Predicting Ceramic Workers’ Lung Health via X-ray Using Machine Learning

Occupational exposure to ceramic dust can cause fibrosis, pneumoconiosis, silicosis, and TB. Early detection and precise diagnosis of these disorders are critical to avoiding serious sequelae. This study examines machine learning strategies for evaluating X-ray images and predicting lung health outcomes in ceramic workers. Advanced algorithms, including deep learning models such as convolutional neural networks (CNNs) and long short-term memory (LSTM) networks, as well as traditional methods such as support vector machines (SVMs) and random forests, are evaluated for their ability to detect detrimental lung transformations The research emphasizes its ability to detect fibrosis, pneumoconiosis, and discriminate silicosis phases while overcoming hurdles such as unbalanced datasets and noisy imaging data. Using a dataset of 450 X-ray pictures of patients obtained from the ceramic industry in Morbi, Gujarat, this study intends to develop early diagnosis skills, improve health outcomes, and contribute to occupational safety standards in the ceramic sector.