Assessing Sick Building Syndrome in Low-Cost Coastal Residential Dwellings

Sick Building Syndrome (SBS) poses considerable health challenges, particularly in rural areas with limited resources and a sensitivity to climate variations. This research conducted a systematic examination of SBS in inexpensive housing within the Sundarban coastal region, taking into account environmental, occupational, geographic, and socio-economic factors. The data were evaluated using the Composite Sick Building Syndrome Index (CSBSI), Artificial Neural Network (ANN) modeling, and a newly introduced Building-Induced Health Hazards Index (BIHHI), which is intended to address multidimensional health risks across systemic, vestibular–gastrointestinal, and mucosal/dermatological categories. The study found that vulnerability to respiratory and eye issues varied by age and occupation. Older individuals faced more respiratory problems, while younger ones reported ocular discomfort. Housewives, students, fishermen, and farmers were particularly affected due to prolonged indoor exposure and environments with moisture or pollutants. Geographic and seasonal differences were noted, with semi-isolated islands showing the most severe symptoms and winter associated with higher instances of SBS due to poor ventilation and low humidity. Regression analyses verified the CSBSI's validity, and ANN models demonstrated predictive accuracy, highlighting machine learning's role in early detection in low-resource settings. The BIHHI is a new methodological advancement that connects symptom-level evaluations with practical policy recommendations. Its flexibility for rural areas vulnerable to climate issues allows for targeted interventions like bioclimatic housing designs and socio-economic support. By integrating advanced indices and predictive modelling, this study provides innovative methods and actionable guidance to reduce health hazards in resource-constrained communities sensitive to climate change.