Detection of Tuberculosis using Chest Xray and Hospital Recommendation System

Tuberculosis (TB) remains an alarming worldwide health issue. Traditional tests for diagnosis, such as sputum smear microscopy and culture, have limited precision and accessibility, especially in resource-constrained areas. Chest X-rays (CXRs) offer a promising alternative for TB detection, providing a non-invasive and widely accessible means of assessing lung health. This research proposes a novel Tuberculosis Detection and Hospital Recommendation System utilizing CXR imaging and demographic variables, aiming to overcome the challenges associated with TB diagnosis and healthcare access. The Tuberculosis Detection portion of the system uses deep learning algorithms trained on a huge dataset of tagged CXR pictures and patient attributes. By leveraging artificial intelligence, this phase aims to predict the presence of TB with high accuracy, offering an automated and objective tool for TB detection. The integration of demographic variables enhances the predictive capability of the model, providing insights into the relationship between patient characteristics and disease status. Through the analysis of CXR images and demographic data, the system enables early and precise identification of TB cases, facilitating timely intervention and treatment initiation. Personalized hospital suggestions are prepared during the hospital recommendation phase, taking into account the patient's preferences, geography, and severity of condition. By considering factors such as proximity, hospital amenities, and patient preferences, the system empowers patients with informed choices while optimizing resource allocation within healthcare systems. This phase enhances patient autonomy and satisfaction by providing tailored recommendations aligned with individual needs and preferences. The comprehensive approach of the proposed system addresses the complexities of TB diagnosis and healthcare access, offering a data-driven solution for improving patient outcomes and public health. Through the utilization of deep learning algorithms, demographic data, and personalized recommendations, the system represents a significant advancement in TB management, contributing to the global efforts to overcome this deadly disease.