Early-Stage Lung Cancer Prediction: A Machine Learning Approach

Predicting patients’ lung cancer has become an important research topic for both medical and informatics experts. Machine learning (ML) now exerts considerable influence in the healthcare field, thanks to its formidable computational capacity, which makes it possible to establish an early prognosis of disease through accurate data analysis. This research inquiry examined five ML algorithms: K-nearest neighbors (KNN), Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), and Support Vector Machine (SVM) for the purpose of forecasting lung cancer during its early stages. To achieve this objective, various performance metrics were employed to assess ML algorithms for lung cancer prediction. The comparative methodology unveils that the proposed LR and SVM classifiers have attained a notable precision of 90.3%, making them effective techniques for predicting lung cancer data. This substantiated evidence is poised to support healthcare specialists in cost-effective management and providing timely treatment. Its solid foundations strengthen the effectiveness of healthcare interventions and ultimately improve patient outcomes.