1
|
Alie MS, Negesse Y. Machine learning prediction of adolescent HIV testing services in Ethiopia. Front Public Health 2024; 12:1341279. [PMID: 38560439 PMCID: PMC10981275 DOI: 10.3389/fpubh.2024.1341279] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 03/04/2024] [Indexed: 04/04/2024] Open
Abstract
Background Despite endeavors to achieve the Joint United Nations Programme on HIV/AIDS 95-95-95 fast track targets established in 2014 for HIV prevention, progress has fallen short. Hence, it is imperative to identify factors that can serve as predictors of an adolescent's HIV status. This identification would enable the implementation of targeted screening interventions and the enhancement of healthcare services. Our primary objective was to identify these predictors to facilitate the improvement of HIV testing services for adolescents in Ethiopia. Methods A study was conducted by utilizing eight different machine learning techniques to develop models using demographic and health data from 4,502 adolescent respondents. The dataset consisted of 31 variables and variable selection was done using different selection methods. To train and validate the models, the data was randomly split into 80% for training and validation, and 20% for testing. The algorithms were evaluated, and the one with the highest accuracy and mean f1 score was selected for further training using the most predictive variables. Results The J48 decision tree algorithm has proven to be remarkably successful in accurately detecting HIV positivity, outperforming seven other algorithms with an impressive accuracy rate of 81.29% and a Receiver Operating Characteristic (ROC) curve of 86.3%. The algorithm owes its success to its remarkable capability to identify crucial predictor features, with the top five being age, knowledge of HIV testing locations, age at first sexual encounter, recent sexual activity, and exposure to family planning. Interestingly, the model's performance witnessed a significant improvement when utilizing only twenty variables as opposed to including all variables. Conclusion Our research findings indicate that the J48 decision tree algorithm, when combined with demographic and health-related data, is a highly effective tool for identifying potential predictors of HIV testing. This approach allows us to accurately predict which adolescents are at a high risk of infection, enabling the implementation of targeted screening strategies for early detection and intervention. To improve the testing status of adolescents in the country, we recommend considering demographic factors such as age, age at first sexual encounter, exposure to family planning, recent sexual activity, and other identified predictors.
Collapse
Affiliation(s)
- Melsew Setegn Alie
- Department of Public Health, School of Public Health, College of Medicine and Health Science, Mizan-Tepi University, Mizan-Aman, Ethiopia
| | - Yilkal Negesse
- Department of Public Health, College of Medicine and Health Science, Debre-Markos University, Gojjam, Ethiopia
| |
Collapse
|
2
|
Birhanu MY, Ketema DB, Desta M, Habtegiorgis SD, Mengist B, Alamneh AA, Abeje AN, Tegegne E, Mengist AG, Dessalegn M, Bekele GM, Jemberie SS. Married women pre-marital HIV testing status in Ethiopia: Individual and community level factor analysis. Front Med (Lausanne) 2023; 10:913040. [PMID: 36936216 PMCID: PMC10018750 DOI: 10.3389/fmed.2023.913040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Accepted: 02/03/2023] [Indexed: 03/06/2023] Open
Abstract
Introduction Marriage between serodiscordant individuals accounts for 65-85% of new infections. Pre-marital Human Immune Virus (HIV) testing opens the door for HIV infection prevention and control. There are no studies that have evaluated the coverage and factors influencing pre-marital HIV testing at the community level in Ethiopia. Methods This study was conducted using 10,008 samples of data extracted from Ethiopian demographic and health surveys (EDHS), 2016. To identify individual and community level factors a multi-level binary logistic regression model was used. Among fitted models, "full" model was taken as the best model. To declare the presence or absence of significant association with pre-marital HIV testing, a p-value < 0.05 with confidence interval (CI) was used. Results In Ethiopia, 21.4% (95% CI: 20.6, 22.2%) of study participants had pre-marital HIV testing. Age 35-49 years (AOR = 0.25; 95% CI: 0.09, 0.66), educated (AOR = 1.76; 95% CI: 1.17, 2.79), rich (AOR = 1.95; 95% CI: 1.13, 3.55), having media exposure (AOR = 1.54; 95% CI: 1.30, 4.71), and high community level literacy (AOR = 0.38; 95% CI: 0.22, 0.66) were factors significantly associated with pre-marital HIV testing. Conclusion The low coverage of pre-marital HIV testing in Ethiopia is insufficient to have a significant influence on the HIV/Acquired Immune Deficiency Syndrome (AIDS) epidemic. Information dissemination to create awareness about human rights and public health implications of pre-marital HIV testing áre necessary while it is made mandatory.
Collapse
Affiliation(s)
- Molla Yigzaw Birhanu
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
- *Correspondence: Molla Yigzaw Birhanu,
| | - Daniel Bekele Ketema
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Melaku Desta
- Department of Human Nutrition, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Samuel Derbie Habtegiorgis
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Belayneh Mengist
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Alehegn Aderaw Alamneh
- Department of Human Nutrition, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Ayenew Negesse Abeje
- Department of Human Nutrition, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Eniyew Tegegne
- Department of Environmental Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Aytenew Geremew Mengist
- Department of Gynecology and Obstetrics, College of Medicine and Health Sciences, Injibara University, Injibara, Ethiopia
| | - Migbar Dessalegn
- Department of Surgery, School of Medicine, Debre Markos University, Debre Markos, Ethiopia
| | - Getamesay Molla Bekele
- Department of Gynecology and Obstetrics, School of Medicine, Debre Markos University, Debre Markos, Ethiopia
| | - Selamawit Shita Jemberie
- Department of Human Nutrition, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| |
Collapse
|
3
|
Astawesegn FH, Conroy E, Mannan H, Stulz V. Measuring socioeconomic inequalities in prenatal HIV test service uptake for prevention of mother to child transmission of HIV in East Africa: A decomposition analysis. PLoS One 2022; 17:e0273475. [PMID: 35998196 PMCID: PMC9398021 DOI: 10.1371/journal.pone.0273475] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2021] [Accepted: 08/09/2022] [Indexed: 11/19/2022] Open
Abstract
Background Despite efforts made towards the elimination of mother-to-child HIV transmission, socioeconomic inequality in prenatal HIV test uptake in East Africa is not well understood. Therefore, this study aimed at measuring socioeconomic inequalities in prenatal HIV test uptake and explaining its main determinants in East Africa Method We analysed a total weighted sample of 45,476 women aged 15–49 years who birthed in the two years preceding the survey. The study used the most recent DHS data from ten East African countries (Burundi, Comoros, Ethiopia, Kenya, Malawi, Mozambique, Rwanda, Uganda, Zambia, and Zimbabwe). The socioeconomic inequality in prenatal HIV test uptake was measured by the concentration index and illustrated by the concentration curve. Then, regression based Erreygers decomposition method was applied to quantify the contribution of socioeconomic factors to inequalities of prenatal HIV test uptake in East Africa. Results The concentration index for prenatal HIV test uptake indicates that utilization of this service was concentrated in higher socio-economic groups with it being 15.94% higher among these groups in entire East Africa (p <0.001), 40.33% higher in Ethiopia (p <0.001) which was the highest and only 1.87% higher in Rwanda (p <0.01) which was the lowest. The decomposition analysis revealed that household wealth index (38.99%) followed by maternal education (13.69%), place of residence (11.78%), partner education (8.24%), watching television (7.32%), listening to the radio (7.11%) and reading newsletters (2.90%) made the largest contribution to socioeconomic inequality in prenatal HIV test in East Africa. Conclusion In this study, pro-rich inequality in the utilization of prenatal HIV tests was evident. The decomposition analysis findings suggest that policymakers should focus on improving household wealth, educational attainment, and awareness of mother-to-child transmission of HIV (MTCT) through various media outlets targeting disadvantaged sub-groups.
Collapse
Affiliation(s)
- Feleke Hailemichael Astawesegn
- Translational Health Research Institute (THRI), School of Medicine, Western Sydney University, Penrith, NSW, Australia
- School of Public Health, College of Medicine and Health Sciences, Hawassa University, Hawassa, Ethiopia
- * E-mail:
| | - Elizabeth Conroy
- Translational Health Research Institute (THRI), School of Medicine, Western Sydney University, Penrith, NSW, Australia
| | - Haider Mannan
- Translational Health Research Institute (THRI), School of Medicine, Western Sydney University, Penrith, NSW, Australia
| | - Virginia Stulz
- School of Nursing and Midwifery Centre for Nursing and Midwifery Research, Western Sydney University, Nepean, Hospital 1 level Court Building, Kingswood, NSW, Australia
| |
Collapse
|
4
|
Worku MG, Teshale AB, Tesema GA. Prevalence and associated factors of HIV testing among young (15-24) women in eastern Africa: a multilevel analysis of demographic health survey data (2008-2018). Arch Public Health 2022; 80:117. [PMID: 35410302 PMCID: PMC9004117 DOI: 10.1186/s13690-022-00879-2] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/31/2021] [Accepted: 04/01/2022] [Indexed: 11/24/2022] Open
Abstract
Background According to available evidence, only 15% of young women in sub-Saharan Africa know their Human immune deficiency virus (HIV) status. Despite a high prevalence of HIV infection among adolescents and young women, policymakers give less attention to HIV testing and counseling services. So, this study aimed to investigate the pooled prevalence and associated factors of HIV testing among young women in east Africa. Methods The most recent DHS surveys done among 11 east African countries were pooled and a weighted sample of 73,661 young women were included. At bivariable analysis variables with a p-value≤0.2 were selected for multivariable analysis and variables with a p-value of ≤0.05 in the multivariable analysis were considered as a statistically significant determinant of HIV testing. Results Pooled prevalence of HIV testing among young women was 55.3%: 95% CI (54.97%, 55.69%). In the multilevel multivariable analysis: respondent age, marital status, educational level, occupation, media exposure, having higher and comprehensive knowledge about HIV / AIDS, having some and higher risky sexual behavior, visiting health care facilities, being rural dweller, being from rich households, having multiple sexual partners, early sex initiation and community-level education were significantly associated with HIV testing. Conclusion The prevalence of HIV testing among young women was significantly affected by both individual and community-level factors. To prevent the transmission and dissemination of HIV, there should be a systematic and coordinated approach and policy for HIV testing among young people.
Collapse
Affiliation(s)
- Misganaw Gebrie Worku
- Department of Human Anatomy, University of Gondar, college of medicine and health science, School of Medicine, Gondar, Ethiopia.
| | - Achamyeleh Birhanu Teshale
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Getayeneh Antehunegn Tesema
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| |
Collapse
|
5
|
Worku MG, Tesema GA, Teshale AB. Prevalence and associated factors of HIV testing among reproductive-age women in eastern Africa: multilevel analysis of demographic and health surveys. BMC Public Health 2021; 21:1262. [PMID: 34187431 PMCID: PMC8243417 DOI: 10.1186/s12889-021-11292-9] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2020] [Accepted: 06/15/2021] [Indexed: 11/27/2022] Open
Abstract
BACKGROUND Despite efforts made to reduce the spread of the human immune-deficiency virus (HIV), its testing coverage remains low in low and middle-income countries (LMIC). Besides, information on factors associated with HIV counseling and testing among reproductive-age women is not sufficiently available. Therefore, this study was aimed to determine the pooled prevalence and factors associated with HIV testing among reproductive-age women in eastern Africa. METHODS Secondary data analysis was conducted based on the Demographic and Health Surveys (DHS) data conducted in East African countries. We pooled the most recent DHS surveys done in 11 East African countries. A total weighted sample of 183,411 reproductive-age women was included for this study. Both bivariable and multivariable multilevel logistic regression models were fitted. Variables with a p-value ≤0.2 in the bivariable analysis were selected for multivariable analysis. Finally, in the multivariable analysis, variables with a p-value ≤0.05 were considered as significant factors affecting HIV testing. RESULTS The pooled prevalence of HIV testing in eastern Africa was 66.92% (95%CI: 66.70, 67.13%). In the multivariable multilevel analysis factors such as the age of respondent, marital status, educational level, HIV knowledge, HIV stigma indicator, risky sexual behavior and women who visit a health facility were positively associated with HIV testing coverage among reproductive-age women. While women from rich and richest households, having multiple sexual partners, being from rural dwellers, late initiation of sex and higher community illiteracy level had a lower chance of being tested for HIV. CONCLUSION The pooled prevalence of HIV testing in eastern Africa was higher than most previous studies. Age of respondent, residence, wealth index, marital status, educational level, HIV knowledge, stigma indicator, risky sexual behavior, women who visit a health facility, multiple sexual partnerships, early initiation of sex and community illiteracy level were significantly associated with HIV testing. There should be an integrated strategic plan to give education about methods of HIV transmission and the implication of HIV testing and counseling. So all the stakeholders should have an integrated approach by giving special attention to the factors that hinder HIV testing to increase awareness regarding the benefit of HIV testing and counseling to control the spread of HIV/AIDS.
Collapse
Affiliation(s)
- Misganaw Gebrie Worku
- Department of Human Anatomy, College of Medicine and Health Science, School of Medicine, University of Gondar, Gondar, Ethiopia
| | - Getayeneh Antehunegn Tesema
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| | - Achamyeleh Birhanu Teshale
- Department of Epidemiology and Biostatistics, Institute of Public Health, College of Medicine and Health Sciences, University of Gondar, Gondar, Ethiopia
| |
Collapse
|
6
|
Heri AB, Cavallaro FL, Ahmed N, Musheke MM, Matsui M. Changes over time in HIV testing and counselling uptake and associated factors among youth in Zambia: a cross-sectional analysis of demographic and health surveys from 2007 to 2018. BMC Public Health 2021; 21:456. [PMID: 33676482 PMCID: PMC7937241 DOI: 10.1186/s12889-021-10472-x] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/25/2020] [Accepted: 02/19/2021] [Indexed: 01/13/2023] Open
Abstract
INTRODUCTION Zambia is among the countries with the highest HIV burden and where youth remain disproportionally affected. Access to HIV testing and counselling (HTC) is a crucial step to ensure the reduction of HIV transmission. This study examines the changes that occurred between 2007 and 2018 in access to HTC, inequities in testing uptake, and determinants of HTC uptake among youth. METHODS We carried out repeated cross-sectional analyses using three Zambian Demographic and Health Surveys (2007, 2013-14, and 2018). We calculated the percentage of women and men ages 15-24 years old who were tested for HIV in the last 12 months. We analysed inequity in HTC coverage using indicators of absolute inequality. We performed bivariate and multivariate logistic regression analyses to identify predictors of HTC uptake in the last 12 months. RESULTS HIV testing uptake increased between 2007 and 2018, from 45 to 92% among pregnant women, 10 to 58% among non-pregnant women, and from 10 to 49% among men. By 2018 roughly 60% of youth tested in the past 12 months used a government health centre. Mobile clinics were the second most common source reaching up to 32% among adolescent boys by 2018. Multivariate analysis conducted among men and non-pregnant women showed higher odds of testing among 20-24 year-olds than adolescents (aOR = 1.55 [95%CI:1.30-1.84], among men; and aOR = 1.74 [1.40-2.15] among women). Among men, being circumcised (aOR = 1.57 [1.32-1.88]) and in a union (aOR = 2.44 [1.83-3.25]) were associated with increased odds of testing. For women greater odds of testing were associated with higher levels of education (aOR = 6.97 [2.82-17.19]). Education-based inequity was considerably widened among women than men by 2018. CONCLUSION HTC uptake among Zambian youth improved considerably by 2018 and reached 65 and 49% tested in the last 12 months for women and men, respectively. However, achieving the goal of 95% envisioned by 2020 will require sustaining the success gained through government health centres, and scaling up the community-led approaches that have proven acceptable and effective in reaching young men and adolescent girls who are less easy to reach through the government facilities.
Collapse
Affiliation(s)
- Aimé Bitakuya Heri
- Department of Global Health, Nagasaki University School of Tropical Medicine and Global Health, Sakamoto 1-12-4, Nagasaki, 852-8523, Japan
| | - Francesca L Cavallaro
- Institute of Child Health, University College London, 30 Guilford St, Holborn, London, WC1N 1EH, UK
| | - Nurilign Ahmed
- Faculty of Public Health and Policy, London School of Hygiene and Tropical Medicine, Keppel Street, London, WC1E 7HT, UK
| | - Maurice Mubuyaeta Musheke
- Centre for Infectious Disease Research in Zambia, Plot # 34620, Off Alick Nkhata Road, Lusaka, Zambia
| | - Mitsuaki Matsui
- Department of Global Health, Nagasaki University School of Tropical Medicine and Global Health, Sakamoto 1-12-4, Nagasaki, 852-8523, Japan.
| |
Collapse
|
7
|
Davis R, Xiong X, Althabe F, Lefante J, Cafferata ML, Mwenechanya M, Mwanakalanga FH, Chomba E, Buekens P. Factors associated with HIV and syphilis screenings among pregnant women at first antenatal visit in Lusaka, Zambia. BMC Res Notes 2020; 13:423. [PMID: 32894196 PMCID: PMC7487891 DOI: 10.1186/s13104-020-05266-0] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2020] [Accepted: 09/01/2020] [Indexed: 11/16/2022] Open
Abstract
OBJECTIVES To identify characteristics associated with obtaining HIV and syphilis screenings of pregnant women attending a first antenatal visit in Lusaka, Zambia. RESULTS Among 18,231 participants from April 2015 to January 2016, 95% obtained HIV screening, 29% obtained syphilis screening, and 4% did not obtain antenatal HIV or syphilis screenings. Divorced/separated women were associated with a moderate decrease in prevalence of obtaining HIV (adjusted prevalence ratio (aPR) 0.88, 95% confidence interval (95% CI) 0.82, 0.95) and syphilis (aPR 0.51, 95% CI 0.27, 0.96) screenings compared to married women. Women with previous pregnancies were associated with a slight decrease in prevalence of obtaining HIV screening (aPR 0.97, 95% CI 0.95, 0.99) compared to women without previous pregnancy. Older women ≥ 35 years were associated with a slight decrease in prevalence of obtaining HIV screening (aPR 0.96, 95% CI 0.92, 0.99) compared to younger women. The statistically significant differences were not of clinical relevance as defined by a proportional difference of 10 percent. Findings of this study show that a vast majority of pregnant women are obtaining HIV screenings but not syphilis screenings during first antenatal visit. Provision of antenatal HIV and syphilis screening at first visit is only weakly related to patient level factors.
Collapse
Affiliation(s)
- Rindcy Davis
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA.
- , New York, USA.
| | - Xu Xiong
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| | - Fernando Althabe
- Institute for Clinical Effectiveness and Health Policy, Buenos Aires, Argentina
| | - John Lefante
- Department of Global Biostatistics and Data Science, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| | | | | | | | | | - Pierre Buekens
- Department of Epidemiology, Tulane University School of Public Health and Tropical Medicine, New Orleans, LA, USA
| |
Collapse
|