Machine Learning-Driven Early Detection And Monitoring Of Respiratory Disorder Using PCO₂ Analysis

Respiratory disorders like Chronic Obstructive Pulmonary Disease (COPD), asthma, and Acute Respiratory Distress Syndrome (ARDS) pose significant health risks worldwide. This study presents a machine learning-driven framework for early detection and monitoring of these conditions using Partial Pressure of Carbon Dioxide (PCO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf>) analysis. The methodology employs the Chi<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> Probability Density Function (Chi<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> PDF) and Cuckoo Search (CS) model for dimensionality reduction. Harmonic Search (HS) and Particle Swarm Optimization (PSO) are utilized for optimized feature selection. Models such as Nonlinear Regression (NLR), Gaussian Mixture Model (GMM), Linear Regression (LR), Support Vector Machine with Radial Basis Function (SVM-RBF), and Logistic Regression (LoR) are used for disorder detection. The proposed system achieved an accuracy of 95.71. This approach offers a non-invasive, cost-effective solution to enhance respiratory healthcare and improve patient outcomes.