Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa
Abstract Introduction Significant regional variations in the HIV epidemic hurt effective common interventions in sub-Saharan Africa. It is crucial to analyze HIV positivity distributions within clusters and assess the homogeneity of countries. We aim at identifying clusters of countries based on soc...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2023-07-01
|
| Series: | BMC Infectious Diseases |
| Online Access: | https://doi.org/10.1186/s12879-023-08467-7 |
| _version_ | 1797774367796494336 |
|---|---|
| author | Charles K. Mutai Patrick E. McSharry Innocent Ngaruye Edouard Musabanganji |
| author_facet | Charles K. Mutai Patrick E. McSharry Innocent Ngaruye Edouard Musabanganji |
| author_sort | Charles K. Mutai |
| collection | DOAJ |
| description | Abstract Introduction Significant regional variations in the HIV epidemic hurt effective common interventions in sub-Saharan Africa. It is crucial to analyze HIV positivity distributions within clusters and assess the homogeneity of countries. We aim at identifying clusters of countries based on socio-behavioural predictors of HIV for screening. Method We used an agglomerative hierarchical, unsupervised machine learning, approach for clustering to analyse data for 146,733 male and 155,622 female respondents from 13 sub-Saharan African countries with 20 and 26 features, respectively, using Population-based HIV Impact Assessment (PHIA) data from the survey years 2015–2019. We employed agglomerative hierarchical clustering and optimal silhouette index criterion to identify clusters of countries based on the similarity of socio-behavioural characteristics. We analyse the distribution of HIV positivity with socio-behavioural predictors of HIV within each cluster. Results Two principal components were obtained, with the first describing 62.3% and 70.1% and the second explaining 18.3% and 20.6% variance of the total socio-behavioural variation in females and males, respectively. Two clusters per sex were identified, and the most predictor features in both sexes were: relationship with family head, enrolled in school, circumcision status for males, delayed pregnancy, work for payment in last 12 months, Urban area indicator, known HIV status and delayed pregnancy. The HIV positivity distribution with these variables was significant within each cluster. Conclusions /findings The findings provide a potential use of unsupervised machine learning approaches for substantially identifying clustered countries based on the underlying socio-behavioural characteristics. |
| first_indexed | 2024-03-12T22:20:00Z |
| format | Article |
| id | doaj.art-a1f3a048ca094d4cbc45cd6ac70ffa07 |
| institution | Directory Open Access Journal |
| issn | 1471-2334 |
| language | English |
| last_indexed | 2024-03-12T22:20:00Z |
| publishDate | 2023-07-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Infectious Diseases |
| spelling | doaj.art-a1f3a048ca094d4cbc45cd6ac70ffa072023-07-23T11:07:55ZengBMCBMC Infectious Diseases1471-23342023-07-0123111310.1186/s12879-023-08467-7Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan AfricaCharles K. Mutai0Patrick E. McSharry1Innocent Ngaruye2Edouard Musabanganji3African Center of Excellence in Data Science, University of RwandaAfrican Center of Excellence in Data Science, University of RwandaCollege of Science and Technology, University of RwandaCollege of Business and Economics, University of RwandaAbstract Introduction Significant regional variations in the HIV epidemic hurt effective common interventions in sub-Saharan Africa. It is crucial to analyze HIV positivity distributions within clusters and assess the homogeneity of countries. We aim at identifying clusters of countries based on socio-behavioural predictors of HIV for screening. Method We used an agglomerative hierarchical, unsupervised machine learning, approach for clustering to analyse data for 146,733 male and 155,622 female respondents from 13 sub-Saharan African countries with 20 and 26 features, respectively, using Population-based HIV Impact Assessment (PHIA) data from the survey years 2015–2019. We employed agglomerative hierarchical clustering and optimal silhouette index criterion to identify clusters of countries based on the similarity of socio-behavioural characteristics. We analyse the distribution of HIV positivity with socio-behavioural predictors of HIV within each cluster. Results Two principal components were obtained, with the first describing 62.3% and 70.1% and the second explaining 18.3% and 20.6% variance of the total socio-behavioural variation in females and males, respectively. Two clusters per sex were identified, and the most predictor features in both sexes were: relationship with family head, enrolled in school, circumcision status for males, delayed pregnancy, work for payment in last 12 months, Urban area indicator, known HIV status and delayed pregnancy. The HIV positivity distribution with these variables was significant within each cluster. Conclusions /findings The findings provide a potential use of unsupervised machine learning approaches for substantially identifying clustered countries based on the underlying socio-behavioural characteristics.https://doi.org/10.1186/s12879-023-08467-7 |
| spellingShingle | Charles K. Mutai Patrick E. McSharry Innocent Ngaruye Edouard Musabanganji Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa BMC Infectious Diseases |
| title | Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa |
| title_full | Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa |
| title_fullStr | Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa |
| title_full_unstemmed | Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa |
| title_short | Use of unsupervised machine learning to characterise HIV predictors in sub-Saharan Africa |
| title_sort | use of unsupervised machine learning to characterise hiv predictors in sub saharan africa |
| url | https://doi.org/10.1186/s12879-023-08467-7 |
| work_keys_str_mv | AT charleskmutai useofunsupervisedmachinelearningtocharacterisehivpredictorsinsubsaharanafrica AT patrickemcsharry useofunsupervisedmachinelearningtocharacterisehivpredictorsinsubsaharanafrica AT innocentngaruye useofunsupervisedmachinelearningtocharacterisehivpredictorsinsubsaharanafrica AT edouardmusabanganji useofunsupervisedmachinelearningtocharacterisehivpredictorsinsubsaharanafrica |