Machine Learning Approach in Lung Cancer Prediction

Zhenjie Gao

2025

Abstract

As one of the global concerns, cancer has been considered as the most threaten heterogenous disease. Therefore, predicting cancer is a key determinant to identify potential patients, thus earlier strategies and interventions can be applied in order to decrease death rate. Machine learning is a robust technique in field of medication that embodies a huge variety of categorical and predictable approach that provide a platform for human beings to learn from past events and improve furtherer in the future. In this paper, Logistic regression, random forest algorithm and K Nearest Neighbours are taken to find the possible relation between lung cancer and other illnesses. As a result, random forest gained the best overall accuracy of 93%. At the same time, AUC_ROC score of 98.7% correspondingly by using classification report and ROC_AUC score. The research provided a version of combining prediction models in cancer symptoms analysis, showing that machine learning has the potential to cooperate with contemporary medical surgery and achieve a better performance in the medical therapy of earlier stage of cancer.

Paper Citation

in Harvard Style

Gao Z. (2025). Machine Learning Approach in Lung Cancer Prediction. In Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-765-8, SciTePress, pages 218-221. DOI: 10.5220/0013681300004670

in Bibtex Style

@conference{icdse25,
author={Zhenjie Gao},
title={Machine Learning Approach in Lung Cancer Prediction},
booktitle={Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2025},
pages={218-221},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013681300004670},
isbn={978-989-758-765-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Machine Learning Approach in Lung Cancer Prediction
SN - 978-989-758-765-8
AU - Gao Z.
PY - 2025
SP - 218
EP - 221
DO - 10.5220/0013681300004670
PB - SciTePress