Version 1
: Received: 25 May 2024 / Approved: 27 May 2024 / Online: 27 May 2024 (13:18:48 CEST)
How to cite:
Asghari Ilani, M.; Kavei, A.; Moftakhar Tehran, S. A Comparative Analysis of Machine Learning Models for Lung Cancer Prediction: From Traditional Algorithms to Deep Learning Approaches. Preprints2024, 2024051742. https://doi.org/10.20944/preprints202405.1742.v1
Asghari Ilani, M.; Kavei, A.; Moftakhar Tehran, S. A Comparative Analysis of Machine Learning Models for Lung Cancer Prediction: From Traditional Algorithms to Deep Learning Approaches. Preprints 2024, 2024051742. https://doi.org/10.20944/preprints202405.1742.v1
Asghari Ilani, M.; Kavei, A.; Moftakhar Tehran, S. A Comparative Analysis of Machine Learning Models for Lung Cancer Prediction: From Traditional Algorithms to Deep Learning Approaches. Preprints2024, 2024051742. https://doi.org/10.20944/preprints202405.1742.v1
APA Style
Asghari Ilani, M., Kavei, A., & Moftakhar Tehran, S. (2024). A Comparative Analysis of Machine Learning Models for Lung Cancer Prediction: From Traditional Algorithms to Deep Learning Approaches. Preprints. https://doi.org/10.20944/preprints202405.1742.v1
Chicago/Turabian Style
Asghari Ilani, M., Ashkan Kavei and Saba Moftakhar Tehran. 2024 "A Comparative Analysis of Machine Learning Models for Lung Cancer Prediction: From Traditional Algorithms to Deep Learning Approaches" Preprints. https://doi.org/10.20944/preprints202405.1742.v1
Abstract
Driven by the importance of early detection for improving patient outcomes, this study investigates the effectiveness of various machine learning algorithms in predicting lung cancer based on clinical data. Lung cancer remains a significant global health concern, and this research seeks to contribute to advancements in early diagnosis through the application of machine learning techniques. The dataset consists of 385 training and 97 test samples, with a k-fold cross-validation approach (k=5) utilized to mitigate overfitting. Additionally, the ADASYN oversampling technique is employed to address class imbalance. Our analysis includes traditional algorithms such as Logistic Regression and Decision Trees, as well as ensemble methods like XGBoost, LGBM, and AdaBoost. Furthermore, we explore the effectiveness of deep learning models, particularly Deep Neural Networks (DNN). Results demonstrate promising accuracy rates across all models, with some outperforming others in terms of precision, recall, and F1-score. Our findings reveal that LGBM achieves the highest accuracy among all models, with an accuracy rate of 96.91%. It also exhibits superior performance in terms of precision, recall, and F1-score, particularly in classifying both positive and negative instances of lung cancer.
Public Health and Healthcare, Health Policy and Services
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.