RESUMEN
BACKGROUND: Cervical cancer (CC) is among the most prevalent cancer types among women with the highest prevalence in low- and middle-income countries (LMICs). It is a curable disease if detected early. Machine learning (ML) techniques can aid in early detection and prediction thus reducing screening and treatment costs. This study focused on women living with HIV (WLHIV) in Uganda. Its aim was to identify the best predictors of CC and the supervised ML model that best predicts CC among WLHIV. METHODS: Secondary data that included 3025 women from three health facilities in central Uganda was used. A multivariate binary logistic regression and recursive feature elimination with random forest (RFERF) were used to identify the best predictors. Five models; logistic regression (LR), random forest (RF), K-Nearest neighbor (KNN), support vector machine (SVM), and multi-layer perceptron (MLP) were applied to identify the out-performer. The confusion matrix and the area under the receiver operating characteristic curve (AUC/ROC) were used to evaluate the models. RESULTS: The results revealed that duration on antiretroviral therapy (ART), WHO clinical stage, TPT status, Viral load status, and family planning were commonly selected by the two techniques and thus highly significant in CC prediction. The RF from the RFERF-selected features outperformed other models with the highest scores of 90% accuracy and 0.901 AUC. CONCLUSION: Early identification of CC and knowledge of the risk factors could help control the disease. The RF outperformed other models applied regardless of the selection technique used. Future research can be expanded to include ART-naïve women in predicting CC.
Asunto(s)
Infecciones por VIH , Neoplasias del Cuello Uterino , Humanos , Femenino , Uganda/epidemiología , Neoplasias del Cuello Uterino/diagnóstico , Infecciones por VIH/tratamiento farmacológico , Adulto , Aprendizaje Automático Supervisado , Persona de Mediana Edad , Lesiones Precancerosas/diagnóstico , Modelos Logísticos , Algoritmos , Máquina de Vectores de SoporteRESUMEN
BACKGROUND: Active tuberculosis (TB) significantly increases the risk of cardiovascular disease, but the underlying mechanisms remain unclear. This study aimed to investigate the association between inflammation biomarkers and dyslipidemia in patients with drug-resistant TB (DR-TB). METHODS: This was a secondary analysis of data from a cross-sectional multi-center study in Uganda conducted 2021. Participants underwent anthropometric measurements and laboratory tests included a lipid profile, full haemogram and serology for HIV infection. Dyslipidemia was defined as total cholesterol > 5.0 mmol/l and/or low-density lipoprotein cholesterol > 4.14 mmol/l, and/or triglycerides (TG) ≥ 1.7 mmol/l, and/or high density lipoprotein cholesterol (HDL-c) < 1.03 mmol/l for men and < 1.29 mmol/l for women. Biomarkers of inflammation were leukocyte, neutrophil, lymphocyte, monocyte, and platelet counts, as well as neutrophil/lymphocyte (NLR), platelet/lymphocyte, and lymphocyte/monocyte (LMR) ratios, mean corpuscular volume (MCV), and the systemic immune inflammation index (SII) (neutrophil × platelet/lymphocyte). Modified Poisson Regression analysis was used for determining the association of the biomarkers and dyslipidemia. RESULTS: Of 171 participants, 118 (69.0%) were co-infected with HIV. The prevalence of dyslipidemia was 70.2% (120/171) with low HDL-c (40.4%, 69/171) and hypertriglyceridemia (22.5%, 38/169) being the most common components. Patients with dyslipidemia had significantly higher lymphocyte (P = 0.008), monocyte (P < 0.001), and platelet counts (P = 0.014) in addition to a lower MCV (P < 0.001) than those without dyslipidemia. Further, patients with dyslipidemia had lower leucocyte (P < 0.001) and neutrophil (P = 0.001) counts, NLR (P = 0.008), LMR (P = 0.006), and SII (P = 0.049). The MCV was inversely associated with low HDL-C (adjusted prevalence ratio (aPR) = 0.97, 95% CI 0.94-0.99, P = 0.023) but was positively associated with hypertriglyceridemia (aPR = 1.04, 95% CI 1.00-1.08, P = 0.052). CONCLUSIONS: Individuals with dyslipidemia exhibited elevated lymphocyte, monocyte, and platelet counts compared to those without. However, only MCV demonstrated an independent association with specific components of dyslipidemia. There is need for further scientific inquiry into the potential impact of dyslipidemia on red cell morphology and a pro-thrombotic state among patients with TB.
Asunto(s)
Dislipidemias , Infecciones por VIH , Hipertrigliceridemia , Tuberculosis Resistente a Múltiples Medicamentos , Masculino , Humanos , Femenino , Infecciones por VIH/complicaciones , Estudios Transversales , Uganda/epidemiología , Inflamación , HDL-Colesterol , BiomarcadoresRESUMEN
BACKGROUND: Innovations to increase access to sexual and reproductive health (SRH) information, goods, and services are needed, particularly in low-income settings. This study assessed the utilization of a mobile phone application (MPA) to increase access to SRH information, goods, and services among university students in Uganda. METHODS: We conducted a cross-sectional analysis of data from: (1) an endline survey performed as a consequence of a randomized controlled trial (RCT) of the effectiveness of the MPA, and (2) data from use of the MPA for accessing information, goods, and services over the 6-month time period of the RCT, obtained from in-MPA data collection service providers. We performed descriptive analysis of participant characteristics and their association with the utilization of the MPA using logistic regression; analyses of MPA use for accessing different types of information, goods, and services by gender; and analyses of functionality attributes of the MPA and related services. RESULTS: In the study population of young (median 22 years) predominantly female (61%) students, the utilization of the MPA by those who downloaded it was high (81% overall, 82% female, and 82% male). The most popular information portal was the frequently asked questions (71% utilization); the most popular goods were condoms for males (77% utilization) and sanitary pads for females (94% utilization); and the most popular service was HIV testing and counseling (60% utilization). The MPA demonstrated predominantly positive (responsiveness, non-distracting in-app advertisements, and ease of use) attributes. CONCLUSION: A mobile phone app to increase access to SRH information, goods, and services among university students in Uganda demonstrated high utilization. The results of this study support ongoing and future technical improvement efforts and research on effectiveness, economic efficiency, and scalability, along the continuum of activities to scale this intervention in order to improve SRH in low-income settings. TRIAL REGISTRATION: MUREC1/7 No. 07/05-18. Registered; June 29, 2018.
Asunto(s)
Teléfono Celular , Accesibilidad a los Servicios de Salud/estadística & datos numéricos , Aplicaciones Móviles , Servicios de Salud Reproductiva/estadística & datos numéricos , Estudiantes/estadística & datos numéricos , Estudios Transversales , Femenino , Humanos , Masculino , Embarazo , Salud Reproductiva , Servicios de Salud Reproductiva/organización & administración , Estudiantes/psicología , Uganda , UniversidadesRESUMEN
Several effective COVID-19 vaccines are administered to combat the COVID-19 pandemic globally. In most African countries, there is a comparatively limited deployment of vaccination programs. In this work, we develop a mathematical compartmental model to assess the impact of vaccination programs on curtailing the burden of COVID-19 in eight African countries considering SARS-CoV-2 cumulative case data for each country for the third wave of the COVID-19 pandemic. The model stratifies the total population into two subgroups based on individual vaccination status. We use the detection and death rates ratios between vaccinated and unvaccinated individuals to quantify the vaccine's effectiveness in reducing new COVID-19 infections and death, respectively. Additionally, we perform a numerical sensitivity analysis to assess the combined impact of vaccination and reduction in the SARS-CoV-2 transmission due to control measures on the control reproduction number (Rc). Our results reveal that on average, at least 60% of the population in each considered African country should be vaccinated to curtail the pandemic (lower the Rc below one). Moreover, lower values of Rc are possible even when there is a low (10%) or moderate (30%) reduction in the SARS-CoV-2 transmission rate due to NPIs. Combining vaccination programs with various levels of reduction in the transmission rate due to NPI aids in curtailing the pandemic. Additionally, this study shows that vaccination significantly reduces the severity of the disease and death rates despite low efficacy against COVID-19 infections. The African governments need to design vaccination strategies that increase vaccine uptake, such as an incentive-based approach.
RESUMEN
BACKGROUND: University students are one of the most vulnerable groups to sexual reproductive health [SRH] threats like sexually transmitted infections [STIs], unwanted pregnancies, and unsafe abortions and often have limited access to SRH information, goods, and services. This study assessed the effectiveness of using a mobile phone application (APP) to increase access to SRH information, goods, and services among university students in Uganda. METHODS: Using data from a double-blinded randomized controlled trial, participants were randomly assigned to both the intervention (APP) and control (standard of care) arms. We executed descriptive analyses for baseline demographic characteristics by intervention, difference in difference (DID), and quantile regression analyses for both primary and secondary outcomes. RESULTS: The median age of participants was 21 years of age, and the majority were female (over 60%), unemployed (over 85%) and Christian (90%). Over 50% were resident in off-campus hostels and in a relationship. Between baseline and end-line, there was a significant increase in SRH knowledge score (DID = 2, P < 0.001), contraceptive use (DID = 6.6%, P < 0.001), HIV Voluntary testing and counselling (DID = 17.2%, P < 0.001), STI diagnosis and treatment (DID = 12.9%, P < 0.001), and condom use at last sex (DID = 4%,P = 0.02) among students who used the APP. There was a significant 0.98 unit increase in knowledge score (adjusted coefficient = 0.98, P < 0.001), a significant 1.6-fold increase in odds of contraceptive use (adjusted coefficient = 1.6, P = 0.04), a significant 3.5-fold increase in HIV VCT (adjusted coefficient = 3.5, P < 0.001), and a significant 2-fold increase in odds of STI testing and treatment (adjusted coefficient = 1.9, P < 0.001) after adjusting for demographic characteristics among APP users compared to the control group. CONCLUSION: A mobile phone application increased sexual and reproductive health information (knowledge score), access to goods (contraceptives), and services (HIV voluntary testing and counseling and sexually transmitted infection diagnosis and management) among sexually active university students in Uganda. Further technical development, including the refinement of youth-friendly attributes, extending access to the app with other platforms besides android which was pilot tested, as well as further research into potential economic impact and paths to sustainability, is needed before the app is deployed to the general youth population in Uganda and other low-income settings. TRIAL REGISTRATION: MUREC1/7 No. 07/05-18. Registered on June 29, 2018.
RESUMEN
BACKGROUND: This study was conducted to test the acceptability and utilization of family planning benefits cards (FPBCs) as incentives to increase family planning uptake among youth living in urban slums in Uganda. METHODS: We conducted a one-year pilot study with two sub-studies on acceptability and utilization of FPBCs. The acceptability study utilized a quantitative cross-sectional design and was part of a baseline household survey while the utilization study was a primary analysis of claims and clinic data. We performed descriptive analyses and analyses of the association between different variables using binary logistic regression. RESULTS: The acceptability study included 280 eligible females. The majority were married (52%), Christian (87%), and aged 20 and above (84%). Acceptability of the program was high (93%). Seventy-two percent of females used the card at least once to access reproductive health services. Twenty-seven percent of female users discontinued family planning and 14% changed family planning methods during the study. Female users of short-term contraceptive methods were 11 times more likely to discontinue use of FPBCs compared to those who used long-term methods (adjusted OR = 10.9, P = 0.011). Participants in professional/managerial employment were 30 times more likely to discontinue compared to the unemployed (adjusted OR = 30.3, P = 0.015). Participants of parity equal to two were 89% less likely to discontinue use of FPBCs compared to those of parity equal to zero (adjusted OR = 0.1, P = 0.019). CONCLUSION: Family planning benefits cards, deployed as incentives to increase uptake of family planning, exhibited high acceptability and utilization by youth in urban slums in Uganda. There was evidence that use of short-term contraception methods, professional employment, and lower parity were associated with discontinuation of modern family planning methods after initial enrolment. TRIAL REGISTRATION: MUREC1/7 No. 10/05-17. Registered 19th, July 2017.