Revolutionizing Disaster Healthcare

During times of disaster, the impact on public health can be profound, with challenges ranging from vector borne diseases like malaria to traumatic injuries such as bone fractures. However, the availability of medical professionals is often limited due to infrastructure damage and transportation challenges, leading to delays in diagnosis and treatment. To address these challenges, the paper propose a solution leveraging artificial intelligence (AI) technology to automate the detection of malaria and bone fractures using Deep Learning techniques, specifically Convolutional Neural Networks (CNNs). Datasets comprising images of malaria infected and uninfected cells, as well as fractured and normal bone X-rays, is collected and annotated which are then used to train and evaluate CNN models, including YOLOv5,YOLOv7,YOLOv8,ResNet and AlexNet. The best-performing model is integrated into a mobile application, allowing individuals without technical expertise to upload images and receive timely health assessments. By enhancing health issue detection and management in disaster situations, our approach aims to improve relief efforts and minimize the impact on public health.