Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)

BackgroundViral load (VL) suppression is key to ending the global HIV epidemic, and predicting it is critical for healthcare providers and people living with HIV (PLHIV). Traditional research has focused on statistical analysis, but machine learning (ML) is gradually influencing HIV clinical care. W...

Full description

Saved in:
Bibliographic Details
Main Authors: Degninou Yehadji, Geraldine Gray, Carlos Arias Vicente, Petros Isaakidis, Abdourahimi Diallo, Saa Andre Kamano, Thierno Saidou Diallo
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1446876/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344508717694976
author Degninou Yehadji
Degninou Yehadji
Geraldine Gray
Carlos Arias Vicente
Petros Isaakidis
Petros Isaakidis
Abdourahimi Diallo
Saa Andre Kamano
Thierno Saidou Diallo
author_facet Degninou Yehadji
Degninou Yehadji
Geraldine Gray
Carlos Arias Vicente
Petros Isaakidis
Petros Isaakidis
Abdourahimi Diallo
Saa Andre Kamano
Thierno Saidou Diallo
author_sort Degninou Yehadji
collection DOAJ
description BackgroundViral load (VL) suppression is key to ending the global HIV epidemic, and predicting it is critical for healthcare providers and people living with HIV (PLHIV). Traditional research has focused on statistical analysis, but machine learning (ML) is gradually influencing HIV clinical care. While ML has been used in various settings, there’s a lack of research supporting antiretroviral therapy (ART) programs, especially in resource-limited settings like Guinea. This study aims to identify the most predictive variables of VL suppression and develop ML models for PLHIV in Conakry (Guinea).MethodsAnonymized data from HIV patients in eight Conakry health facilities were pre-processed, including variable recoding, record removal, missing value imputation, grouping small categories, creating dummy variables, and oversampling the smallest target class. Support vector machine (SVM), logistic regression (LR), naïve Bayes (NB), random forest (RF), and four stacked models were developed. Optimal parameters were determined through two cross-validation loops using a grid search approach. Sensitivity, specificity, predictive positive value (PPV), predictive negative value (PNV), F-score, and area under the curve (AUC) were computed on unseen data to assess model performance. RF was used to determine the most predictive variables.ResultsRF (94% F-score, 82% AUC) and NB (89% F-score, 82% AUC) were the most optimal models to detect VL suppression and non-suppression when applied to unseen data. The optimal parameters for RF were 1,000 estimators and no maximum depth (Random state = 40), and it identified Regimen schedule_6-Month, Duration on ART (months), Last ART CD4, Regimen schedule_Regular, and Last Pre-ART CD4 as top predictors for VL suppression.ConclusionThis study demonstrated the capability to predict VL suppression but has some limitations. The results are dependent on the quality of the data and are specific to the Guinea context and thus, there may be limitations with generalizability. Future studies may be to conduct a similar study in a different context and develop the most optimal model into an application that can be tested in a clinical context.
format Article
id doaj-art-bc7fa19ebeb74cfa83cc6181454e095c
institution Kabale University
issn 2624-8212
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-bc7fa19ebeb74cfa83cc6181454e095c2025-08-20T03:42:39ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-03-01810.3389/frai.2025.14468761446876Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)Degninou Yehadji0Degninou Yehadji1Geraldine Gray2Carlos Arias Vicente3Petros Isaakidis4Petros Isaakidis5Abdourahimi Diallo6Saa Andre Kamano7Thierno Saidou Diallo8Médecins Sans Frontières Belgique, Guinea Mission, Conakry, GuineaTechnological University Dublin, School of Informatics and Cybersecurity, Dublin, IrelandTechnological University Dublin, School of Informatics and Cybersecurity, Dublin, IrelandMédecins Sans Frontières Belgique, Guinea Mission, Conakry, GuineaMédecins Sans Frontières, Southern Africa Medical Unit, Cape Town, South AfricaUniversity of Ioannina School of Medicine, Department of Hygiene and Epidemiology, Clinical and Molecular Epidemiology Unit, Ioannina, GreeceMédecins Sans Frontières Belgique, Guinea Mission, Conakry, GuineaMédecins Sans Frontières Belgique, Guinea Mission, Conakry, GuineaMinistry of Health and Public Hygiene, National HIV and Hepatitis Control Program (PNLSH), Conakry, GuineaBackgroundViral load (VL) suppression is key to ending the global HIV epidemic, and predicting it is critical for healthcare providers and people living with HIV (PLHIV). Traditional research has focused on statistical analysis, but machine learning (ML) is gradually influencing HIV clinical care. While ML has been used in various settings, there’s a lack of research supporting antiretroviral therapy (ART) programs, especially in resource-limited settings like Guinea. This study aims to identify the most predictive variables of VL suppression and develop ML models for PLHIV in Conakry (Guinea).MethodsAnonymized data from HIV patients in eight Conakry health facilities were pre-processed, including variable recoding, record removal, missing value imputation, grouping small categories, creating dummy variables, and oversampling the smallest target class. Support vector machine (SVM), logistic regression (LR), naïve Bayes (NB), random forest (RF), and four stacked models were developed. Optimal parameters were determined through two cross-validation loops using a grid search approach. Sensitivity, specificity, predictive positive value (PPV), predictive negative value (PNV), F-score, and area under the curve (AUC) were computed on unseen data to assess model performance. RF was used to determine the most predictive variables.ResultsRF (94% F-score, 82% AUC) and NB (89% F-score, 82% AUC) were the most optimal models to detect VL suppression and non-suppression when applied to unseen data. The optimal parameters for RF were 1,000 estimators and no maximum depth (Random state = 40), and it identified Regimen schedule_6-Month, Duration on ART (months), Last ART CD4, Regimen schedule_Regular, and Last Pre-ART CD4 as top predictors for VL suppression.ConclusionThis study demonstrated the capability to predict VL suppression but has some limitations. The results are dependent on the quality of the data and are specific to the Guinea context and thus, there may be limitations with generalizability. Future studies may be to conduct a similar study in a different context and develop the most optimal model into an application that can be tested in a clinical context.https://www.frontiersin.org/articles/10.3389/frai.2025.1446876/fullHIVantiretroviral therapyviral loadmachine learningpredictionclassification
spellingShingle Degninou Yehadji
Degninou Yehadji
Geraldine Gray
Carlos Arias Vicente
Petros Isaakidis
Petros Isaakidis
Abdourahimi Diallo
Saa Andre Kamano
Thierno Saidou Diallo
Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
Frontiers in Artificial Intelligence
HIV
antiretroviral therapy
viral load
machine learning
prediction
classification
title Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
title_full Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
title_fullStr Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
title_full_unstemmed Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
title_short Development of machine learning algorithms to predict viral load suppression among HIV patients in Conakry (Guinea)
title_sort development of machine learning algorithms to predict viral load suppression among hiv patients in conakry guinea
topic HIV
antiretroviral therapy
viral load
machine learning
prediction
classification
url https://www.frontiersin.org/articles/10.3389/frai.2025.1446876/full
work_keys_str_mv AT degninouyehadji developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT degninouyehadji developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT geraldinegray developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT carlosariasvicente developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT petrosisaakidis developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT petrosisaakidis developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT abdourahimidiallo developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT saaandrekamano developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea
AT thiernosaidoudiallo developmentofmachinelearningalgorithmstopredictviralloadsuppressionamonghivpatientsinconakryguinea