Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This study employs a Random Forest classifier and a MobileNetV2 image classification model to analyze the relationship between waste disposal practices and health outcomes in Atonsu, Kumasi, Ghana. The classifier achieved a macro F1 score of 0.63, identifying waste disposal methods as key predictors of illness, while the image model successfully sorted waste with 88.2% accuracy, demonstrating its potential in resource-constrained settings. These findings provide quantitative validation of previously qualitative observations regarding community health and underscore the need for institutional support in implementing technological solutions.
Waste disposal methods significantly predict illness types, revealing a critical link between sanitation practices and public health in Ghana.
The inappropriate disposal of solid waste remains a significant public health and environmental concern worldwide, including in Ghana. Poor sanitation and improper waste management practices contribute to substantial economic costs and avoidable deaths annually. In 2022, a field study in Atonsu, Kumasi, Ghana, reported a community-perceived relationship between household waste disposal and illness patterns, but only through descriptive analysis without quantitative validation. This study extends that investigation using two data-driven approaches. First, a Random Forest classifier was developed to predict illness categories using waste disposal practices and demographic survey data. On a held-out group of respondents who reported illness (N=69), the model obtained a macro F1 score of 0.63, with disposal method emerging as the most important substantive predictor of illness type. Second, a MobileNetV2 image classification model enabled automated waste sorting via visual recognition, achieving 88.2% accuracy and a macro F1 score of 0.87 on the test set (N=415). The vision-based approach offers an affordable, camera-driven alternative to complex multi-sensor systems, making it highly suitable for resource-constrained settings. Taken together, the findings provide quantitative evidence for a community health relationship previously documented only qualitatively. They demonstrate the potential for automated waste-sorting in low-resource environments. Importantly, the results illustrate that technological performance alone does not guarantee public health improvements; effective institutional support and implementation are equally necessary.