Exploring the Association Between Structural Racism and Mental Health: Geospatial and Machine Learning Analysis.

BACKGROUND: Structural racism produces mental health disparities. While studies have examined the impact of individual factors such as poverty and education, the collective contribution of these elements, as manifestations of structural racism, has been less explored. Milwaukee County, Wisconsin, with its racial and socioeconomic diversity, provides a unique context for this multifactorial investigation. OBJECTIVE: This research aimed to delineate the association between structural racism and mental health disparities in Milwaukee County, using a combination of geospatial and deep learning techniques. We used secondary data sets where all data were aggregated and anonymized before being released by federal agencies. METHODS: We compiled 217 georeferenced explanatory variables across domains, initially deliberately excluding race-based factors to focus on nonracial determinants. This approach was designed to reveal the underlying patterns of risk factors contributing to poor mental health, subsequently reintegrating race to assess the effects of racism quantitatively. The variable selection combined tree-based methods (random forest) and conventional techniques, supported by variance inflation factor and Pearson correlation analysis for multicollinearity mitigation. The geographically weighted random forest model was used to investigate spatial heterogeneity and dependence. Self-organizing maps, combined with K-means clustering, were used to analyze data from Milwaukee communities, focusing on quantifying the impact of structural racism on the prevalence of poor mental health. RESULTS: While 12 influential factors collectively accounted for 95.11% of the variability in mental health across communities, the top 6 factors-smoking, poverty, insufficient sleep, lack of health insurance, employment, and age-were particularly impactful. Predominantly, African American neighborhoods were disproportionately affected, which is 2.23 times more likely to encounter high-risk clusters for poor mental health. CONCLUSIONS: The findings demonstrate that structural racism shapes mental health disparities, with Black community members disproportionately impacted. The multifaceted methodological approach underscores the value of integrating geospatial analysis and deep learning to understand complex social determinants of mental health. These insights highlight the need for targeted interventions, addressing both individual and systemic factors to mitigate mental health disparities rooted in structural racism.

The journey to overdose: Using spatial social network analysis as a novel framework to study geographic discordance in overdose deaths.

INTRODUCTION: Drug overdose deaths are often geographically discordant (the community in which the overdose death occurs is different from the community of residence). Thus, in many cases there is a journey to overdose. METHODS: We applied geospatial analysis to examine characteristics that define journeys to overdoses using Milwaukee, Wisconsin, a diverse and segregated metropolitan area in which 26.72 % of overdose deaths are geographically discordant, as a case study. First, we deployed spatial social network analysis to identify hubs (census tracts that are focal points of geographically discordant overdoses) and authorities (the communities of residence from which journeys to overdose commonly begin) for overdose deaths and characterized them according to key demographics. Second, we used temporal trend analysis to identify communities that were consistent, sporadic, and emergent hotspots for overdose deaths. Third, we identified characteristics that differentiated discordant versus non-discordant overdose deaths. RESULTS: Authority communities had lower housing stability and were younger, more impoverished, and less educated relative to hubs and county-wide numbers. White communities were more likely to be hubs, while Hispanic communities were more likely to be authorities. Geographically discordant deaths more commonly involved fentanyl, cocaine, and amphetamines and were more likely to be accidental. Non-discordant deaths more commonly involved opioids other than fentanyl or heroin and were more likely to be the result of suicide. CONCLUSION: This study is the first to examine the journey to overdose and demonstrates that such analysis can be applied in metropolitan areas to better understand and guide community responses.

Occult hepatitis C virus infection in patients with beta-thalassemia major: Is it a neglected and unexplained phenomenon?

Occult hepatitis C virus (HCV) infection (OCI) is described as the presence of viral genome in both hepatocytes and peripheral blood mononuclear cells (PBMCs) despite constant negative results on serum HCV RNA tests. Beta-thalassemia major (BTM) describes a group of inherited blood diseases. Patients with BTM require repeated blood transfusions, increasing the risk of exposure to infectious agents. We aimed to assess the prevalence of OCI in Iranian BTM patients and to identify the role of host factors in OCI positivity. A total of 181 BTM patients with HCV negative markers were selected. HCV RNA was tested in PBMCs using nested polymerase chain reaction assay. The positive samples were then genotyped via restriction fragment-length polymorphism (RFLP) and 5'-untranslated region sequencing. Six (3.3%) out of 181 BTM patients had viral HCV genomes in PBMC samples. Three (50.0%), two (33.3%), and one (16.7%) out of these six patients were infected with HCV-1b, HCV-1a, and HCV-3a, respectively. OCI positivity was significantly associated with the serum level of uric acid (P = 0.045) and ABO blood group (P = 0.032). Also, OCI patients had unfavorable IFNL3 rs12979860 TT, IFNL3 rs8099917 GG, IFNL3 rs12980275 GG, and IFNL4 ss469415590 ∆G/∆G genotypes. In conclusion, we indicated the low frequency of OCI in BTM patients. Nevertheless, more attention is warranted considering the importance of this infection. Also, further studies are necessary to determine the actual prevalence of OCI among BTM patients in Iran.