and PDPs were used to identify any nonlinear changes in the data. A counterfactual simulation demonstrated that a 10% \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eincrease in education and\u003c/span\u003e HIV awareness could significantly reduce HIV incidence. The Grid Search with Cross-Validation (GridSearchCV) method was used for hyperparameter tuning, and \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe model\u003c/span\u003e performance was evaluated using R\u0026sup2;, RMSE, MAE, and MAPE.\u003c/p\u003e\n\u003ch3\u003e3.8 Streamlit Dashboard Deployment\u003c/h3\u003e\n\u003cp\u003eA dashboard app was developed using Python with HyperText Markup Language (HTML) and Cascading Style Sheet (CSS) elements. The app \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ewas\u003c/span\u003e deployed via Streamlit to enable \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe\u003c/span\u003e interactive exploration of HIV incidence maps, SHAP scores, cluster patterns, and counterfactual forecasts. The app is version controlled through GitHub and archived on Zenodo under DOI: \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003e10.5281/zenodo.15292209\u003c/span\u003e\u003cspan address=\"10.5281/zenodo.15292209\" targettype=\"DOI\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e. The app can be publicly accessed at \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://dashboardapppy-3ryuuaxnlmrsrrkqoxpcfw.streamlit.app\u003c/span\u003e\u003cspan address=\"https://dashboardapppy-3ryuuaxnlmrsrrkqoxpcfw.streamlit.app\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e"},{"header":"RESULTS","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Geographic distribution of HIV incidence\u003c/h2\u003e \u003cp\u003eChoropleth mapping revealed pronounced spatial disparities in HIV incidence across the ten administrative regions \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eof Ghana. Regions such as Greater Accra, Ashanti, and Central consistently recorded the highest incidence rates\u003c/span\u003e, surpassing 220 new HIV cases per 100,000 people annually (Figure \u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e1\u003c/span\u003e). In contrast, the Upper East, Northern, and Volta regions had lower incidence levels, averaging below 140 per 100,000, although recent data indicate increasing trends in some of these areas.\u003c/p\u003e \u003cp\u003eThese geographic variations persisted over the \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eperiod 2000\u0026ndash;2022\u003c/span\u003e, suggesting that structural and behavioral inequities have remained entrenched. Figure\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e1\u003c/span\u003e illustrates this trend through a regional choreopleth map of the average incidence rates over the study period, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethereby capturing the temporal stability of these disparities.\u003c/span\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec13\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Regional Clustering by Sociobehavioral Profiles\u003c/h2\u003e \u003cp\u003eTo better understand the heterogeneity in the incidence patterns, unsupervised machine learning (K-means clustering, K\u0026thinsp;=\u0026thinsp;3) was employed to classify regions into three socioepidemiological clusters on the basis of \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe\u003c/span\u003e tandardized values of education access, ART coverage, HIV awareness, and stigma index. The clustering algorithm grouped Greater Accra, Ashanti, and Central into Cluster A, characterized by \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ea high HIV burden alongside high urbanization, ART coverage, access to education, and relatively elevated stigma index scores. Cluster B, composed of the Brong-Ahafo, Western, and Eastern regions, presented intermediate incidence rates and a mixture of socio-behavio\u003c/span\u003eral profiles, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand was hence classified as transitional. Cluster C, which included the northern, upper\u003c/span\u003e-east, and upper-west regions, was characterized by a lower incidence, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ebut also lower levels of ART access, education, and HIV awareness, combined with higher stigma indices.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eThese observations are supported by Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e1\u003c/span\u003e, which details \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe regional-level HIV and TB averages, and\u003c/span\u003e Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e2\u003c/span\u003e, which summarizes \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe regional levels of education access and urbanization.\u003c/span\u003e Regional typologies are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Sociobehavioral Correlations with HIV Incidence\u003c/h2\u003e \u003cp\u003eBivariate correlation analysis demonstrated strong and statistically significant associations between HIV incidence and several key socio\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e-behavio\u003c/span\u003eral predictors. Access \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eto education was positively correlated with HIV incidence (r\u0026thinsp;=\u0026thinsp;0.71), indicating a higher incidence in regions with greater coverage of formal education. This seemingly paradoxical correlation may be explained by differential case detection\u003c/span\u003e; better-educated regions are likely to have higher testing penetration, case ascertainment, and surveillance infrastructure, which can inflate the reported incidence despite potentially lower actual transmission. While counterintuitive at first glance, further analysis suggests that this relationship may be driven by higher levels of testing, urbanization, and surveillance intensity in better-educated regions.\u003c/p\u003e \u003cp\u003eSimilarly, both the urbanization level and the HIV awareness index were positively correlated with incidence (r\u0026thinsp;=\u0026thinsp;0.65 and r\u0026thinsp;=\u0026thinsp;0.59, respectively), reinforcing the notion that areas with more infrastructure and outreach services are more likely to detect and report cases. Condom use rates and the regional stigma index showed complex patterns. While condom use was moderately associated with reduced incidence, stigma appeared to correlate with underreporting and reduced service uptake, especially in lower-burden regions where disclosure remains a challenge.\u003c/p\u003e \u003cp\u003eThese patterns became particularly salient when urban and rural geographies \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ewere compared. Urbanized regions, such as Greater Accra and Ashanti, despite having high education access and ART coverage, also recorded the highest incidence rates. This paradox may be explained by intensified surveillance, elevated partner concurrency, transactional sex, and increased network density. In contrast, rural settings, such as the Lower Manya Krobo Municipality (LMKM) in the Eastern Region, demonstrated localized hyperendemicity. Agormanya, a sentinel site within the LMKM, reported an HIV prevalence of 19.2%\u003c/span\u003e, among the highest in Ghana, despite the region\u0026rsquo;s relatively modest health infrastructure (Ocran, 2022; Dias, 2021).\u003c/p\u003e \u003cp\u003eThese rural\u0026ndash;urban contrasts align with the SHAP and PDP outputs from the predictive models, which ranked urbanization, education\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eal access, and stigma among the most influential variables (\u003c/span\u003e Figs.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003e\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e).\u003c/span\u003e Evidence suggests that regional differences in the HIV burden are not binary but instead shaped by layered contextual factors, including behavioral norms, population mobility, stigma gradients, and access visibility.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e3\u003c/span\u003e presents scatterplots illustrating the relationships between HIV incidence and selected predictors, and Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e3\u003c/span\u003e summarizes the strength and direction of these associations using Pearson correlation coefficients. Table\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e4\u003c/span\u003e provides \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe background on the quality and transformation of these variables.\u003c/span\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section2\"\u003e \u003ch2\u003e4.4 SHAP-Based Interpretation of Structural Predictors\u003c/h2\u003e \u003cp\u003eTo further explore the drivers of HIV incidence, random forest and XGBoost models were trained on the harmonized dataset and interpreted by Shapley Additive Explanations (SHAP) values. The SHAP summary plot ranks \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe features\u003c/span\u003e based on their mean absolute contribution to \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe model predictions. ART coverage, educational access, HIV awareness, urbanization, and TB co-infection\u003c/span\u003e were the most significant predictors.\u003c/p\u003e \u003cp\u003eSeveral threshold effects were observed. Notably, regions with an education index above 0.6 experienced a steep increase in the observed incidence, possibly reflecting increased detection due to improved health literacy and testing uptake. Conversely, ART coverage exceeding 45% was associated with \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ea substantial decline\u003c/span\u003e in \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe incidence, highlighting the preventive impact of treatment-as-prevention approaches. HIV awareness levels above 70% exhibited diminishing returns, suggesting that beyond a certain threshold, increased awareness alone\u003c/span\u003e did not yield further reductions in transmission.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e4\u003c/span\u003e displays the global SHAP summary plot, whereas Fig.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003e offers detailed SHAP dependence plots illustrating how changes in education and ART coverage influenced the predicted incidence across regions. Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e5\u003c/span\u003e summarizes \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe SHAP-based rankings and explanations.\u003c/span\u003e\u003c/p\u003e \u003cp\u003e\u003c/p\u003e\n\u003ch2\u003e4.5 Counterfactual Simulation: Impact of Modifying Key Predictors\u003c/h2\u003e\n\u003cp\u003eA counterfactual analysis was performed using the trained XGBoost model \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eto simulate the potential effects of policy interventions. A hypothetical 10% increase in either HIV awareness or educational access was applied uniformly across all regions. The results revealed that high-burden regions such as Greater Accra, Ashanti, and Western benefitted the most, with projected reductions in incidence ranging from 13\u0026ndash;16.3%.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003eThe transitional and lower-access regions demonstrated modest projected declines between 7% and 10%. Notably, the simulations revealed that regions with lower baseline levels of education or awareness experienced the greatest relative gains, indicating greater elasticity of response. These findings support the idea that targeted structural improvements, particularly in educational access and public health awareness, can yield meaningful reductions in HIV burden when directed toward vulnerable regions.\u003c/p\u003e\n\u003cp\u003eThese counterfactual results highlight the policy sensitivity of behavioral determinants in Ghana\u0026rsquo;s HIV response. Importantly, they illustrate that the effectiveness of interventions such as education and awareness is not uniform but context-dependent, amplified in transitional zones with mid-level infrastructure, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand underutilized testing. This confirms a \u0026ldquo;diminishing returns\u0026rdquo; pattern, where high-incidence urban centers with saturated services gain less from blanket messaging, whereas transitional or underresourced regions respond more elastically to marginal investment. Thus, counterfactual simulation does not merely estimate statistical change; it functions as a strategic tool for public health targeting, guiding scalable, cost-efficient investments, where they are likely to yield the greatest marginal benefit.\u003c/span\u003e\u003c/p\u003e\n\u003cp\u003eThese findings are grounded in the predictor distributions described in Table \u003cspan class=\"InternalRef\"\u003e2\u003c/span\u003e and SHAP simulation logic outlined in Table \u003cspan class=\"InternalRef\"\u003e5\u003c/span\u003e. Figure \u003cspan class=\"InternalRef\"\u003e6\u003c/span\u003e shows the projected changes in incidence across regions.\u003c/p\u003e\n\u003cp\u003e\u003c/p\u003e\n\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\n \u003ch2\u003e4.6 Residual Mapping and Latent Factors\u003c/h2\u003e\n \u003cp\u003eResidual analysis comparing the predicted and observed incidence revealed spatial patterns, suggesting that latent factors were not captured in the model. The central and eastern regions exhibited systematic underprediction, possibly indicating the presence of protective community norms, localized prevention programs, or reporting gaps \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethat were not accounted for in the dataset. This discrepancy may reflect unmeasured behavioral resilience or underdocumented public health interventions.\u003c/span\u003e\u003c/p\u003e\n \u003cp\u003eConversely, the Greater Accra and Western regions showed consistent overprediction, which could signal higher-than-expected transmission dynamics or limitations of the model in capturing highly mobile populations, transactional sexual behaviors, or complex social and sexual network dynamics. These insights are visualized in Fig. \u003cspan class=\"InternalRef\"\u003e7\u003c/span\u003e, which maps the regional distribution of the average residuals. Thus, residual analysis serves as a diagnostic tool, guiding future efforts to refine both surveillance and predictive modeling.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"DISCUSSION","content":"\u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e5.1 Principal findings and interpretations\u003c/h2\u003e \u003cp\u003eThe study applied ecological machine learning and spatial clustering to investigate the socio\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e-behavio\u003c/span\u003eral and structural determinants of HIV incidence across ten administrative regions of Ghana. According to the findings, HIV incidence is highest in Greater Accra, Ashanti, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand some areas in the Central and Eastern regions, which have more schools, larger towns, and greater access to ART. In addition\u003c/span\u003e, these results mirror a broader phenomenon in sub-Saharan Africa (SSA), where highly urbanized areas tend to have a higher rate of HIV among youth and young women, despite having better healthcare [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eThese urban \"hotspots\" often align with zones of heightened economic activity and risky sexual behavior\u003c/span\u003e [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eParadoxically, these urban areas still had high incidence rates. SHAP and PDP visualization\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003es in this study suggest\u003c/span\u003e that while ART coverage of over 45% is negatively correlated with HIV incidence rates (Figs.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003e), this trend was not significant in urban areas. ART saturation may reduce marginal gains unless accompanied by behavioral shifts [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. This is in agreement with studies showing that biomedical interventions alone are insufficient without complementary behavioral or structural shifts, especially among high-risk female populations, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003esuch as bar workers\u003c/span\u003e [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e (Cluster A: high burden, high access; Cluster B: transitional; Cluster C: low burden, low access) reflects the ideas proposed by previous studies [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e], demonstrating that HIV outcomes are shaped not only by infrastructure but also by layered behavioral, economic, and spatial inequalities.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003e5.2 Urban\u0026ndash;Rural Inequities and Behavioral Dynamics\u003c/h2\u003e \u003cp\u003eAlthough urban areas such as Accra demonstrate higher ART coverage and testing rates, they paradoxically sustain an elevated incidence. This urban-rural paradox mirrors broader regional findings where urban youth, particularly girls aged 15\u0026ndash;24, face higher HIV risks due to mobility, economic survival strategies, and social vulnerabilities [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. SHAP outputs (Figs.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eA-\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eD) revealed that this mismatch arises from high-risk behaviors, population mobility, and structural gaps such as inconsistent education programming. In contrast, rural zones such as Lower Manya Krobo (LMKM) report hyper-local epidemics\u0026mdash;Agormanya\u0026rsquo;s 19.2% prevalence [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]\u0026mdash;despite \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe regional averages being lower.\u003c/span\u003e Such local disparities reflect \"micro-epidemic\" dynamics observed across Eastern and Southern Africa, where high-prevalence pockets are not necessarily aligned with broader regional averages [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e1\u003c/span\u003e, \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e2\u003c/span\u003e, and \u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e4\u003c/span\u003e provide supporting evidence of these structural differences.\u003c/p\u003e \u003cp\u003eThis spatial vulnerability reflects the underlying behavioral and structural vulnerabilities. Male reluctance toward HIV testing and under-targeted adolescents have been observed as drivers of under-diagnosis in rural zones [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Similarly, Gu et al. (2021) found that peer influence and risk perception were critical barriers to adolescent HIV testing, even in well-serviced urban zones [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. These findings are consistent with our model residuals (Fig.\u0026nbsp;\u003cspan refid=\"Fig20\" class=\"InternalRef\"\u003e7\u003c/span\u003e), which were under\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e-predicted in the Eastern and Central Regions, potentially because of stigma-suppressed disclosure\u003c/span\u003e [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] or local resilience factors.\u003c/p\u003e \u003cp\u003eEducational access and HIV awareness (SHAP dependence plots, Fig.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eA \u0026amp; \u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eD) only reduced the incidence above the 0.6 threshold, This resonates with findings that general awareness rarely leads to preventive action unless paired with structural empowerment, particularly among populations such as female bar workers, who often report high HIV awareness but lack negotiating power for condom use [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. Moreover, some scholars argue that general awareness (~\u0026thinsp;98%) often does not translate into comprehensive knowledge [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. This supports a threshold-based policy: boost\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eing access in undeserved areas, where gains would be exponential.\u003c/span\u003e\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec21\" class=\"Section2\"\u003e \u003ch2\u003e5.3 Simulation of Structural Levers and Policy Impacts\u003c/h2\u003e \u003cp\u003eCounterfactual modeling demonstrated that a\u0026thinsp;+\u0026thinsp;10% increase in HIV awareness or education\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eal access can yield incidence reductions of up to 16.3% in high-burden regions (\u003c/span\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig19\" class=\"InternalRef\"\u003e6\u003c/span\u003e\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e). This observation aligns with real-world results from initiatives\u003c/span\u003e such as the Determined, Resilient, Empowered, AIDS-free, Mentored, and Safe (DREAMS) program, which showed up to \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ea 40% reduction\u003c/span\u003e in HIV incidence in targeted adolescent groups when structural and behavioral components were integrated [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e]. \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eThe observed\u003c/span\u003e responsiveness \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eof the model to education-based interventions underscores the need for structural tailoring. For instance, Dambach et al. (2020) highlighted that, in bar settings, even moderate wage improvements or access to sexual health counseling could shift behavior away from transactional sex. These are scalable levers that can complement national awareness campaigns\u003c/span\u003e [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe SHAP simulations (Figs.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig19\" class=\"InternalRef\"\u003e6\u003c/span\u003e) also demonstrated that this effect (education boost reduces HIV in hotspots) is most pronounced in transitional regions, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ewhere the baseline indicators are moderate. These m\u003c/span\u003eodel-derived insights correspond with \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe feature importance results in\u003c/span\u003e Table\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e5\u003c/span\u003e and data validation metrics in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e3\u003c/span\u003e, and support the case for a paradigm shift toward non-biomedical drivers in HIV prevention.\u003c/p\u003e \u003cp\u003eThese simulations reinforce\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ed the\u003c/span\u003e need for differentiated programming. Regions such as Ashanti and Western responded sharp\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ely\u003c/span\u003e to educational improvements. These findings echo those of a 2021 study that linked female education and literacy programs to durable HIV prevention outcomes [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSuch evidence also support\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003es the findings of\u003c/span\u003e previous research from 2021, which advocated for region-targeted interventions in SSA, highlighting that one-size-fits-all strategies are inefficient and ethically problematic in heterogeneous epidemics [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThese findings suggest that public health investments in educational infrastructure and awareness campaigns could have the greatest impact when strategically allocated to transitional or undeserved regions. In effect, simulations serve as policy scenario-testing tools, enabling decision-makers to visualize tangible returns on specific structural reforms.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec22\" class=\"Section2\"\u003e \u003ch2\u003e5.4 Comparison with Prior Literature\u003c/h2\u003e \u003cp\u003eThe findings from this investigation are broadly aligned with those of prior studies, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ebut introduce new granularity. While\u003c/span\u003e past studies [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e] \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ehave\u003c/span\u003e highlighted spatial disparities in HIV testing, this study quantifies behavioral thresholds and identifies saturation effects. Notably, the nonlinear impact of education\u0026mdash;initial increases in incidence due to testing bias, followed by later declines\u0026mdash;has not been previously modeled in Ghana.\u003c/p\u003e \u003cp\u003eA policy on abstinence-only education in LMKM contradicts the Ministry of Health\u0026rsquo;s comprehensive messaging, creating mixed narratives that impede behavioral change [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. These contradictory curricula are rarely captured in national datasets, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ebut they significantly shape the local epidemic trajectories.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eUnlike traditional regression-based models [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e], The SHAP-driven ML analysis (Figs.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eA\u0026ndash;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eD) in this study uncovered nonlinear and threshold effects across \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe structural predictors. While it does not model spatial lag explicitly, the feature behavior patterns provide richer insight than models that assume\u003c/span\u003e linear, independent effects.\u003c/p\u003e \u003cdiv id=\"Sec23\" class=\"Section3\"\u003e \u003ch2\u003e5.5 Study Limitations\u003c/h2\u003e \u003cp\u003eThis study has several limitations that should be considered when \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003einterpreting the findings\u003c/span\u003e. First, the use of an ecological design based on region-level aggregates introduces the risk of \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ean ecological fallacy. As a result, the associations observed between regional predictors and HIV incidence cannot be assumed to apply to individuals within th\u003c/span\u003eese regions [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. While this is valid, recent spatial studies such as Bulstra et al. (2020) used similar regional aggregation techniques and were still able to identify robust patterns of micro-epidemics, suggesting \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethat the method retains analytical value even if individual-level inferences\u003c/span\u003e are limited [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAlthough K-Nearest Neighbors (KNN) imputation was employed to address missing data (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e3\u003c/span\u003e), the assumption that data were missing at random may not hold for certain variables, particularly sensitive behavioral indicators such as condom use. Previous studies [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] underscore\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ed the potential for social desirability bias in such self-reported b\u003c/span\u003eehaviors, which could distort the accuracy of the imputed values. F\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eurthermore, t\u003c/span\u003ehis limitation is well justified, especially in light of studies such as Dambach et al. (2020), who documented social desirability bias in self-reporting among female bar workers, resulting in significant under-reporting of risky sexual behaviors [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFurthermore, the spatial aggregation process, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ein\u003c/span\u003e which Ghana\u0026rsquo;s 16 newly demarcated regions were merged into the ten legacy administrative zones, may have obscured intraregional disparities. This could result in the underestimation of localized epidemics, especially in emerging high-risk zones not historically identified as hotspots [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. The study also lacked the ability to control for latent confounders, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003esuch as transactional sex, economic migration, and displacement due to infrastructure development, such as dam construction. These factors, although not captured in the current dataset, are known to influence HIV transmission patterns, particularly in high-burden districts, such as Agormanya\u003c/span\u003e [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Moreover, this limitation is critical, as other studies have highlighted how mobility and economic factors drive risk, particularly among informal labor sectors such as market traders and bar workers [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. In regions with infrastructure-induced displacement, HIV burden may be significantly underestimated if these transient populations are excluded.\u003c/p\u003e \u003cp\u003eFurthermore,the omission of key populations, such as sex workers and mobile traders, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003emay lead to a structural under-diagnosis in high-burden zones. Several studies have reported that these groups often operate outside routine surveillance systems and require targeted outreach strategies\u003c/span\u003e [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Their exclusion weakens the generalizability of the current findings and limits \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003etheir predictive sensitivity for areas experiencing rapid urban growth or seasonal migration.\u003c/span\u003e\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec24\" class=\"Section2\"\u003e \u003ch2\u003e5.6 Policy and Programmatic Implications\u003c/h2\u003e \u003cp\u003eThe\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ese findings highlight the urgent need for a more granular, equity-focused approach to HIV prevention and control in Ghana. Moving beyond national averages, the regional stratification observed in this study calls for precis\u003c/span\u003ee public health strategies that are responsive to the unique sociostructural profiles of each region.\u003c/p\u003e \u003cp\u003eFirst, there is a clear need to expand community-based HIV testing services, particularly for men and adolescents who continue to exhibit lower testing rates. Gu et al. (2021) showed that adolescent testing uptake can be significantly improved through school-based and peer-driven interventions, particularly when stigma and peer influence are addressed simultaneously [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. Mobile testing units, home-based testing kits, and self-testing options may help close this diagnostic gap between under-served northern and rural zones [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. These interventions should be prioritized in areas where the testing prevalence is below the threshold values identified in the SHAP modeling framework (Fig.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eD).\u003c/p\u003e \u003cp\u003eSecond, policy realignment is necessary in regions \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ein wh\u003c/span\u003eich abstinence-only education continues to dominate. In Lower Manya Krobo Municipality, for example, policy contradictions between the Ghana Education Service and the Ministry of Health have led to mixed messaging between educators and students [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. This mirrors \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe structural misalignment reported\u003c/span\u003e by Sambah et al. (2020), where conflicting institutional narratives on youth sexuality undermined HIV prevention among female students [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. Integrating comprehensive, evidence-based sex education, which includes condom use, partner reduction, and biomedical prevention, is essential for curbing localized epidemics. Moreover, cross-border trading corridors\u0026mdash;identified as risk zones for mobile women traders\u0026mdash;should incorporate livelihood support with HIV prevention messaging and services [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. However, Cane et al. (2021) argue\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ed that livelihood support is insufficient unless paired with efforts to address gendered power imbalances that sustain women's vulnerability to coercion and HIV risk\u003c/span\u003e [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eResource allocation decisions should also be informed by SHAP-guided clustering (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e) and partial dependence plots (Fig.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e4\u003c/span\u003e), which help \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eto identify \u0026ldquo;transitional\u0026rdquo; regions\u003c/span\u003e with moderate coverage but high responsiveness to interventions. This data-driven targeting aligns with \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe calls for fine-scale geospatial mapping seen in Bulstra et al. (2020), who emphasized that localized epidemic zones often escape national policy radar and require precision prevention approaches\u003c/span\u003e [\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFinally, implementing SHAP-informed or AI-assisted programming assumes \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ea digital infrastructure and analytic capacity\u003c/span\u003e, which may be lacking in rural health systems. As Owusu et al. (2020) highlight\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eed, the gap in digital literacy and uneven access to data platforms could hinder the practical integration of these tools, reinforcing existing inequities if not addressed through training and decentralization efforts\u003c/span\u003e [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"CONCLUSION","content":"\u003cdiv id=\"Sec26\" class=\"Section2\"\u003e \u003ch2\u003e6.1 Conclusion\u003c/h2\u003e \u003cp\u003eThis study analyzed the influence of spatial and socio\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e-behavioral factors on HIV/AIDS incidence in Ghana using a combination of ecological modeling, spatial clustering, and explainable machine learning techniques. It was shown that both biomedical factors\u003c/span\u003e, such as ART availability, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand socio-structural characteristics, such as education, awareness, stigma, and urban density, contribute to regional variations in HIV incidence.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eThe results revealed three distinctive region-level groups (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e) characterized by varying levels of HIV risk and available resources. These analyses collectively reveal that HIV risk in Ghana exhibits distinct spatial and contextual variations. Areas with high HIV prevalence, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003esuch as the Greater Accra, enjoy better access to resources but are also exposed to greater behavioral risk. The\u003c/span\u003e lower incidence in rural areas could be attributed \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eto either\u003c/span\u003e genuine safety or lack of reporting (Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e1\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe simulations reveal\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eed that targeted social policy interventions could\u003c/span\u003e substantial\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ely impact\u003c/span\u003e HIV incidence. Increasing education or awareness by 10% in high-incidence areas could reduce new infections by as much as 16% (Fig.\u0026nbsp;\u003cspan refid=\"Fig19\" class=\"InternalRef\"\u003e6\u003c/span\u003e). These results highlight the importance of structural interventions for tackling HIV epidemic\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003es. Investing in education and awareness, particularly in areas experiencing a transition from low to moderate risk, has been shown to have a greater impact on reducing the incidence than increasing biomedical interventions. These findings support the reorientation of policies to\u003c/span\u003e address the root causes of HIV \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003einfections.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eThis study presents a methodology that enables researchers and policymakers to analyze spatial disparities, tailor interventions to specific regions, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand predict the public health benefits of evidence-based social policies.\u003c/span\u003e This advocates the adoption of regionally specific, evidence-based, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand socially responsive interventions.\u003c/span\u003e\u003c/p\u003e \u003cdiv id=\"Sec27\" class=\"Section3\"\u003e \u003ch2\u003e6.2 Policy Recommendations\u003c/h2\u003e \u003cp\u003eThe results highlight the importance of regionally specific HIV policies in Ghana. Improving education and awareness by small margins could lead to a 16% decrease in HIV incidence in areas undergoing economic and demographic transformation\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003es\u003c/span\u003e (Fig.\u0026nbsp;\u003cspan refid=\"Fig19\" class=\"InternalRef\"\u003e6\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eEastern, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand Brong-Ahafo. These regions are particularly amenable to behavioral interventions, indicating that efforts such as HIV education, peer support, and school-based initiatives should receive greater attention. Communication\u003c/span\u003e should be culturally sensitive and \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eshould address misunderstandings and social barriers.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eAreas such as Greater Accra and Ashanti face a conundrum as they have high ART coverage, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ebut persistently high HIV incidence.\u003c/span\u003e The incidence \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eof HIV remains elevated despite high ART uptake. SHAP dependence plots (\u003c/span\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eA-\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003eD) suggest that this may be due to persistent behavioral risks and saturation effects. Addressing behavioral factors, stigma, and network-based transmission is necessary to improve HIV control in these areas. Outreach to mobile youth, MSM, and sex workers should be a crucial component of prevention efforts. Approaches could include expanding Pre-Exposure Prophylaxis (PrEP) availability, conducting mobile testing, and running digital campaigns that leverage behavioral science to encourage participation and compliance.\u003c/p\u003e \u003cp\u003eTools such as SHAP and geospatial clustering (Figs.\u0026nbsp;\u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Fig18\" class=\"InternalRef\"\u003e5\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e) should be formally integrated into the decision-making processes of regional health directorates. These dashboards help inform planning and enable timely identification of \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe increasing risk. Integrating transparent ML outputs into district-level decisions improves transparency and responsiveness.\u003c/span\u003e\u003c/p\u003e \u003cp\u003eHIV services should be closely linked to maternal health, TB, and gender-based violence programs, particularly in under-resourced cluster C areas (Fig.\u0026nbsp;\u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e2\u003c/span\u003e). A coordinated effort involving public, private, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand donor resources is\u003c/span\u003e required to address geographical disparities and ensure lasting reforms. Applying preemptive, data-driven, \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003eand tailored approaches in each region is crucial\u003c/span\u003e for achieving \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ean equitable HIV reduction.\u003c/span\u003e\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eAIC: Akaike Information Criterion\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;AIDS: Acquired Immunodeficiency Syndrome\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;AI: Artificial Intelligence\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;API: Application Programming Interface\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;ART: Antiretroviral Therapy\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;CI: Confidence Interval\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;CSS - Cascading Style Sheets\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;CSV: Comma-Separated Values\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;CV: Cross-Validation\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;DAG: Directed Acyclic Graph\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;DHS: Demographic and Health Survey\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;DREAM: Determined, Resilient, Empowered, AIDS-free, Mentored, and Safe\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;GAC: Ghana AIDS Commission\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;GHS: Ghana Health Service\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;GIS: Geographic Information System\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;GridSearchCV: Grid Search with Cross-Validation\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;GSS: Ghana Statistical Service\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;HDX: Humanitarian Data Exchange\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;HIV: Human Immunodeficiency Virus\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;HTML - HyperText Markup Language\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;KNN: K-Nearest Neighbors\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;LISA: Local Indicators of Spatial Association\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;LMKM: Lower Manya Krobo Municipality\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;LSTM: Long Short-Term Memory\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MAE: Mean Absolute Error\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MAPE: Mean Absolute Percentage Error\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MAR: Missing At Random\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;ML: Machine Learning\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MoH: Ministry of Health\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;MSM: Men who have Sex with Men\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;OR: Odds Ratio\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;ORCID: Open Researcher and Contributor ID\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;PCA: Principal Component Analysis\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;PDP: Partial Dependence Plot\u003c/p\u003e\n\u003cp\u003ePrEP:\u0026nbsp; \u0026nbsp;Pre-Exposure Prophylaxis\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;PySAL: Python Spatial Analysis Library\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;QGIS: Quantum Geographic Information System\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;R\u0026sup2;: Coefficient of Determination\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;RMSE: Root Mean Square Error\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SDG: Sustainable Development Goal\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SHAP: SHapley Additive exPlanations\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SHAP-ML: SHAP-based Machine Learning\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SSA: Sub-Saharan Africa\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;STROBE: Strengthening the Reporting of Observational Studies in Epidemiology\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SVR: Support Vector Regressor\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;SVM: Support Vector Machine\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;TB: Tuberculosis\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;UNAIDS: Joint United Nations Programme on HIV/AIDS\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;WHO: World Health Organization\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;Zenodo: Open-access data repository platform\u003c/p\u003e\n"},{"header":"Declarations","content":"\u003cp\u003eEthical approval or consent was not required as this study used only publicly available data. Publicly available aggregated data were analyzed. Personally identifiable information and samples collected from individuals were excluded.\u003c/p\u003e\n\u003cp\u003eConsent for publication: Not applicable. This study did not include any personal information.\u003c/p\u003e\n\u003cp\u003eAvailability of data and materials: All materials used in this study were made openly accessible at the Zenodo repository under a CC-BY 4.0 license. The Zenodo archive contains detailed documentation, metadata, and replicability-verification files. There were no limitations to the use of the\u0026nbsp;data provided.\u003c/p\u003e\n\u003cp\u003eAll necessary files and information required for reproducing the analysis are included in the Zenodo repository.\u003c/p\u003e\n\u003cul\u003e\n \u003cli\u003eCleaned regional-level dataset (ghana_infectious_disease_model_dataset_cleaned.csv)\u003c/li\u003e\n \u003cli\u003eGeospatial boundary files (GHA_10regions_merged_final.geojson)\u003c/li\u003e\n \u003cli\u003eModel code and forecasting Script\u003c/li\u003e\n \u003cli\u003eDocumentation and SHA-256 verification\u003c/li\u003e\n\u003c/ul\u003e\n\u003cp\u003eData were gathered from publicly available national reports and statistical summaries provided by organizations such as\u0026nbsp;the GHS, GAC, MoH, GSS, UNAIDS, and the World Bank. The data were carefully cleaned, organized, and prepared for forecasting. This study did not use individual-level human data. The analysis employed regional-level data for forecasting.\u003c/p\u003e\n\u003cp\u003eCompeting interests: The author declares no competing interests.\u003c/p\u003e\n\u003cp\u003eFunding: The author\u0026nbsp;did not receive any financial support for this study.\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; contributions: VG contributed to all aspects of the study, including\u0026nbsp;the conceptualization, methodology, data collection and analysis, software development, validation, visualization, and drafting and editing of the manuscript.\u003c/p\u003e\n\u003cp\u003eAcknowledgments: The authors gratefully acknowledge the contributions of the Ghana Health Service, Ghana AIDS Commission, Ghana Statistical Service, and the Humanitarian Data Exchange (HDX) platform for sharing valuable epidemiological and demographic datasets that enabled the advancement of this research.\u0026nbsp;I acknowledge the efforts of individuals who share open geospatial data through the geoboundaries\u0026rsquo;\u0026nbsp;platform. This research was dedicated to the memory of my sister, Imelda Farr, who motivated me to pursue this academic goal.\u003c/p\u003e\n\u003cp\u003eAuthors\u0026apos; information: VG is a Biomedical Scientist working at the Medical Department of the Cocoa Clinic in Accra, Ghana. He earned an MSc in Data Science from the University of East London and is currently pursuing an MSc in Public Health through distance learning at the University of Suffolk. He is interested in developing models for infectious diseases, making predictions using epidemiological data, and using machine-learning techniques to inform public health strategies.\u003c/p\u003e\n"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eFenny AP, Crentsil AO, Asuman D. Determinants and distribution of comprehensive HIV/AIDS knowledge in Ghana. \u003cem\u003eGlob J Health Sci\u003c/em\u003e. 2017;9(12):106\u0026ndash;17. https://doi.org/10.5539/gjhs.v9n12p32.\u003c/li\u003e\n\u003cli\u003eOcran B, Talboys S, Shoaf K. Conflicting HIV/AIDS sex education policies and mixed messaging among educators and students in the Lower Manya Krobo Municipality, Ghana. \u003cem\u003eInt J Environ Res Public Health\u003c/em\u003e. 2022;19(23):15487. https://doi.org/10.3390/ijerph192315487.\u003c/li\u003e\n\u003cli\u003eBa DM, Ssentongo P, Sznajder KK. Prevalence, behavioral and socioeconomic factors associated with human immunodeficiency virus in Ghana: a population-based cross-sectional study. \u003cem\u003eJ Glob Health Rep\u003c/em\u003e. 2019;3:e2019092. https://doi.org/10.29392/joghr.3.e2019092.\u003c/li\u003e\n\u003cli\u003eDey NEY, Ansah K, Norman QY, Manukure J, Brew AB, Dey E, et al. HIV testing among sexually active Ghanaians: an examination of the rural‒urban correlates. \u003cem\u003eAIDS Behav\u003c/em\u003e. 2022;26(11):4063\u0026ndash;4081. https://doi.org/10.1007/s10461-022-03731-4.\u003c/li\u003e\n\u003cli\u003eFiorentino M, Coulibaly B, Couderc C, Keita B, Anoma C, Dah E, et al. Men Who Have Sex with Both Men and Women in West Africa: Factors Associated with a High Behavioral Risk of Acquiring HIV from Male Partners and Transmission to Women. \u003cem\u003eArch Sex Behav\u003c/em\u003e. 2023;53:757\u0026ndash;69. https://doi.org/10.1007/s10508-023-02715-2.\u003c/li\u003e\n\u003cli\u003eNutor JJ, Duah HO, Duodu PA, Agbadi P, Alhassan RK, Darkwah E. Geographical variations and factors associated with recent HIV testing prevalence in Ghana: spatial mapping and complex survey analyses of the 2014 demographic and health surveys. BMJ Open. 2021;11(2):e045458. https://doi.org/10.1136/bmjopen-2020-045458.\u003c/li\u003e\n\u003cli\u003eCane RM, Melesse DY, Kayeyi N, Manu A, Wado YD, Barros AJD, et al. HIV trends and disparities by gender and urban\u0026ndash;rural residence among adolescents in sub-Saharan Africa. \u003cem\u003eReproductive Health\u003c/em\u003e. 2021;18(1):99. https://doi.org/10.1186/s12978-021-01118-7\u003c/li\u003e\n\u003cli\u003eBulstra CA, Hontelez JAC, Giardina F, Steen R, Nagelkerke N, B\u0026auml;rnighausen T, et al. Mapping and characterizing areas with high levels of HIV transmission in sub-Saharan Africa: A geospatial analysis of national survey data. \u003cem\u003ePLoS Med\u003c/em\u003e. 2020;17(3):e1003042. https://doi.org/10.1371/journal.pmed.1003042\u003c/li\u003e\n\u003cli\u003eJahagirdar D, Walters MK, Novotney A, Brewer ED, Frank TD, Carter A, et al. Global, regional, and national sex-specific burden and control of the HIV epidemic, 1990\u0026ndash;2019, for 204 countries and territories: the Global Burden of Diseases Study 2019. \u003cem\u003eLancet HIV\u003c/em\u003e. 2021;8(10):e633\u0026ndash;51. https://doi.org/10.1016/S2352-3018(21)00152-1.\u003c/li\u003e\n\u003cli\u003eDambach P, Mahenge B, Mashasi I, Muya A, Barnhart DA, B\u0026auml;rnighausen T, et al. Sociodemographic characteristics and risk factors for HIV transmission in female bar workers in sub-Saharan Africa: a systematic literature review. \u003cem\u003eBMC Public Health\u003c/em\u003e. 2020;20(1):697. https://doi.org/10.1186/s12889-020-08838-8\u003c/li\u003e\n\u003cli\u003eDias BRL, Rodrigues TB, Botelho EP, de Oliveira MFV, Feij\u0026atilde;o AR, Polaro SHI. Integrative review on the incidence of HIV infection and its socio-spatial determinants. \u003cem\u003eRev Bras Enferm\u003c/em\u003e [Internet]. 2021;74(2). Available from: https://pubmed.ncbi.nlm.nih.gov/34037150/.\u003c/li\u003e\n\u003cli\u003eGu L, Zhang N, Mayer KH, McMahon J, Nam S, Conserve DF, et al. Autonomy-Supportive Healthcare Climate and HIV-Related Stigma Predict Linkage to HIV Care in Men Who Have Sex With Men in Ghana. J Int Assoc Provid AIDS Care. 2021;20:2325958220978113. https://doi.org/10.1177/2325958220978113\u003c/li\u003e\n\u003cli\u003eAdam A, Fusheini A, Ayanore MA, Amuna N, Agbozo F, Kugbey N, et al. HIV stigma and status disclosure in three municipalities in Ghana. \u003cem\u003eAnn Glob Health\u003c/em\u003e [Internet]. 2021 Jun 18;87(1):49. Available from: https://pubmed.ncbi.nlm.nih.gov/34164262/.\u003c/li\u003e\n\u003cli\u003eMannoh I, Amundsen D, Turpin G, Lyons CE, Viswasam N, Hahn E, et al. A systematic review of HIV testing implementation strategies in Sub-Saharan African countries. \u003cem\u003eAIDS Behav\u003c/em\u003e [Internet]. 2021;26(5):1660\u0026ndash;71. https://pubmed.ncbi.nlm.nih.gov/34797449/.\u003c/li\u003e\n\u003cli\u003eAdetokunboh OO, Are EB. Spatial distribution and determinants of HIV high burden in the Southern African sub-region. \u003cem\u003ePLoS ONE\u003c/em\u003e. 2024 Apr 26;19(4):e0301850. https://doi.org/10.1371/journal.pone.0301850\u003c/li\u003e\n\u003cli\u003eIbrahim NK, Asghari A. Ecological fallacy and individual risk. \u003cem\u003eFront Public Health\u003c/em\u003e. 2016;4:46. https://doi.org/10.3389/fpubh.2016.00046.\u003c/li\u003e\n\u003cli\u003eSevugu JT. Socio-demographic, behavioural and biomedical factors contributing to HIV spread among adults in Ghana: a case-control study. \u003cem\u003eTexila Int J Acad Res\u003c/em\u003e. 2021 Jul;8(3):64\u0026ndash;79. doi:10.21522/TIJAR.2014.08.03.Art006\u003c/li\u003e\n\u003cli\u003e\u003cstrong\u003e18. Koomson F, Teye-Kwadjo E.\u003c/strong\u003e How much do we really know about sociosexuality in Ghana? \u003cem\u003eSex Cult\u003c/em\u003e. 2021;25:167\u0026ndash;188. Available from: https://doi.org/10.1007/s12119-020-09764-y.\u003c/li\u003e\n\u003cli\u003eGigu\u0026egrave;re K, Eaton JW, Marsh K, Johnson LF, Johnson CC, Ehui E, et al. Trends in knowledge of HIV status and efficiency of HIV testing services in sub-Saharan Africa, 2000\u0026ndash;20: a modeling study using survey and HIV testing programme data. Lancet HIV. 2020;8(5):e284\u0026ndash;93. https://doi.org/10.1101/2020.10.20.20216283\u003c/li\u003e\n\u003cli\u003eWand H, Morris N, Reddy T. Temporal and spatial monitoring of HIV prevalence and incidence rates using geospatial models: Results from South African women. Spatial Spatio-Temporal Epidemiol. 2021;37:100413. https://doi.org/10.1016/j.sste.2021.100413.\u003c/li\u003e\n\u003cli\u003eSambah F, Baatiema L, Appiah F, Ameyaw EK, Budu E, Ahinkorah BO, et al. Educational attainment and HIV testing and counseling service utilization during antenatal care in Ghana: Analysis of Demographic and Health Surveys. PLoS One. 2020;15(1):e0227576. https://doi.org/10.1371/journal.pone.0227576\u003c/li\u003e\n\u003cli\u003eOwusu AY. A gendered analysis of living with HIV/AIDS in the Eastern Region of Ghana. BMC Public Health. 2020;20(1):1114. https://doi.org/10.1186/s12889-020-08702-9 \u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e1\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cbr\u003e\u0026nbsp;\u003cem\u003eSpatial Analysis \u0026ndash; HIV \u0026amp; TB Summary\u003c/em\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" class=\"fr-table-selection-hover\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRegion\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eHIV Incidence (Mean)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eStd\u003c/strong\u003e\u003cstrong\u003e_\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;Dev\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMin\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMax\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eTB Incidence (Mean)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eAshanti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e224.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e33.71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e154.35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e288.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e159.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eBrong-Ahafo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e199.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e29.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e140.46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e260.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e147.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eCentral\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e231.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e35.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e163.72\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e298.04\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e152\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eEastern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e207.73\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e31.01\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e148.43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e267.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e144.06\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eGreater Accra\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e254.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e35.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e184.7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e300.98\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e167.26\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eNorthern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e144\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e21.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e97.13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e188.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e136.07\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eUpper East\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e120.46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e17.44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e94.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e155.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e128.23\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eUpper West\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e120.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e17.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e94.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e154.8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e128.29\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eVolta\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e191.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e28.69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e132.32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e251.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e148.01\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003eWestern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e200.04\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e29.74\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e138.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e259.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 95px;\"\u003e\n \u003cp\u003e151.99\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\u003cstrong\u003e\u003c/strong\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e2\u0026nbsp;\u003c/strong\u003e\u003cbr\u003e\u003cem\u003eSpatial Analysis \u0026ndash; Malaria, Education, Urbanization Summary\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eRegion\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMalaria Incidence (Mean)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eEducation Access Index (Mean)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eUrbanization Level (Mean)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eAshanti\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e199.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e56.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e62.94\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eBrong-Ahafo\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e216.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e53.38\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e50.76\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eCentral\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e207.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e54.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e48.15\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eEastern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e199.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e58.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e56.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eGreater Accra\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e129.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e65.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e78.71\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eNorthern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e304.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e43.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e39.34\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eUpper East\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e359.51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e48.11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e34.98\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eUpper West\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e367.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e45.52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e36.72\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eVolta\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e216.06\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e52.49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e45.47\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003eWestern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e224.07\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e55.16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 140px;\"\u003e\n \u003cp\u003e52.52\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e3\u003c/strong\u003e\u003cbr\u003e\u003cem\u003eKey Feature Importance and SHAP Summary for hiv_incidence\u003c/em\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"628\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFetures\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eData Type\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMissing Values\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eMissing %\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eUnique Values\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eOutliers\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eDetcted\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePost Winsorisation\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eregion\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003eobject\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003edate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003eobject\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e612\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003etb_outlier\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003ebool\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003emalaria_outlier\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003ebool\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e379\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eurban_rural_sum_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eage_sum_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003emigration_rate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9261\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eregional_stigma_index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e6579\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eurbanization_level\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e112\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ehealth_facility_density\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9761\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003etesting_coverage_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eaccess_to_art_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ehiv_awareness_index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eyouth_unemployment_rate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003efemale_literacy_rate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003econdom_use_rate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e69\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eeducation_access_index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eregion_fixed\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003eobject\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_rural_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9531\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_urban_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9531\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_15_64_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9792\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e334\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_65_plus_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9781\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_0_14_pct\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9751\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003epopulation_total\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9631\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ehiv_incidence\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9598\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003etb_incidence\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9598\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003emalaria_incidence\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003efloat64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e9598\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003emonth\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003eint64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003eN/A\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eyear\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003eint64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 217px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ehiv_outlier\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 58px;\"\u003e\n \u003cp\u003ebool\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 64px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 66px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 71px;\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 81px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\u003cstrong\u003e\u003cem\u003e\u003cstrong\u003e\u003cem\u003e\u003cstrong\u003e\u003cem\u003e\u003cstrong\u003e\u003cem\u003e\u003cstrong\u003e\u003cem\u003e\u003cstrong\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/em\u003e\u003c/strong\u003e\u003c/em\u003e\u003c/strong\u003e\u003c/em\u003e\u003c/strong\u003e\u003c/em\u003e\u003c/strong\u003e\u003c/em\u003e\u003c/strong\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFeature Name\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eDescription\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003eeducation_access_index\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e% of population with secondary education or higher\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003econdom_use_rate\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003ePercentage consistently using condoms\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003efemale_literacy_rate\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003eLiteracy among women aged 15+\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003eyouth_unemployment_rate\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003eYouth (15\u0026ndash;24) unemployment rate\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003ehiv_awareness_index\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003eComposite score measuring HIV knowledge and awareness\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003eaccess_to_art_pct\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e% of HIV-positive individuals receiving ART\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003etesting_coverage_pct\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e% of population tested for HIV\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003ehealth_facility_density\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003eNumber of health facilities per 10,000 people\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003eregional_stigma_index\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e0\u0026ndash;1 index quantifying HIV-related stigma in regions\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003eurbanization_level\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003e% of population living in urban areas\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 206px;\"\u003e\n \u003cp\u003e\u003ccode\u003e\u003cstrong\u003emigration_rate\u003c/strong\u003e\u003c/code\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 362px;\"\u003e\n \u003cp\u003eNet migration rate per 1,000 people\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e4\u003c/strong\u003e\u003cbr\u003e\u0026nbsp;\u003cem\u003eCorrelation\u003c/em\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003cem\u003ecoefficients between HIV incidence and key predictor\u003c/em\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003ePredictor\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eMalaria Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eTB Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eEducation Access\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eCondom Use Rate\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eFemale Literacy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eYouth Unemployment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Awareness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eART Coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Testing Coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eFacility Density\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003eUrbanization Level\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eMalaria Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.53\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eTB Incidence\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.08\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.68\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eEducation Access\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.92\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.83\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eCondom Use Rate\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eFemale Literacy\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.27\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.84\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eYouth Unemployment\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.48\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Awareness\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.93\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eART Coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.97\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.9\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eHIV Testing Coverage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.91\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.96\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eFacility Density\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.09\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.22\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eUrbanization Level\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.89\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e-0.48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.88\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.87\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0.22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003e\u0026nbsp;\u003c/em\u003e\u003cstrong\u003eTable\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003e5\u0026nbsp;\u003c/strong\u003e\u003cbr\u003e \u003cem\u003eKey Feature Importance and SHAP Summary for hiv_incidence\u003c/em\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 208px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFeature\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 100px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSHAP Score\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 248px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eKey Interaction Highlighted\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 208px;\"\u003e\n \u003cp\u003eSHAP for \u003cstrong\u003econdom_use_rate\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 100px;\"\u003e\n \u003cp\u003e0.127\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 248px;\"\u003e\n \u003cp\u003ePositive effect increases with literacy\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 208px;\"\u003e\n \u003cp\u003eSHAP for \u003cstrong\u003eeducation_access_index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 100px;\"\u003e\n \u003cp\u003e0.241\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 248px;\"\u003e\n \u003cp\u003eNonlinear jump effect around score ~55\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 208px;\"\u003e\n \u003cp\u003eSHAP for \u003cstrong\u003ehiv_awareness_index\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 100px;\"\u003e\n \u003cp\u003e0.198\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 248px;\"\u003e\n \u003cp\u003eSteep increase above awareness ~65\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 208px;\"\u003e\n \u003cp\u003eSHAP for \u003cstrong\u003etb_incidence\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 100px;\"\u003e\n \u003cp\u003e0.113\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 248px;\"\u003e\n \u003cp\u003eModerate rise, esp. with higher urbanization\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"HIV/AIDS, Ghana, spatial epidemiology, sociobehavioral determinants, explainable machine learning, public health disparities, ART coverage, stigma, education, SHAP","lastPublishedDoi":"10.21203/rs.3.rs-6745789/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6745789/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground:\u003c/h2\u003e \u003cp\u003eDespite the national decline in cases, Ghana continues to experience significant regional disparities in HIV/AIDS incidence due to inequities in social factors, including education, stigma, HIV awareness, and access to ART. Such inequalities are often hidden in national statistics, which reduce the accuracy of public health measures.\u003c/p\u003e\u003ch2\u003eMethods:\u003c/h2\u003e \u003cp\u003eA unified regional dataset was created using GHS, GAC, MoH, GSS, UNAIDS, and World Bank data from 2000 to 2022, which combined sociobehavioral and health infrastructure factors. Using spatial clustering and choropleth mapping, high-incidence areas were identified and regional vulnerability was assessed. Random Forest and XGBoost analyzed key structural features via SHAP values, PDPs, and counterfactual simulations.\u003c/p\u003e\u003ch2\u003eResults:\u003c/h2\u003e \u003cp\u003eSpatial clustering and choropleth mapping revealed a spike in HIV incidence in \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethe\u003c/span\u003e Greater Accra, Ashanti, and Central regions. This pattern was linked to factors such as high urbanization, social stigma, and unequal access to ART. Clustering identified three main regional typologies based on the health indicators. SHAP and PDP analyses indicated \u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003ethat HIV incidence declined abruptly when educational access exceeded 60%, or ART coverage surpassed 45%.\u003c/span\u003e Residual mapping suggested possible under\u003cspan type=\"SmallCaps\" class=\"SmallCaps\" name=\"Emphasis\"\u003e-reporting of HIV incidence or latent socio-structural buffers in rural areas. A 10% increase in education or awareness reduced the incidence by up to 16% in the high-burden regions\u003c/span\u003e.\u003c/p\u003e\u003ch2\u003eConclusions:\u003c/h2\u003e \u003cp\u003eIn Ghana, HIV/AIDS incidence is influenced by access to healthcare and various spatial and social disparities. This study revealed the importance of creating policies that support education, reduce stigma, and ensure equal access to ART across different regions. Through explainable machine learning, the influence of behavioral and geographic factors on Ghana\u0026rsquo;s HIV incidence was examined.\u003c/p\u003e","manuscriptTitle":"Socio-Behavioral and Spatial Determinants of HIV/AIDS Incidence in Ghana: An Ecological Cross-Sectional Study with Explainable Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-29 11:50:29","doi":"10.21203/rs.3.rs-6745789/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"082e6fba-de8e-45cd-86e0-8c724e97f61e","owner":[],"postedDate":"May 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-19T12:53:48+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-29 11:50:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6745789","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6745789","identity":"rs-6745789","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}