Predictive factors of ART adherence in people living with HIV in Guangxi, China: a retrospective cross-sectional study

Lai, Jingzhen; Jiang, Zhuocheng; Zhang, Hong; Wei, Wudi; Li, Xu; Zhou, Oulu; Wang, Gang; Yang, Yao; Han, Jing; Liang, Hao; Ning, Chuanyi

doi:10.1080/09540121.2021.1967851

Cited by 5 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methodologically, our work was related to other studies predicting outcomes by inferring a model being trained by a set of historical data [15,22,25,40,[54][55][56]. Given appropriate assumptions, such techniques allow for valid predictions about the counterfactual outcomes under different settings for determining interventions.…”

Section: Plos Global Public Healthmentioning

confidence: 99%

“…In contrast, machine learning (ML), the creation of computer programs that can learn and therefore improve their performances by gathering more data and experiences [21], could prove beneficial in exploring individual patient factors predictive of tuberculosis treatment non-adherence. In fact, several studies have reported the effectiveness of machine learning models in accurately illustrating the target parameters for implementing stakeholders to ensure adherence to tuberculosis treatment and other chronic diseases [4,13,[22][23][24][25]. Yet, studies conducted in the Ugandan contexts have not adequately utilized machine learning as a method to generate patient predictors of tuberculosis treatment non-adherence [5,26,27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district

Gichuhi

Magumba

Kumar

et al. 2023

PLOS Glob Public Health

View full text Add to dashboard Cite

Despite the availability and implementation of well-known efficacious interventions for tuberculosis treatment by the Ministry of Health, Uganda (MoH), treatment non-adherence persists. Moreover, identifying a specific tuberculosis patient at risk of treatment non-adherence is still a challenge. Thus, this retrospective study, based on a record review of 838 tuberculosis patients enrolled in six health facilities, presents, and discusses a machine learning approach to explore the individual risk factors predictive of tuberculosis treatment non-adherence in the Mukono district, Uganda. Five classification machine learning algorithms, logistic regression (LR), artificial neural networks (ANN), support vector machines (SVM), random forest (RF), and AdaBoost were trained, and evaluated by computing their accuracy, F1 score, precision, recall, and the area under the receiver operating curve (AUC) through the aid of a confusion matrix. Of the five developed and evaluated algorithms, SVM (91.28%) had the highest accuracy (AdaBoost, 91.05% performed better than SVM when AUC is considered as evaluation parameter). Looking at all five evaluation parameters globally, AdaBoost is quite on par with SVM. Individual risk factors predictive of non-adherence included tuberculosis type, GeneXpert results, sub-country, antiretroviral status, contacts below 5 years, health facility ownership, sputum test results at 2 months, treatment supporter, cotrimoxazole preventive therapy (CPT) dapsone status, risk group, patient age, gender, middle and upper arm circumference, referral, positive sputum test at 5 and 6 months. Therefore, machine learning techniques, specifically classification types, can identify patient factors predictive of treatment non-adherence and accurately differentiate between adherent and non-adherent patients. Thus, tuberculosis program management should consider adopting the classification machine learning techniques evaluated in this study as a screening tool for identifying and targeting suited interventions to these patients.

show abstract

Section: Plos Global Public Healthmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district

Gichuhi

Magumba

Kumar

et al. 2023

PLOS Glob Public Health

View full text Add to dashboard Cite

show abstract

“…Previous studies showed that gender, transmission route, education level, substance use, medication reminders, side effects, ART duration, beliefs about ART, self-efficacy, social support, depression, HIV-related stigma, etc. were associated with ART adherence among PLHIV in China [5][6][7][8][9][10]. Another study showed that having higher perceived social capital was a significant predictor of better HIV ART adherence among PLHIV in North America [11].…”

Section: Introductionmentioning

confidence: 99%

Factors associated with antiretroviral treatment adherence among people living with HIV in Guangdong Province, China: a cross sectional analysis

Liu,

Yan,

et al. 2024

BMC Public Health

View full text Add to dashboard Cite

Background Understanding factors associated with antiretroviral treatment (ART) adherence is crucial for ART success among people living with HIV (PLHIV) in the “test and treat” era. Multiple psychosocial factors tend to coexist and have a syndemic effect on ART adherence. We aimed to explore factors associated with ART adherence and the syndemic effect of multiple psychosocial factors on ART adherence among PLHIV newly starting ART in Guangdong Province, China. Methods Newly diagnosed PLHIV from six cities in Guangdong Province were recruited between May 2018 and June 2019, and then followed up from May 2019 to August 2020. Baseline and follow-up data were collected from a questionnaire and the national HIV surveillance system, the follow-up data of which were analyzed in this study. A Center for Adherence Support Evaluation (CASE) index > 10 points was defined as optimal ART adherence, which was measured via participants’ self-reported adherence during follow-up survey. Multivariable logistic regression was used to identify factors associated with ART adherence. Exploratory factor analysis (EFA) and multi-order latent variable structural equation modeling (SEM) were performed to explore the syndemic effect of multiple psychosocial factors on ART adherence. Results A total of 734 (68.53%) follow-up participants were finally included in this study among the 1071 baseline participants, of whom 91.28% (670/734) had self-reported optimal ART adherence. Unemployment (aOR = 1.75, 95%CI: 1.01–3.02), no medication reminder (aOR = 2.28, 95%CI: 1.09–4.74), low medication self-efficacy (aOR = 2.28, 95%CI: 1.27–4.10), low social cohesion (aOR = 1.82, 95%CI: 1.03–3.19), no social participation (aOR = 5.65, 95%CI: 1.71–18.63), and ART side effects (aOR = 0.46, 95%CI: 0.26–0.81) were barriers to optimal ART adherence. The EFA and second-order latent variable SEM showed a linear relationship (standardized coefficient = 0.43, P < 0.001) between ART adherence and the latent psychosocial (syndemic) factor, which consisted of the three latent factors of medication beliefs and self-efficacy (standardized coefficient = 0.65, P < 0.001), supportive environment (standardized coefficient = 0.50, P < 0.001), and negative emotions (standardized coefficient=-0.38, P < 0.01). The latent factors of medication beliefs and self-efficacy, supportive environment, and negative emotions explained 42.3%, 25.3%, and 14.1% of the variance in the latent psychosocial factor, respectively. Conclusions About nine out of ten PLHIV on ART in Guangdong Province self-reported optimal ART adherence. However, more efforts should be made to address barriers to optimal ART adherence.

show abstract

“…Emerging data on China show positive effects of younger, higher incomes and higher education level on optimal adherence 5. Alcohol consumption, substance abuse, complex regimen and severe adverse effects may contribute to non-adherence 6 7. Moreover, individuals’ attitudes and beliefs about the consequences of adherence were also closely related to the treatment compliance 8…”

Section: Introductionmentioning

confidence: 99%

A model to predict adherence to antiretroviral therapy among people living with HIV

Chen

Long

et al. 2021

Sex Transm Infect

View full text Add to dashboard Cite

ObjectivesSuboptimal adherence to antiretroviral therapy (ART) dramatically hampers the achievement of the UNAIDS HIV treatment targets. This study aimed to develop a theory-informed predictive model for ART adherence based on data from Chinese.MethodsA cross-sectional study was conducted in Shenzhen, China, in December 2020. Participants were recruited through snowball sampling, completing a survey that included sociodemographic characteristics, HIV clinical information, Information-Motivation-Behavioural Skills (IMB) constructs and adherence to ART. CD4 counts and HIV viral load were extracted from medical records. A model to predict ART adherence was developed from a multivariable logistic regression with significant predictors selected by Least Absolute Shrinkage and Selection Operator (LASSO) regression. To evaluate the performance of the model, we tested the discriminatory capacity using the concordance index (C-index) and calibration accuracy using the Hosmer and Lemeshow test.ResultsThe average age of the 651 people living with HIV (PLHIV) in the training group was 34.1±8.4 years, with 20.1% reporting suboptimal adherence. The mean age of the 276 PLHIV in the validation group was 33.9±8.2 years, and the prevalence of poor adherence was 22.1%. The suboptimal adherence model incorporates five predictors: education level, alcohol use, side effects, objective abilities and self-efficacy. Constructed by those predictors, the model showed a C-index of 0.739 (95% CI 0.703 to 0.772) in internal validation, which was confirmed be 0.717 via bootstrapping validation and remained modest in temporal validation (C-index 0.676). The calibration capacity was acceptable both in the training and in the validation groups (p>0.05).ConclusionsOur model accurately estimates ART adherence behaviours. The prediction tool can help identify individuals at greater risk for poor adherence and guide tailored interventions to optimise adherence.

show abstract

Predictive factors of ART adherence in people living with HIV in Guangxi, China: a retrospective cross-sectional study

Cited by 5 publications

References 15 publications

A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district

A machine learning approach to explore individual risk factors for tuberculosis treatment non-adherence in Mukono district

Factors associated with antiretroviral treatment adherence among people living with HIV in Guangdong Province, China: a cross sectional analysis

A model to predict adherence to antiretroviral therapy among people living with HIV

Contact Info

Product

Resources

About