Characterizing residential mobility among people with HIV in Tennessee and its impact on HIV care outcomes.

OBJECTIVE: Our objective was to assess the prevalence and patterns of mobility among people with HIV (PWH) in Tennessee and its impact on HIV care outcomes. DESIGN: Retrospective cohort study. METHODS: We combined residential address and HIV surveillance data from PWH in Tennessee from 2016 to 2018. Using Poisson regression, we estimated associations between in-state mobility (change in address or total miles moved) in 1 year and outcomes in the subsequent year; retention: having two CD4 + /HIV RNA values (labs) in a calendar year at least 3 months apart, loss to follow-up (LTFU): having labs at baseline but not the subsequent year, and viral suppression: HIV RNA less than 200 copies/ml. We applied a kernel density estimator to origin-destination address lines to visualize mobility patterns across demographic subgroups. RESULTS: Among 17 428 PWH [median age 45 years (interquartile range; IQR 34-53)], 6564 (38%) had at least one move. Median miles moved was 8.9 (IQR 2.6-143.4)). We observed in-state movement between major cities (Chattanooga, Knoxville, Memphis and Nashville) and out-of-state movement to and from Georgia and Florida. Having at least one in-state move was associated with a decreased likelihood of retention [adjusted relative risk (aRR) = 0.91; 95% confidence interval (CI) 0.88-0.95], and an increased risk of LTFU (aRR = 1.17; 95% CI 1.04-1.31, two to three moves vs. none). Greater distance moved in-state was associated with decreased retention and increased LTFU (aRR = 0.53; 95% CI 0.49-0.58, aRR = 2.52; 95% CI 2.25-2.83, respectively for 1000 vs. 0 miles). There was no association between mobility and viral suppression. CONCLUSION: Mobility is common among PWH in Tennessee and is associated with initial poor engagement in HIV care.

Semi-Supervised Contrastive Learning for Remote Sensing: Identifying Ancient Urbanization in the South-Central Andes.

Archaeology has long faced fundamental issues of sampling and scalar representation. Traditionally, the local-to-regional-scale views of settlement patterns are produced through systematic pedestrian surveys. Recently, systematic manual survey of satellite and aerial imagery has enabled continuous distributional views of archaeological phenomena at interregional scales. However, such "brute force" manual imagery survey methods are both time- and labor-intensive, as well as prone to inter-observer differences in sensitivity and specificity. The development of self-supervised learning methods (e.g., contrastive learning) offers a scalable learning scheme for locating archaeological features using unlabeled satellite and historical aerial images. However, archaeological features are generally only visible in a very small proportion relative to the landscape, while the modern contrastive-supervised learning approach typically yields an inferior performance on highly imbalanced datasets. In this work, we propose a framework to address this long-tail problem. As opposed to the existing contrastive learning approaches that typically treat the labeled and unlabeled data separately, our proposed method reforms the learning paradigm under a semi-supervised setting in order to fully utilize the precious annotated data (<7% in our setting). Specifically, the highly unbalanced nature of the data is employed as the prior knowledge in order to form pseudo negative pairs by ranking the similarities between unannotated image patches and annotated anchor images. In this study, we used 95,358 unlabeled images and 5,830 labeled images in order to solve the issues associated with detecting ancient buildings from a long-tailed satellite image dataset. From the results, our semi-supervised contrastive learning model achieved a promising testing balanced accuracy of 79.0%, which is a 3.8% improvement as compared to other state-of-the-art approaches.

Geographic Variation in Access to Cardiac Rehabilitation.

BACKGROUND: There is marked geographic variation in cardiac rehabilitation (CR) initiation, ranging from 10% to 40% of eligible patients at the state level. The potential causes of this variation, such as patient access to CR centers, are not well studied. OBJECTIVES: The authors sought to determine how access to CR centers affects CR initiation in Medicare beneficiaries. METHODS: The authors used Medicare files to identify CR-eligible Medicare beneficiaries and calculate CR initiation rates at the hospital referral region (HRR) level. We used linear regression to evaluate the percent variation in CR initiation accounted for by CR access across HRRs. We then employed geospatial hotspot analysis to identify CR deserts, or counties in which patient load per CR center is disproportionately high. RESULTS: A total of 1,133,657 Medicare beneficiaries were eligible for CR from 2014 to 2017, of whom 263,310 (23%) initiated CR. The West North Central Census Division had the highest adjusted CR initiation rate (35.4%) and the highest density of CR programs (6.58 per 1,000 CR-eligible Medicare beneficiaries). Density of CR programs accounted for 21.2% of geographic variation in CR initiation at the HRR level. A total of 40 largely urban counties comprising 14% of the United States population age ≥65 years had disproportionately low CR access and were identified as CR deserts. CONCLUSIONS: A substantial proportion of geographic variation in CR initiation was related to access to CR programs, with a significant amount of the U.S. population living in CR deserts. These data invite further study on interventions to increase CR access.