An explainable AI-driven biomarker discovery framework for Non-Small Cell Lung Cancer classification

Dwivedi, Kountay; Rajpal, Ankit; Rajpal, Sheetal; Agarwal, Manoj; Kumar, Virendra; Kumar, Naveen

doi:10.1016/j.compbiomed.2023.106544

Cited by 17 publications

(8 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The National Cancer Institute's SEER dataset is a comprehensive source of cancer statistics in the United States. It contains data on cancer incidence, survival, and mortality, as well as demographic and clinical information on cancer patients [30]. The SEER database encompasses around 34.6% of the American populace and comprises data from 18 diverse geographical zones, encompassing urban and rural areas.…”

Section: Methodsmentioning

confidence: 99%

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

Makubhai,

R Pathak,

R Chandre

2024

IJ-AI

View full text Add to dashboard Cite

Lung cancer prediction is crucial for early detec-tion and treatment, and explainable AI models have gained attention for their interpretability. This study aims to compare various explainable AI models using diverse datasets for lung cancer prediction. Clinical, genomic, and imaging data from multiple sources were collected, prepro-cessed, and used to train models such as Logistic Regression, SVC-Linear, SVC-rbf, Decision Tree, Random Forest, AdaBoost Classifier, and XGBoost Classifier. Preliminary results indicate that Random Forest achieved the highest accuracy of 98.9% across multiple datasets. Evaluation metrics such as accuracy, precision, recall, and F1 score were utilized, along with interpretability techniques like feature importance rankings and rule extraction methods. The study's findings will aid in identifying effective and interpretable AI models, facilitating early detection and treatment decisions for lung cancer.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

Makubhai,

R Pathak,

R Chandre

2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Depending on the choice of feature extraction to be performed, the availability of outcome labels, and the need for exploratory analysis, the selection of optimal biomarkers and operationalizing the biomarker platform may proceed as a supervised, semi‐supervised, self‐supervised, or unsupervised learning task. Moreover, when convolutional neural networks are employed in supervised or semi‐supervised learning, explainability analysis may need to be performed to ensure that raw inputs of discriminatory biomarkers considered in predicting a target variable are highlighted to support efficiency and scalability during downstream performance analysis (Dwivedi et al, 2023; van der Velden et al, 2022).…”

Section: Implementing Ai‐assisted Saliva Liquid Biopsy For Oral and M...mentioning

confidence: 99%

Artificial intelligence in salivary biomarker discovery and validation for oral diseases

Adeoye

2023

Oral Diseases

View full text Add to dashboard Cite

Salivary biomarkers can improve the efficacy, efficiency, and timeliness of oral and maxillofacial disease diagnosis and monitoring. Oral and maxillofacial conditions in which salivary biomarkers have been utilized for disease‐related outcomes include periodontal diseases, dental caries, oral cancer, temporomandibular joint dysfunction, and salivary gland diseases. However, given the equivocal accuracy of salivary biomarkers during validation, incorporating contemporary analytical techniques for biomarker selection and operationalization from the abundant multi‐omics data available may help improve biomarker performance. Artificial intelligence represents one such advanced approach that may optimize the potential of salivary biomarkers to diagnose and manage oral and maxillofacial diseases. Therefore, this review summarized the role and current application of techniques based on artificial intelligence for salivary biomarker discovery and validation in oral and maxillofacial diseases.

show abstract

“…The aforementioned studies typically employed conventional machine learning algorithms such as random forest or support vector machines to classify NSCLC and/or identify signature biomarkers. Deep learning-based techniques have proven their expertise over traditional algorithms in lung cancer classiőcation, diagnosis, and survival prediction [7,18,19]. The caveat, however, in employing deep learning-based models, especially deep neural networks, is their highly opaque nature of decision-making [20], which in turn brings upon a paramount trust concern among pathologists [21].…”

Section: Motivation and Contributionmentioning

confidence: 99%

“…The caveat, however, in employing deep learning-based models, especially deep neural networks, is their highly opaque nature of decision-making [20], which in turn brings upon a paramount trust concern among pathologists [21]. The explainable AI (XAI) concept, a recent advancement in developing trustworthy machine/deep learning models, attempts to overcome this trust issue by providing reasonable interpretations (such as the contribution of individual features in classiőcation) of the inherent processing of the deep learning models [7,22,23].…”

Section: Motivation and Contributionmentioning

confidence: 99%

An Explainable Ensemble of Neural Networks Precisely Discovers NSCLC Signature Biomarkers

Dwivedi

Kishore²,

Rajpal

et al. 2023

Preprint

View full text Add to dashboard Cite

This work proposes a novel framework of an explainable ensemble of neural networks to classify NSCLC samples into adenocarcinoma and squamous cell carcinoma, using DNA methylation data. The framework utilizes an ensemble of shallow neural networks and soft-voting decision fusion for classification. Subsequently, these neural networks are interpreted via SHapley Additive exPlanations (SHAP) to highlight the most relevant DNA methylation CpG probes. The proposed framework-based model achieves a classification accuracy of 0.989, outperforming other ensemble models such as XGboost, Random Forest, AdaBoost, CatBoost, and GradientBoosting. SHAP analysis reveals 702 relevant CpG probes, that are mapped to a set of 499 signature biomarkers. While 104 of these signature biomarkers are potentially druggable (using DGIdb database), 40 of them overlap with the OncoKB cancer genes list. In the future, the framework could be made robust enough to classify other carcinomas. Moreover, multiomics data-based classification could provide better accuracy and more stable biomarkers.

show abstract

An explainable AI-driven biomarker discovery framework for Non-Small Cell Lung Cancer classification

Cited by 17 publications

References 69 publications

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

Comparative analysis of explainable AI models for predicting lung cancer using diverse datasets

Artificial intelligence in salivary biomarker discovery and validation for oral diseases

An Explainable Ensemble of Neural Networks Precisely Discovers NSCLC Signature Biomarkers

Contact Info

Product

Resources

About