Related Experiment Video
Updated: Sep 25, 2025
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
Published on: June 10, 2025
Application of explainable artificial intelligence in the identification of Squamous Cell Carcinoma biomarkers
Jaishree Meena1, Yasha Hasija1
1Department of Biotechnology, Delhi Technological University, Delhi, India, 110042.
Abstract:
Non-melanoma skin cancers (NMSCs) are the fifth most common type of cancer worldwide, affecting both men and women. Each year, more than a million new occurrences of NMSC are estimated, with Squamous Cell Carcinoma (SCC) representing approximately 20% of all skin malignancies. The purpose of this study was to find potential diagnostic biomarkers for SCC by application of eXplainable Artificial Intelligence (XAI) on XGBoost machine learning (ML) models trained on binary classification datasets comprising the expression data of 40 SCC, 38 AK, and 46 normal healthy skin samples. After successfully incorporating SHAP values into the ML models, 23 significant genes were identified and were found to be associated with the progression of SCC. These identified genes may serve as diagnostic and prognostic biomarkers in patients with SCC.
Insights
Researchers identified 23 significant genes associated with Squamous Cell Carcinoma (SCC) progression using explainable AI and machine learning. These genes show promise as diagnostic and prognostic biomarkers for non-melanoma skin cancer.
Area of Science:
- Oncology
- Bioinformatics
- Artificial Intelligence
Background:
- Non-melanoma skin cancers (NMSCs) are a global health concern, with Squamous Cell Carcinoma (SCC) accounting for a significant portion of diagnoses.
- Early and accurate diagnosis is crucial for effective treatment and improved patient outcomes in SCC.
- Identifying reliable biomarkers can enhance diagnostic and prognostic capabilities for SCC.
Purpose of the Study:
- To discover novel diagnostic biomarkers for Squamous Cell Carcinoma (SCC).
- To leverage eXplainable Artificial Intelligence (XAI) and machine learning for biomarker identification.
- To analyze gene expression data from SCC, actinic keratosis (AK), and healthy skin samples.
Main Methods:
- Utilized XGBoost machine learning models for binary classification of skin samples.
- Applied eXplainable Artificial Intelligence (XAI), specifically SHAP values, to interpret ML model predictions.
- Trained models on gene expression data from 40 SCC, 38 AK, and 46 normal skin samples.
Main Results:
- Successfully integrated SHAP values into the machine learning models.
- Identified 23 genes significantly associated with the progression of SCC.
- These genes demonstrated potential as diagnostic and prognostic indicators.
Conclusions:
- The 23 identified genes represent potential novel biomarkers for SCC.
- XAI combined with ML offers a powerful approach for discovering biomarkers in complex diseases.
- Further validation of these genes could lead to improved diagnostic tools for SCC patients.
