An explainable AI-driven biomarker discovery framework for Non-Small Cell Lung Cancer classification. (February 2023)

• Record Type: Journal Article
• Authors: Dwivedi, Kountay; Rajpal, Ankit; Rajpal, Sheetal; Agarwal, Manoj; Kumar, Virendra; Kumar, Naveen
• Is Part Of: Computers in biology and medicine. Volume 153(2023)
• Publication Date: 2023-02
• Subjects: Explainable AI -- Non-Small Cell Lung Cancer -- Biomarkers -- Classification -- Neural network -- Machine learning; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2023.106544
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Non-Small Cell Lung Cancer (NSCLC) exhibits intrinsic heterogeneity at the molecular level that aids in distinguishing between its two prominent subtypes — Lung Adenocarcinoma (LUAD) and Lung Squamous Cell Carcinoma (LUSC). This paper proposes a novel explainable AI (XAI)-based deep learning framework to discover a small set of NSCLC biomarkers. The proposed framework comprises three modules — an autoencoder to shrink the input feature space, a feed-forward neural network to classify NSCLC instances into LUAD and LUSC, and a biomarker discovery module that leverages the combined network comprising the autoencoder and the feed-forward neural network. In the biomarker discovery module, XAI methods uncovered a set of 52 relevant biomarkers for NSCLC subtype classification. To evaluate the classification performance of the discovered biomarkers, multiple machine-learning models are constructed using these biomarkers. Using 10-Fold cross-validation, Multilayer Perceptron achieved an accuracy of 95.74% ( ± 1.27) at 95% confidence interval. Further, using Drug-Gene Interaction Database, we observe that 14 of the discovered biomarkers are druggable. In addition, 28 biomarkers aid the prediction of the survivability of the patients. Out of 52 discovered biomarkers, we find that 45 biomarkers have been reported in previous studies on distinguishing between the two NSCLC subtypes. To the best of our knowledge, the remaining seven biomarkers have not yet been reported for NSCLC subtyping and could be further explored for their contribution to targeted therapy of lung cancer. Highlights: Discovered 52 NSCLC biomarkers using a novel XAI-based deep learning framework. Achieved improved accuracy of 95.7% in subtype classification of NSCLC. 45 out of 52 biomarkers have been identified as lung cancer biomarkers in literature. 14 out of 52 biomarkers are found potentially druggable. The XAI-based feature selection outperforms six popular feature selection methods.