Lung cancer poses a significant health challenge, with early detection being crucial for better outcomes. Traditional diagnostic methods have limitations, leading to missed diagnoses. Machine learning offers promise in revolutionizing disease detection by leveraging data and advanced algorithms. This paper explores using machine learning for early lung cancer detection. Sophisticated algorithms enable accurate diagnostic systems, improving efficiency and scalability. Challenges like data quality and interpretability also need to be addressed. This study evaluates machine learning algorithms on real datasets to assess their effectiveness in clinical practice, contributing to the field of healthcare applications. We have found highest accuracy (96.77%), precision (98.33%), recall (98.33%) and F1-score (98.33%) in the Random Forest classifier.
Lung Cancer Detection: A Machine Learning Approach for Early Diagnosis
06.11.2024
612140 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch