Prediction Analysis of Idiopathic Pulmonary Fibrosis Progression from OSIC Dataset
Sampurna Mandal, Valentina Emilia Bălaş, Rabindra Nath Shaw, Ankush Ghosh
Abstract
Pulmonary fibrosis is a progressive lungs disease which usually gets worse over time. Once this disease damages the lungs, it cannot be cured totally. But early detection and proper diagnosis can help to keep this disease in control. It causes scarring in the lungs over time. As an effect, people face breathing difficulty. It can cause shortness of breath, even at rest. The general causes of pulmonary fibrosis can be exposure to toxic element like coal dust, asbestos fibres, silica dust, hard metal dusts etc. But in majority of the cases, the doctor cannot figure out the exact cause of this disease. That's why this disease is termed as Idiopathic Pulmonary Fibrosis. The objective of this paper is to analyse and compare the performance of various machine leaning models by predicting the final forced volume capacity measurements for each patient and a confidence value. It can be deployed on any computer to predict a patient's severe condition regarding lungs function which is based on a CT scan of the lungs of the patients. Lung function is checked out based on a spirometer output that measures the forced vital capacity (FVC) of the lungs. In the future, early diagnosis of pulmonary fibrosis should be possible. Machine learning model is helping to use the human resources efficiently and it is also reducing the expanses spent on the social and healthcare aspects of this deadly disease.