AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling
Studies in Health Technology and Informatics · 2025
DOI: 10.3233/shti250903 ↗Kurz gefasst
Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Minh Huu Nhat Le und 14 weiteren Autor:innen. Beteiligte Einrichtung: International Master/Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan. Hauptthemen laut MEDLINE: Deep Learning, Neoplasms, Tumor Microenvironment. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
The tumor immune microenvironment (TME) influences cancer progression and treatment. RNA-Seq has identified six immune subtypes: Wound Healing (WH, C1), IFN- Dominant (IFNG, C2), Inflammatory (INF, C3), Lymphocyte Depleted (LD, C4), Immunologically Quiet (IQ, C5), and TGF-β Dominant (TGFb, C6). This study uses a Convolutional Neural Network (CNN) to classify these subtypes from RNA-Seq data. The model, with ReLU activation and dropout, achieved a 10-fold F1-score of 0.9483 and AUC of 0.9969. Results show CNN’s effectiveness in handling class imbalance and modeling complex gene interactions, outperforming XGBoost, Random Forest, and TabNet. Future work will validate results on independent datasets and incorporate multi-omics data to improve accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- International Master/Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
- Research Center of Artificial Intelligence in Medicine and Health, Taipei Medical University, Taipei, Taiwan.
- AIBioMed Research Group, Taipei Medical University, Taipei, Taiwan.
- Faculty of Information Technology, University of Science, Ho Chi Minh City (HCMC), Vietnam.
- Department of Information Technology, Vaasa University of Applied Sciences, Vaasa, Finland.
- EPAM Data and Analytics, Ho Chi Minh City, Vietnam.
Zitieren
APA
Le, M. H. N., Pham, H. H., Nguyen, H. Q., Ong, H. X., Kha, H. Q., Nguyen, P. K., Nguyen, T. H., Huynh, H. H., Nguyen, D., Nguyen, T. M., Vo, A. T., Nguyen, T. V. M., Nguyen, L. H. P., Tran, T. M. T., & Le, N. Q. K. (2025). AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250903
Vancouver
Le MHN, Pham HH, Nguyen HQ, Ong HX, Kha HQ, Nguyen PK, et al. AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250903
BibTeX
@article{Le2025,
author = {Le, Minh Huu Nhat and Pham, Ha-Hieu and Nguyen, Huy Quoc and Ong, Hong Xuan and Kha, Hien Quang and Nguyen, Phat Ky and Nguyen, Thanh-Huy and Huynh, Han Hong and Nguyen, Dang and Nguyen, Thanh-Minh and Vo, An Thuy and Nguyen, Thuy Vu Minh and Nguyen, Lam Huu Phuc and Tran, Trung Minh Tu and Le, Nguyen Quoc Khanh},
title = {AI-Driven Deep Learning Approach for Pan-Cancer Immune Profiling},
journal = {Studies in Health Technology and Informatics},
year = {2025},
doi = {10.3233/shti250903}
}
EUVIMED