Research Article
Leveraging Machine Learning Models to Predict HIV/AIDS Treatment Interruption in Patients in Machakos County, Kenya
Issue:
Volume 11, Issue 6, December 2025
Pages:
158-170
Received:
2 October 2025
Accepted:
17 October 2025
Published:
7 November 2025
DOI:
10.11648/j.ijdsa.20251106.11
Downloads:
Views:
Abstract: HIV/AIDS remains a major global health challenge, with Sub-Saharan Africa carrying the highest burden. In Kenya, where adult prevalence is 4.3%, treatment interruption (IIT) continues to undermine antiretroviral therapy (ART) outcomes. This study applied machine learning (ML) to identify predictors of IIT and guide interventions in Machakos County, where prevalence is 3.3% and relies on manual appointment management of patients, physical tracing and phone tracing of patients. A retrospective cross-sectional study used secondary data from KenyaEMR covering 14,339 adults on ART between 2020 and 2024. Data preprocessing included cleaning, anonymization, imputation, encoding, LASSO feature selection, and SMOTE oversampling. Descriptive statistics and chi-square tests assessed associations, while Random Forest (RF), XGBoost, and Support Vector Machine (SVM) models were trained and validated to predict IIT. Overall, 910 patients (6%) experienced IIT. Risk was highest among adolescents and young adults (15-24 years), single individuals, urban residents, patients with viral load ≥1000 cps, those on ART <12 months, TB co-infected, and non-DTG regimen users. Poor adherence, unstable status, lack of phone ownership, and shorter refill durations also predicted IIT. Non-significant factors included sex, CD4 count, counseling, and clinic workload. Among models, RF achieved the best performance (recall 0.97, precision 0.87, F1 0.92, AUROC 0.96, accuracy 0.91), outperforming XGBoost and SVM. IIT in Machakos County is shaped by demographic, clinical, socioeconomic, and health system factors. Random Forest showed the best predictive capacity, highlighting the value of ML for early identification of at-risk patients. Strategies should include DTG scale-up, early retention support, multi-month dispensing, and digital health interventions. Integrating predictive analytics into EMRs can strengthen HIV program outcomes.
Abstract: HIV/AIDS remains a major global health challenge, with Sub-Saharan Africa carrying the highest burden. In Kenya, where adult prevalence is 4.3%, treatment interruption (IIT) continues to undermine antiretroviral therapy (ART) outcomes. This study applied machine learning (ML) to identify predictors of IIT and guide interventions in Machakos County,...
Show More
Research Article
Stacked Ensemble Classifier for Adoption of Point-of-Collection Water Treatment Technology Among Households in Western Kenya
Issue:
Volume 11, Issue 6, December 2025
Pages:
171-177
Received:
17 September 2025
Accepted:
29 September 2025
Published:
10 November 2025
DOI:
10.11648/j.ijdsa.20251106.12
Downloads:
Views:
Abstract: TheDispensersforSafeWaterprogramunderEvidenceActionpromotespoint of collection water treatment through the installation of chlorine dispenser gadgets in rural parts of Kenya. Although the initiative has improved access to safe drinking water, monitoring household adoption remained a challenge during the COVID-19 pandemic, which limited field-based data collection and led to increased dependence on phone surveys. In addition, technology adoption data are often imbalanced, which poses difficulties for traditional classification methods. This study aimed to develop and implement a stacking ensemble classifier to model the adoption of chlorine dispensers among households in western Kenya. Data were collected from 27,457 households. The analysis used structured household, promoter and spot check survey data. The key variables included chlorine availability, user knowledge, household demographics, and engagement with promoters. RF, ANN, and NB models were trained and evaluated individually, then combined using a stacked ensemble approach. The ensemble model outperformed all base learners, achieving the highest accuracy (69.1%) and AUC (0.6959). The variable importance analysis revealed that the presence of chlorine and the knowledge of the user were the strongest predictors of adoption. In conclusion, ensemble learning provides a reliable method for modeling behavioral adoption in public health interventions. The findings offer practical insights for programs and demonstrate the potential of machine learning in improving, targeting and monitoring of safe water initiatives in low-resource settings.
Abstract: TheDispensersforSafeWaterprogramunderEvidenceActionpromotespoint of collection water treatment through the installation of chlorine dispenser gadgets in rural parts of Kenya. Although the initiative has improved access to safe drinking water, monitoring household adoption remained a challenge during the COVID-19 pandemic, which limited field-based ...
Show More
,
Charles Katila
