Performance assessment of ensemble learning methods in COPD diagnosis

Chronic Obstructive Pulmonary Disease (COPD) is a progressive lung disorder that result in ongoing restriction of airflow restriction, significantly affecting quality of life and increasing mortality rates. Accurate assessment and early determination of COPD severity are essential for patient-specific treatments and timely medical interventions. Current diagnostic approaches rely on pulmonary function tests, medical history evaluations, and symptom assessments, yet they often fail to provide reliable and consistent results. Machine learning methods have become data-driven approaches for disease classification and predictive modeling in healthcare. Using big data methods advances both diagnostic precision and clinical choice-making approaches. Implementation of machine learning algorithms would improve the classification process through modified diagnostic methods that remedy standard diagnostic system deficiencies. This research explores the effectiveness of machine learning-based approaches in COPD classification, emphasizing their role in improving diagnostic reliability. The study investigates various models to determine their accuracy and efficiency in assessing COPD severity. The findings contribute to the growing body of knowledge on AI-driven medical diagnostics, aiming to support healthcare professionals in achieving more precise and timely detection of COPD.