Lung cancer risk prediction using augmented machine learning pipelines with explainable AI - Data augmentation for class imbalance

Aug 3, 2026

Lung cancer remains a leading cause of cancer-related mortality, making early, accurate risk prediction essential. This study addresses performance degradation caused by class imbalance in small clinical lung cancer datasets by pairing classification models with data augmentation methods. Comparative experiments evaluate multiple augmentation-classifier combinations, showing that K-Means SMOTE with a Multi-Layer Perceptron achieves the best results (93.55% accuracy, AUC-ROC 96.76%). LIME is applied to improve interpretability and support transparent medical decision-making.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Introduction

Related challenges and motivation

Machine learning for lung cancer risk prediction

Class imbalance and data augmentation

Study approach and evaluation criteria

TYPE Original Research PUBLISHED 03 September 2025 DOI 10.3389/frai.2025.1602775 OPEN ACCESS EDITED BY Giuseppe De Pietro, National Research Council (CNR), Italy REVIEWED BY Chao Zhang, Shanxi University, China Md Afroz, University of Prince Mugrin, Saudi Arabia *CORRESPONDENCE Saranyaraj D [saranyaraj.d@vit.ac.in](saranyaraj.d@vit.ac.in) RECEIVED 02 April 2025 ACCEPTED 31 July 2025 PUBLISHED 03 September 2025 CITATION M S P, D S and Chakrabortty A (2025) Lung cancer risk prediction using augmented machine learning pipelines with explainable AI. Front. Artif. Intell. 8:1602775 . doi: 10.3389/frai.2025.1602775 COPYRIGHT © 2025 M S, D and Chakrabortty. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. Lung cancer risk prediction using augmented machine learning pipelines with explainable AI Pavithran M S, Saranyaraj D* and Anirban Chakrabortty School of Computer Science and Engineering, Vellore Institute of Technology, Chennai Campus, Tamil Nadu, India Lung cancer remains the leading cause of cancer-related deaths worldwide, making early and precise diagnosis is critical for improving the patient survival rates. Machine learning has shown promising results in predictive analysis for lung cancer prediction. However, class imbalance in clinical datasets negatively impacts the performance of Machine Learning classifiers, leading to biased predictions and reduced accuracy. In an attempt to address this issue, various data augmentation techniques were applied alongside classification models to enhance predictive performance. This study evaluates data augmentation techniques paired with machine learning classifiers to address class imbalance in a small lung cancer dataset. A comparative analysis was conducted to assess the impact of different augmentation techniques with classification models. Experimental findings demonstrate that K-Means SMOTE, combined with a Multi-Layer Perceptron classifier, achieves the highest accuracy of 93. 55% and an AUC-ROC score of 96.76%, surpassing other augmentation-classifier combinations. These results underscore the importance of selecting optimal augmentation methods to improve classification performance. Furthermore, to ensure model interpretability and transparency in medical decision-making, LIME is utilized to provide insights into model predictions. The study highlights the significance of advanced augmentation techniques in addressing data imbalance, ultimately enhancing lung cancer risk prediction through machine learning. The findings contribute to the growing field of AI-driven healthcare by emphasizing the necessity of selecting effective augmentation-classifier pairs to develop more accurate and reliable diagnostic models. Due to the dataset’s high cancer prevalence (87.45%) and limited size, this work is a preliminary methodological comparison, not a clinical tool. Findings emphasize the importance of augmentation for imbalanced data and lay the groundwork for future validation with larger, representative datasets. KEYWORDS lung cancer prediction, class imbalance, explainable AI, LIME, SMOTE 1 Introduction Lung cancer is one of the most prevalent causes of cancer deaths worldwide, accounting for approximately 1.8 million deaths annually. Irrespective of the advances in medicine and treatment procedures, early detection is a significant concern. The five-year survival rate of lung cancer is significantly high in the initial stage of detection, but most of the cases are diagnosed in late stages due to the reason that the disease does not sho

FAQs

What problem does the study focus on in lung cancer prediction?

The study focuses on class imbalance in small lung cancer datasets, which can bias classifiers toward the majority class and reduce sensitivity and recall.

Which augmentation-classifier combination performs best?

K-Means SMOTE combined with a Multi-Layer Perceptron classifier achieves the highest reported accuracy (93.55%) and AUC-ROC (96.76%).

How does the study support explainable and transparent predictions?

LIME is used to provide insights into model predictions, aiming to improve interpretability in medical decision-making.

Aug 3, 2026

Upload by Evangeline