ARTIFICIAL INTELLIGENCE DRIVEN AND COMPARATIVE ANALYSIS OF PULMONARY DISEASE PREDICTION EMPLOYING RANDOM FOREST FOR ACCURATE DIAGNOSIS
Keywords:
Machine Learning, Bio-Informatics, Random Forest, Cancer, Artificial Intelligence, Pulmonary diseasesAbstract
Pulmonary diseases, such as chronic obstructive pulmonary disease (COPD), pneumonia, and tuberculosis, continue to be leading contributors to global morbidity and mortality. Accurate and early diagnosis remains critical in improving patient outcomes and reducing healthcare burdens. This study proposes an artificial intelligence (AI)-driven approach for pulmonary disease prediction using the Random Forest (RF) algorithm, known for its robustness, accuracy, and interpretability. Clinical datasets comprising structured data, including chest X-ray images, patient demographics, symptoms, and medical history, were preprocessed and analyzed using ensemble machine learning techniques. The proposed model achieved a high classification accuracy of 94.8%, outperforming traditional models like Logistic Regression and Support Vector Machine in precision, recall, and F1-score. The integration of AI into pulmonary disease diagnostics has demonstrated promising potential in improving detection rates, especially in resource-constrained environments. The Lung Cancer Dataset comprises 5000 records and 18 attributes, detailing demographic information, lifestyle factors, health indicators, and family history related to lung cancer. It includes data on age, gender, smoking habits, exposure to pollution, mental stress, long-term illness, energy levels, immune weakness, breathing issues, alcohol consumption, throat discomfort, oxygen saturation, chest tightness, and family history of lung cancer and smoking. The dataset was utilised for analyzing risk factors and understanding the impact of various health and lifestyle factors on lung cancer. This research contributes to the growing field of AI-assisted healthcare by providing a reliable and interpretable model capable of assisting clinicians in early and accurate pulmonary disease diagnosis.
Published
How to Cite
Issue
Section
FUDMA Journal of Sciences