Explore the vast range of titles available.

Background Achieving high retention of people living with HIV (PLHIV) in care remains a challenge in Uganda, despite substantial progress towards UNAIDS 95–95-95 targets. The purpose of this study was to apply and compare machine learning and deep learning models using de-identified longitudinal clinical data collected from HIV clinics in Uganda to predict clients at high risk of missing treatment appointments. Predictions were made at the visit level, and a missed appointment was defined as failure to attend a scheduled clinical visit within 28 days of the assigned return data in accordance with the PEPFAR definition of loss to follow-up. Methods We compared the performance of traditional machine learning models (i.e. commonly used non-sequential models such as Decision Tree, Random Forest, AdaBoost, and XGBoost) and the Bidirectional Encoder Representations from Transformers (BERT) model, which is designed to model sequential and contextual information in longitudinal data. Feature importance using the Shapley additive exPlanations method was used to identify the most influential predictors. We also evaluated the impact of various sampling techniques, i.e. undersampling, oversampling, and synthetic minority oversampling, to address class imbalance and improve model performance. Model performance was evaluated using accuracy, precision, recall, F1-score, and the Area Under the Curve-Receiver Operating Characteristic (AUC-ROC) metrics. Results The study was based on a longitudinal dataset of 66,206 PLHIV who initiated HIV care during 2000–2023 in 86 health facilities. The data comprised 1,479,121 clinical visits, an average of 22 clinical visits per client; 158,266 (10.7%) missed appointments, and 49,588 (74.9%) of clients missed at least one appointment. Median (interquartile range [IQR]) age was 38.0 [29.0–47.0] years, and the majority ( n  = 43,132, 65.1%) were female. The BERT model achieved the highest performance in predicting missed appointments, with an AUC of 0.96 [CI: 0.94–0.97], precision of 89.0% [CI: 87.1%–90.9%], recall of 100% [CI: 100.0%–100.0%], and an F1-score of 94.0% [CI: 92.5%–95.5%] for the missed appointment class. In comparison, the best-performing traditional model, XGBoost with undersampling, achieved an AUC of 0.90 [CI: 0.87–0.92], precision of 33.2% [CI: 30.3%–36.1%], recall of 79.7% [CI: 77.2%–82.2%], and an F1-score of 46.8% [CI: 43.7%–49.9%] for the missed appointment class. Feature importance analysis showed that treatment adherence, visit frequency, treatment duration, and visits on the current regimen were the most influential predictors of appointment interruption. Conclusion In this retrospective analysis, transformer-based sequential modeling showed promising performance for visit-level prediction of missed HIV appointments compared with the non-sequential models evaluated. These findings should be interpreted cautiously, as further temporal and external validation is required. If validated prospectively, such models may support EMR workflows by identifying clients at higher risk of missed visits, potentially enabling more targeted outreach and retention support in HIV care programs.

We investigated progress towards UNAIDS 90-90-90 targets among female sex workers in Kampala, Uganda, who bear a disproportionate burden of HIV. Between April and December 2012, 1,487 female sex workers, defined as women, 15-49 years, residing in greater Kampala, and selling sex for money in the last 6 months, were recruited using respondent-driven sampling. Venous blood was collected for HIV and viral load testing [viral load suppression (VLS) defined as <1,000 copies/mL]. We collected data using audio computer-assisted self-interviews and calculated weighted population-level estimates. The median age was 27 years (interquartile range: 23 to 32). HIV seroprevalence was 31.4% (95% confidence interval [CI]: 29.0, 33.7%). Among all female sex workers who tested HIV-positive in the survey (population-level targets), 45.5% (95% CI: 40.1, 51.0) had knowledge of their serostatus (population-level target: 90%), 37.8% (95% CI: 32.2, 42.8) self-reported to be on ART (population-level target: 81%), and 35.2% (95% CI: 20.7, 30.4) were virally suppressed (population-level target: 73%). HIV prevalence among Kampala female sex workers is high, whereas serostatus knowledge and VLS are far below UNAIDS targets. Kampala female sex workers are in need of intensified and targeted HIV prevention and control efforts.

Increasing HIV diagnosis is important for combatting HIV. We invited individuals aged ≥ 13 years seeking voluntary HIV testing at Mildmay Clinic in Uganda to undertake a computer or audio-computer-assisted self-interview to facilitate post-test counseling. We evaluated first-visit data from 12,233 consenting individuals between January 2011 and October 2013. HIV prevalence was 39.0%. Of those with HIV, 37.2% already knew they were infected. Undiagnosed infection was associated with not being single, screening positive for depression (aOR 1.16, 95% CI 1.04–1.28), and screening for harmful drinking behavior (aOR 1.23, 95% CI 1.10–1.39). The odds of retesting subsequent to HIV diagnosis were lower for males (aOR 0.80, 95% CI 0.70–0.92) and those screening positive for harmful drinking behavior (aOR 0.77, 95% CI 0.66–0.88). Retesting was also associated with higher education and perceived social status below ‘better off’. Our findings reiterate the value of population-based HIV surveys to provide estimates of testing coverage.

Although sub-Saharan Africa has the highest HIV burden globally, few studies have investigated disabilities and HIV in this region. We conducted a secondary analysis of text data from in-depth interviews (2014–2015) to describe HIV perceptions among a subsample of 73 deaf individuals participating in the Crane survey, Kampala, Uganda. Being deaf was defined as being profoundly or functionally deaf, having deafness onset 5 + years ago, and preferring sign language to communicate. Among participants ever tested for HIV (47%), most (88%) had a negative test. Thematic analysis revealed overcoming challenges/barriers followed by socioeconomic status, support systems, HIV, stigma, abuse, and health conditions as major themes. An unanticipated finding was the role of sex work to support basic living needs. The data showed related themes among participants, suggesting a complex context in which deaf participants experience HIV prevention and treatment. It is important to tailor HIV interventions for deaf and disabled persons.

Background Violence and traumatic events are highly prevalent among refugees, but less is known about the impact of these experiences among self-settled refugees in the country of asylum. We evaluated the association between traumatic experiences and PTSD and depression symptoms among female Democratic Republic of Congo (DRC) refugees living in Kampala, Uganda. Methods Participants were recruited using respondent driven sampling in one refugee service center in Kampala, Uganda. Eligibility criteria included: Congolese nationality, age 18+ years, self-settled in Kampala for at least 6 months, refugee status or documentation of application for refugee status. Only data from female participants were included in this analysis. Depression symptoms were screened with the Patient Health Questionnaire-2, and symptom criteria for PTSD and traumatic experiences were evaluated with the Harvard Trauma Questionnaire. Logistic regression models were performed to separately assess associations between mental health outcomes (PTSD and depression), rape and non-sexual violence. Results Five hundred eighty women with a mean age of 33 years were interviewed. Among participants, 73% (95% CI:67–78%) met symptom criteria for PTSD, 57% (95% CI: 51–63%) for depression, and 65% reported thoughts of ending one’s life. 79% of women reported experience of rape, for over half (54%) it occurred more than once, and 82% were gang raped. Crude and adjusted odds ratios (ORs) show that PTSD was most strongly associated with being raped (OR = 2.43, p  < 0.01), lacking shelter (OR = 2.86, p  < 0.01), lacking food or water (OR = 2.53, p  = 0.02), lacking access to health care (OR = 2.84, p  < 0.01), forced labor (OR = 2.6, p  < 0.01), extortion and/or robbery (OR = 3.08, p  < 0.01), experiencing the disappearance/kidnapping of a family member or friend (OR = 2.72, p  < 0.01), and witnessing the killing or murder of other people (OR = 3.28, p  < 0.01). Depression was significantly associated with several traumatic experiences including rape (OR = 2.3, p  = 0.01), and experiencing the disappearance/kidnapping of a child or spouse (OR = 1.99, p  = 0.01). Conclusions Refugee women self-settled in Kampala reported high lifetime experiences of violence and traumatic events including rape, as well as high rates of PTSD and depression. Future programming addressing self-settled refugees and their settlement in host countries may benefit from including local and national integration strategies.

Background Duplicate patient records pose a significant challenge to healthcare registries and electronic medical record (EMR) systems in Uganda, primarily due to the absence of a national unique patient identifier. These duplicates lead to fragmented patient care, misallocation of resources, and inaccuracies in data reporting, which hinder effective monitoring of disease progression, disrupt continuity of care, and complicate efforts to track patient outcomes. This study evaluated the performance of three classification algorithms in identifying duplicate records of people living with HIV (PLHIV) and examined which demographic variables support reliable patient matching. Methods The study used a six-step deduplication process involving dataset extraction, preprocessing, indexing, comparison, classification, and performance evaluation. Records of PLHIV who were active in care between June and November 2022 were extracted from the UgandaEMR system - an EMR installed at 15 public health facilities in six districts in the Rwenzori Region. The dataset included demographic variables, i.e. given name, middle name, surname, sex, age, date of birth, address, and phone number. Three classification algorithms were evaluated: a threshold-based algorithm, a weighted average score-based method in which variable weights were assigned based on discriminative importance and refined iteratively, and a decision tree trained on rule-based labels and evaluated using a synthetic reference dataset of 1,000 records (500 original and 500 duplicates) due to the absence of a fully labeled real-world dataset. The algorithms’ performance was assessed using sensitivity, specificity, and F-score metrics. Results A total of 44,717 records for PLHIV active in care in the Rwenzori region from June to November 2022 were extracted. At the pair level (156,700 candidate pairs), the weighted average score-based algorithm identified 447 matches and 2,996 potential matches, while the threshold-based algorithm identified 118 matches and 8,560 potential matches. At the record level, the weighted average score-based algorithm flagged 2,459 records (5.8%) as duplicates, while the threshold-based algorithm flagged 223 records (0.5%) as duplicates. On the synthetic reference dataset, the weighted average score-based algorithm achieved the highest performance: sensitivity (99.0%), specificity (98.8%), and F-score (98.9%), followed by the decision tree and threshold-based methods. Conclusions The weighted average score-based algorithm achieved the best performance. Findings highlight that a combination of a few demographic variables can be employed to differentiate PLHIV. However, in the absence of a fully adjudicated gold standard, these performance metrics should be interpreted as algorithmic benchmarks under controlled conditions rather than estimates of real-world effectiveness. Improving duplicate record detection at scale will require validation on a larger, independently labeled dataset representative of the PLHIV population in Uganda.

Background Female sex workers are vulnerable to HIV, sexually transmitted diseases, and unintended pregnancies; however, the literature on female sex workers (FSW) focuses primarily on HIV and is limited regarding these other health issues. Methods We conducted a respondent-driven sampling (RDS) survey during April-December 2012 to characterize the reproductive health of and access to contraceptives FSW in Kampala, Uganda. Eligibility criteria included age ≥ 15 years, residence in greater Kampala, and having sold sex to men in ≤ 6 months. Data were analyzed using RDS-Analyst. Survey logistic regression was used in SAS. Results We enrolled 1,497 FSW with a median age of 27 years. Almost all FSW had been pregnant at least once. An estimated 33.8% of FSW were currently not using any form of family planning (FP) to prevent pregnancy; 52.7% used at least moderately effective FP. Among those using FP methods, injectable contraception was the most common form of FP used (55.4%), followed by condoms (19.7%), oral contraception (18.1%), and implants (3.7%). HIV prevalence was 31.4%, syphilis prevalence was 6.2%, and 89.8% had at least one symptom of a sexually transmitted disease in the last six months. Using at least a moderately effective method of FP was associated with accessing sexually transmitted disease treatment in a stigma-free environment in the last six months (aOR: 1.6, 95% CI: 1.1–2.4), giving birth to 2–3 children (aOR: 2.5, 95% CI: 1.4–4.8) or 4–5 children (aOR: 2.9, 95% CI: 1.4–5.9). It is plausible that those living with HIV are also less likely than those without it to be using a moderately effective method of FP (aOR: 0.7, 95% CI: 0.5–1.0). Conclusions The provision of integrated HIV and sexual and reproductive health services in a non-stigmatizing environment has the potential to facilitate increased health service uptake by FSW and decrease missed opportunities for service provision.

Transgender women in Kampala face stigma, high HIV acquisition or transmission risk and poor access to health services. We explored the HIV and gender-related contexts of their lives. Snowball sampling was used to enrol 45 participants between July-October 2013. Data collection included audio-computerassisted self-interviews, qualitative face-to-face interviews and blood tests for HIV and CD4. One in five respondents tested HIV positive. Emergent themes revealed highly varied forms of gender identity and gender expression. Almost all respondents asserted that they frequently engaged in sex work, mainly due to lack of employment. HIV-related themes included limited access to nonstigmatising health services, inconsistent condom use, inaccurate perceptions of self and partners’ risk, alcohol use, receptive anal sex with men, multiple sex partners, frequent self and enacted stigma, and violence. Findings highlight the urgency of providing members of this marginalised population with tailored, innovative, comprehensive and effective HIV prevention programmes that address structural issues such as access to HIV services and limited employment as well as behavioural issues such as inconsistent condom use, multiple sexual partners, self and enacted stigma, violence and alcohol use.

We report on the results of a respondent-driven sampling survey among men who have sex with men (MSM) in Kampala, Uganda, where same-sex behavior is criminalized and highly stigmatized. We enrolled 608 MSM aged 18 + years and residing in greater Kampala from June 2012-November 2013. Anonymous data were collected through audio-computer assisted self-interviews; blood was tested for HIV-1 antibodies, CD4 + T cell counts, and viral load. Estimated HIV prevalence was 12.2 % (95 % confidence interval [CI] 8.0–16.1), increasing with age. One in five (19.6 %) stated knowing their HIV-positive status and a similar proportion of HIV-infected MSM were virally suppressed (19.3 %; 95 % CI 3.3–33.1). HIV-related risk behaviors included unprotected anal sex (35.8 % at last sex act), selling sex (38.5 %), having multiple steady (54.3 %) or casual (63.6 %) partners, and ever injecting drugs (31.6 %). Forty percent experienced homophobic abuse; 44.5 % ever experienced suicide ideation. HIV prevalence among MSM remains high whereas knowledge of seropositive status and suppression of viral load remains low. MSM report a wide range of high risk behaviors, frequent homophobic abuse, poor mental health, as well as low levels of testing and treatment. Better access to tailored prevention and treatment services to improve population-level viral load suppression are warranted.

Transgender women in Kampala face stigma, high HIV acquisition or transmission risk and poor access to health services. We explored the HIV and gender-related contexts of their lives. Snowball sampling was used to enrol 45 participants between July-October 2013. Data collection included audio-computer-assisted self-interviews, qualitative face-to-face interviews and blood tests for HIV and CD4. One in five respondents tested HIV positive. Emergent themes revealed highly varied forms of gender identity and gender expression. Almost all respondents asserted that they frequently engaged in sex work, mainly due to lack of employment. HIV-related themes included limited access to non-stigmatising health services, inconsistent condom use, inaccurate perceptions of self and partners' risk, alcohol use, receptive anal sex with men, multiple sex partners, frequent self and enacted stigma, and violence. Findings highlight the urgency of providing members of this marginalised population with tailored, innovative, comprehensive and effective HIV prevention programmes that address structural issues such as access to HIV services and limited employment as well as behavioural issues such as inconsistent condom use, multiple sexual partners, self and enacted stigma, violence and alcohol use.