Lungs Disease Prediction Using Machine Learning And Deep Learning

Abstract

Lung-related illnesses are rapidly emerging as a major global health challenge, impacting millions each year. The surge in respiratory complications after the COVID-19 pandemic has further emphasized the need for early, precise, and efficient diagnostic techniques. While conventional diagnostic methods are trustworthy, they are often time-consuming and heavily dependent on expert interpretation. To overcome these limitations, Machine Learning (ML) and Deep Learning (DL) have begun playing a crucial role in automating and improving lung disease detection.This research examines the use of various ML and DL models for identifying and classifying different lung conditions. Techniques such as Support Vector Machine (SVM), Random Forest (RF), Logistic Regression, K-Nearest Neighbors (KNN), and Convolutional Neural Networks (CNN) are analyzed based on their performance with medical datasets. Their capabilities are compared using standard evaluation metrics including accuracy, precision, recall, and F1-score.Recent studies consistently show that deep learning methods—especially CNNs—achieve better accuracy than traditional ML algorithms. However, challenges such as limited dataset availability, class imbalance, and reduced interpretability of advanced models still persist. Overall, integrating ML and DL approaches offers a promising pathway toward faster, more accurate lung disease diagnosis and improved patient outcomes.