Planning for healthcare services using geospatial artificial intelligence (geo -ai) in the peri urban areas of Varanasi

Abstract

The rapidly increasing population in peri-urban areas in India has put tremendous strain on the healthcare system. With limited resources, it has become difficult to provide adequate healthcare services to the people living in these areas. This thesis addresses the healthcare challenges faced by peri-urban areas in India, with a focus on Varanasi. The inadequate provision of healthcare facilities and unequal distribution of resources are significant issues in these regions. By using geo-spatial data and AI algorithms, healthcare providers can make data-driven decisions to improve access to healthcare services, reduce health disparities, and prevent and control the spread of infectious diseases. The potential of GeoAI in healthcare is immense. The study aims to plan for provision of healthcare and healthcare services in the peri-urban areas of Varanasi using Geo-AI. by identifying gaps in the current healthcare system and proposing technology-based solutions. The main objectives include identifying shortcomings in peri-urban healthcare sectors, performing a gap assessment, and developing a GeoAI model to reduce the identified gaps. The theoretical frameworks of GeoAI, machine learning, and deep learning models guide the research. the advances in artificial intelligence (AI) and geospatial technology have enabled healthcare providers and policymakers to effectively address this challenge. AI and geospatial technology can help healthcare systems in peri-urban areas identify, analyse, and visualize spatial patterns and trends that can inform decisions relating to healthcare access and quality. By leveraging spatial data and AI techniques, healthcare providers and policymakers can make data-driven decisions to improve healthcare access and quality, reduce disparities, and prevent and control disease. By mapping healthcare services and population density, healthcare providers and policymakers can gain insights into where additional resources need to be allocated. GeoAI can also be used to identify areas where there is a high prevalence of certain diseases or risk factors. Data collection methods include household surveys to study the relationship between socio-economic indicators and healthcare choices, facility surveys to examine the quality of existing healthcare infrastructure, and focused group discussions to gather in-depth community opinions. A total of 70 samples were collected for the primary survey. The results include the development of a model to evenly distribute healthcare facilities and the creation of a mobile application to increase accessibility and simplify healthcare provision. The thesis contributes to iv improving healthcare services and accessibility in peri-urban areas through the utilization of GeoAI techniques.