Cargando…

Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms

Inadequate knowledge is one of the principal obstacles for preventing HIV/AIDS spread. Worldwide, it is reported that adolescents and young people have a higher vulnerability of being infected. Thus, the need to understand youths’ knowledge towards HIV/AIDS becomes crucial. This study aimed to ident...

Descripción completa

Detalles Bibliográficos
Autores principales: Aybar-Flores, Alejandro, Talavera, Alvaro, Espinoza-Portilla, Elizabeth
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10093875/
https://www.ncbi.nlm.nih.gov/pubmed/37047934
http://dx.doi.org/10.3390/ijerph20075318
_version_ 1785023694297366528
author Aybar-Flores, Alejandro
Talavera, Alvaro
Espinoza-Portilla, Elizabeth
author_facet Aybar-Flores, Alejandro
Talavera, Alvaro
Espinoza-Portilla, Elizabeth
author_sort Aybar-Flores, Alejandro
collection PubMed
description Inadequate knowledge is one of the principal obstacles for preventing HIV/AIDS spread. Worldwide, it is reported that adolescents and young people have a higher vulnerability of being infected. Thus, the need to understand youths’ knowledge towards HIV/AIDS becomes crucial. This study aimed to identify the determinants and develop a predictive model to estimate HIV/AIDS knowledge among this target population in Peru. Data from the 2019 DHS Survey were used. The software RStudio and RapidMiner were used for quasi-binomial logistic regression and computational model building, respectively. Five classification algorithms were considered for model development and their performance was assessed using accuracy, sensitivity, specificity, FPR, FNR, Cohen’s kappa, F1 score and AUC. The results revealed an association between 14 socio-demographic, economic and health factors and HIV/AIDS knowledge. The accuracy levels were estimated between 59.47 and 64.30%, with the random forest model showing the best performance (64.30%). Additionally, the best classifier showed that the gender of the respondent, area of residence, wealth index, region of residence, interviewee’s age, highest educational level, ethnic self-perception, having heard about HIV/AIDS in the past, the performance of an HIV/AIDS screening test and mass media access have a major influence on HIV/AIDS knowledge prediction. The results suggest the usefulness of the associations found and the random forest model as a predictor of knowledge of HIV/AIDS and may aid policy makers to guide and reinforce the planning and implementation of healthcare strategies.
format Online
Article
Text
id pubmed-10093875
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-100938752023-04-13 Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms Aybar-Flores, Alejandro Talavera, Alvaro Espinoza-Portilla, Elizabeth Int J Environ Res Public Health Article Inadequate knowledge is one of the principal obstacles for preventing HIV/AIDS spread. Worldwide, it is reported that adolescents and young people have a higher vulnerability of being infected. Thus, the need to understand youths’ knowledge towards HIV/AIDS becomes crucial. This study aimed to identify the determinants and develop a predictive model to estimate HIV/AIDS knowledge among this target population in Peru. Data from the 2019 DHS Survey were used. The software RStudio and RapidMiner were used for quasi-binomial logistic regression and computational model building, respectively. Five classification algorithms were considered for model development and their performance was assessed using accuracy, sensitivity, specificity, FPR, FNR, Cohen’s kappa, F1 score and AUC. The results revealed an association between 14 socio-demographic, economic and health factors and HIV/AIDS knowledge. The accuracy levels were estimated between 59.47 and 64.30%, with the random forest model showing the best performance (64.30%). Additionally, the best classifier showed that the gender of the respondent, area of residence, wealth index, region of residence, interviewee’s age, highest educational level, ethnic self-perception, having heard about HIV/AIDS in the past, the performance of an HIV/AIDS screening test and mass media access have a major influence on HIV/AIDS knowledge prediction. The results suggest the usefulness of the associations found and the random forest model as a predictor of knowledge of HIV/AIDS and may aid policy makers to guide and reinforce the planning and implementation of healthcare strategies. MDPI 2023-03-30 /pmc/articles/PMC10093875/ /pubmed/37047934 http://dx.doi.org/10.3390/ijerph20075318 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Aybar-Flores, Alejandro
Talavera, Alvaro
Espinoza-Portilla, Elizabeth
Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title_full Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title_fullStr Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title_full_unstemmed Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title_short Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms
title_sort predicting the hiv/aids knowledge among the adolescent and young adult population in peru: application of quasi-binomial logistic regression and machine learning algorithms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10093875/
https://www.ncbi.nlm.nih.gov/pubmed/37047934
http://dx.doi.org/10.3390/ijerph20075318
work_keys_str_mv AT aybarfloresalejandro predictingthehivaidsknowledgeamongtheadolescentandyoungadultpopulationinperuapplicationofquasibinomiallogisticregressionandmachinelearningalgorithms
AT talaveraalvaro predictingthehivaidsknowledgeamongtheadolescentandyoungadultpopulationinperuapplicationofquasibinomiallogisticregressionandmachinelearningalgorithms
AT espinozaportillaelizabeth predictingthehivaidsknowledgeamongtheadolescentandyoungadultpopulationinperuapplicationofquasibinomiallogisticregressionandmachinelearningalgorithms