Conectar
Healthcare utilisation (HU) is key to improving the health of residents in urban informal settlements. This study aimed to explore household-level factors influencing HU among informal settlement households in Freetown, Sierra Leone.
Cross-sectional survey.
Three informal settlements (Cockle Bay, Dwarzark and Moyiba) in Freetown, Sierra Leone.
Primary data from 4871 households were collected during the Health and Wellbeing survey conducted between April and May 2023, targeting households with adults aged 18 years and older.
The primary outcomes were households HU both within and outside informal settlements. Household-level predisposing and enabling explanatory variables were derived from Andersen’s Behavioural Model of HU.
Disability in households increases HU within settlements (especially in Dwarzark, 13% and Moyiba, 10%) but is less likely outside. Households engaged in income-generating activities are more likely to seek healthcare within settlements, but 12% less likely outside in Cockle Bay and Dwarzark. Food insecurity decreases HU within Dwarzark (9%) and increases HU outside by 174% in Moyiba. Longer water fetching times and water shortages were associated with higher HU (between 6% and 16%) within settlements, especially in Cockle Bay and Dwarzark. Clean water sources (eg, piped dwelling, bowser, surface, bottled) were consistently associated with higher HU both within and outside settlements. Shared sanitation facilities (such as shared toilets) were positively associated with HU both within and outside settlements, particularly in Dwarzark and Moyiba. Households with income from fishing, informal salaried work and bike riding showed higher HU both within and outside settlements, especially in Dwarzark and Moyiba.
We identified strong settlement-specific patterns of household-level factors that influence HU both within and outside Freetown’s informal settlements. These findings provide a foundation for developing targeted policies such as strengthening local services, addressing affordability and accessibility barriers and supporting vulnerable occupation groups.
by Nilavro Das Kabya, MD Shaifullah Sharafat, Rahimul Islam Emu, Mehrab Karim Opee, Riasat Khan
Malabar spinach is a nutrient-dense leafy vegetable widely cultivated and consumed in Bangladesh. Its productivity is often compromised by Alternaria leaf spot and straw mite infestations. This work proposes an efficient and interpretable deep learning framework for automatic Malabar spinach leaf disease classification. A curated dataset of Malabar spinach images collected from Habiganj Agricultural University and supplemented with public samples was categorized into three classes: Alternaria, straw mite, and healthy leaves. A lightweight SpinachCNN established a strong baseline, while Spinach-ResSENet, enhanced with squeeze-and-excitation modules, improved channel-wise attention and feature discrimination. A customized Vision Transformer (SpinachViT) and SwinV2-Base were further investigated to assess the benefits of transformer-based architectures under limited data. To mitigate annotation scarcity, we employed SimSiam-based self-supervised pretraining on unlabeled images, followed by supervised fine-tuning with cross-entropy or a hybrid objective combining cross-entropy and supervised contrastive loss. The best-performing domain-optimized model, SimSiam-CBAM-ResNet-50, incorporated Convolutional Block Attention Modules and achieved 97.31% test accuracy, 0.9983 macro ROC-AUC, and low calibration error, while maintaining robustness to Gaussian and salt-and-pepper noise. Although a SwinV2-Base benchmark pretrained on ImageNet-22k reached slightly higher accuracy (97.98%, 98.99% with test-time augmentation), its 86.9M parameters and reliance on large-scale pretraining reduce feasibility for edge deployment. In contrast, the SimSiam-CBAM model offers a more parameter-efficient and deployment-friendly solution for real-world agricultural applications. Model decisions are interpretable via Grad-CAM, Grad-CAM++, and LayerCAM, which consistently highlight biologically relevant lesion regions. The spinach dataset used in this study is publicly available on: https://huggingface.co/datasets/saifullah03/malabar_spinach_leaf_disease_dataset.
FreshRSS 