A Comparative Study on AI-Driven Integration of Multisource Data for Prediction and Classification of Chronic Respiratory Diseases

Resumen

The epidemiological study of disease, such as chronic respiratory disease such as COPD and asthma, is complicated by the heterogeneity of the population of India. Smoking, indoor air pollution and exposure at the workplace are shared risk factors for such diseases. By 2020, respiratory diseases were the reason for the large percentage of deaths, and therefore precise epidemiological mapping and intervention methods were even more important. The lung's main job is to supply oxygen to the blood so that it can circulate throughout the body. Respiratory disease and breathlessness can be induced by infections of the lung. A multifaceted interaction of environmental, occasion-related, genotypic, and other variables results in respiratory disease. Air pollutants from the workplace and near surroundings can cause or worsen lung cancer, asthma, and Chronic Obstructive Pulmonary Disease (COPD). The primary objectives of this study were the identification of the optimal dataset for respiratory disease predetermination and the helping with the technology developments required for early detection. Based on the outcomes, the amalgamation of machine learning approaches with comprehensive datasets might significantly increase predetermination accuracy. In addition, stimulating collaboration between healthcare specialists and technology developers might unlock modern preventative processes and epistemological instruments. Extensive Artificial Intelligence (AI) and Machine Learning (ML) procedures with image, clinical, and breath sound datasets constitute a comprehensive approach for respiratory disease predetermination.