Exploring the Determinants of Lung Cancer: A Machine Learning-Based Approach

DOI

10.2991/978-94-6463-540-9_2How to use a DOI?

Keywords

Lung Cancer; Logical Regression; Pearson Correlation; Random Forest

Abstract

In the current field of medical research, identifying and evaluating the key factors affecting the onset of cancer and especially the lung cancer’s onset is of great significance to improve the early management and diagnosis of lung cancer. This study employed a comprehensive approach, utilizing both the random forest algorithm and logistic regression, to analyze and predict the risk factors associated with lung cancer. Logistic regression algorithm can provide a model for the probabilistic relationship between features and lung cancer risk. Pearson correlation analysis’s feature importance scoring method and random forest algorithm can select the most influential features from numerous potential risk factors to build an efficient lung cancer risk prediction model. The study began with a preliminary analysis of multiple variables in the data set to determine their relevance to lung cancer development. Pearson correlation analysis was employed to assess the magnitude of the linear relationship between each feature and the risk of lung cancer, and random forest algorithm was further used to score and rank the importance of the features. On the basis of feature selection, specific features were selected as input variables for model training, and a lung cancer risk prediction model was constructed by machine learning algorithm. By comparing and analyzing the baseline model constructed with all the features, the selected feature model maintains comparable or even higher prediction accuracy while reducing the model complexity. This result proves that feature selection plays a crucial role in enhancing model efficiency and accuracy.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Hanxuan Ye
PY  - 2024
DA  - 2024/10/16
TI  - Exploring the Determinants of Lung Cancer: A Machine Learning-Based Approach
BT  - Proceedings of the 2024 2nd International Conference on Image, Algorithms and Artificial Intelligence (ICIAAI 2024)
PB  - Atlantis Press
SP  - 7
EP  - 17
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-540-9_2
DO  - 10.2991/978-94-6463-540-9_2
ID  - Ye2024
ER  -