Prediction of lung disease using machine and deep learning techniques

Abstract

Nowadays lung diseases are becoming a significant problem. In spite of this, Corona virus disease 2019 (COVID-19) has become a pandemic all over the world from last two years which effected lungs of few patients also. Many people are suffering from lungs diseases like Asthma, Allergies, lung cancer etc. The patients whose lung gets affected due to COVID-19 may face some lungs diseases in near future, so it very significant to early diagnosis of lungs diseases to save human life. Machine learning (ML) with feature selection techniques play significant role in the medical field by making diseases diagnoses accurate and early. The objective of this paper is to presents a review of recent ML algorithms and feature selection techniques used to predict lung diseases. As we cover the study between 2020 – 2021, some supervised (SVM, Logistic Regression, Random Forest, Logistic model tree, Bayesian Networks) machine learning techniques on 18,253 data instances and unsupervised (KNN,CNN) machine learning techniques on 8,761 data instances were used to detect accuracy, precision, recall, sensitivity and F1-score in order to predict lung diseases.