Machine Learning for Prediction the Severity of Restrictive Defect of Lung among Factory Workers

Restrictive lung disease such as pneumoconiosis is the most common disease among people working in dusty environment such as mines and in industry. The gold standard diagnosis for this disease is spirometry, which is used to evaluate the lung performance. However, this tool has certain limitations such as high service costs, limited access to the device, and availability of specialists. These limitations impede early detection of this disease. The objective of this study is to utilize machine learning algorithms to predict the severity of restrictive lung defects among factory workers, aiding in early identification before proceeding to the spirometry test. Three severity classes considered. - Normal, Mild, and Moderate or Severe. By using spirometry’s results and behavioral data among 685 workers from a cross-sectional study in a furniture factory in Thailand, six machine learning algorithms were developed. They were Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, XGBoost and Support Vector Machine (SVM). The best model was Random Forest with Synthetic Minority Oversampling (SMOTE) to deal with imbalance class and Recursive Feature Elimination (RFE) to select most important features. The important features for prediction were weight, height, age, education, hours of work, smoking and mask wearing at the f1-score = 0.746, precision = 0.743, recall = 0.756, and accuracy = 0.75. The model was deployed through a web application for ease of use and the application was used among the factory workers for early screening of the disease. The users were satisfied with the application for its effectiveness, ease of use, time, and cost savings.