Comparative analysis of machine learning models for lung cancer detection

Le résumé fourni par la source

Lung cancer is one of the common and fatal type of cancer today. Improving patient outcomes and survival rates is contingent upon early identification. The authors are using five ML models namely logistic regression, random forest, Bernoulli Naive Bayes, Gaussian Naive Bayes, and support vector machine for identifying lung cancer at early stages. Dataset which are used in this work are from patient demographic and medical imaging scans. Evaluation metrics like recall, F1-score, accuracy, and precision are used to assess performance. Five ML models’ interpretability are explored to learn about the characteristics and classification choices. Obtained results high-lights on the effective machine learning (ML) model for detecting lung cancer in early stages. This work enhances on the insightful of the advantages and disadvantages of more than 4 ML techniques for lung cancer detection. Comprehending the performance attributes of these models is essential for making well-informed decisions in clinical practice and for creating trustworthy screening instruments for early identification and remediation.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.