An Optimized Extreme Gradient Boosting Regressor Approach Based Lung Cancer Detection

DOI

10.2991/978-94-6463-700-7_26How to use a DOI?

Keywords

Lung Cancer Detection; ML Techniques - XGB; XGBR; and OXGBR; Gamma and Lambda hyper-parameters

Abstract

Presently, the pitiful part of this sphere is that the greatest of them, i.e. comprising a few children, youths on top of the ladies, are habituated to smoking. These vigorous smokers instigate nicotine pollution, thereby escalating the percentage of causing cancer to smokers and non-smokers in society. Lung cancer is the primary basis for demises around the globe and it ranks 4th foremost reason of decease in India. Apart from smoking cancer may be caused due to pollution, disclosure to radon and other infections, this rate of cancer rises gradually. When the lung cancer identification is initial then it is possible to cure it at the earliest. Then the amount of possibility of demise owing to lung cancer can be lessened as soon as possible. This forecast is performed these days stem from Artificial Intelligence (AI) related customs with deep learning (DL) or with machine learning (ML) incessant approaches and IoT centered image classifiers. Currently, this research work is application of varied ML algorithms have enormous applicability’s to this arena as of their wise computational expertise for an appropriate forecast of such sicknesses with precise data in view of Lung Cancer (4/30/1992) UC Irvine ML Repository that is utilized here in this exploration.

In-depth investigation and a comprehensive literature analysis in this research work suggested a few algorithms that includes Extreme Gradient Boosting Regressor and continually the next one, i.e., an Optimized Extreme Gradient Boosting Regressor, also reflected as well suited for categorisation of lung cancer. Their experimental outcomes proves that the accuracy, AUC and sensitivity of XGBR and OXGBR are obtained as 91.73%, 0.89, & 77% for the former as well as 94.37%, 0.94 & 91% for the latter respectively. As these results are yet not the desirable ones. Still in future additional hyper-parameters are to be honed to obtain the best desirable outcomes with an intensive investigation put in further continually in this current methodology. For the reason that forecast and execute an additionally honed procedure for prompt identification and exposure of lung cancer besides affording the precise data for the appropriate well-chosen ML algorithm. Then the exact cure is to be tied up for healing this chronic illness, thereby preventing the death and reducing its rate, likewise prolonging the patient’s lifespan cobble together their sustenance intended for their upper limit duration in a healthy way with care.

Copyright

© 2025 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  - Sasikala Dhamodaran
AU  - Shafqat Ul Ahsaan
AU  - Naheeda Zaib
AU  - Shraddha Jaiswal
PY  - 2025
DA  - 2025/04/19
TI  - An Optimized Extreme Gradient Boosting Regressor Approach Based Lung Cancer Detection
BT  - Proceedings of the International Conference on Advancements in Computing Technologies and Artificial Intelligence (COMPUTATIA-2025)
PB  - Atlantis Press
SP  - 318
EP  - 329
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-700-7_26
DO  - 10.2991/978-94-6463-700-7_26
ID  - Dhamodaran2025
ER  -