Articles Tập 67 Số CĐ13-HNKH Bệnh viện 19-8 10/09/2026

EVALUATING THE EFFECTIVENESS OF APPLYING A MEDICAL KNOWLEDGE GRAPH COMBINED WITH MULTIMODAL ARTIFICIAL INTELLIGENCE TO SUPPORT EARLY DIAGNOSIS OF NASOPHARYNGEAL CARCINOMA IN VIETNAM

Đào Phạm Thị Bích, Trang Nguyễn Thị Quỳnh, Nam Phan Xuân, Trường Hoàng Hữu, Anh Đinh Tuấn, Yến Trần Hải, Anh Nguyễn Thị Ngọc, Cương Hoàng Minh, Đăng Nguyễn Văn, Hương Nguyễn Thị Thanh, Thủy Nguyễn Thanh, Tuyến Bùi Quang, Hòa Nguyễn Xuân, Đào Nguyễn Thị Anh, Thủy Phạm Thị Bích, Tần Phạm Huy, Đông Khổng Văn, Tâm Trần Văn, Lưu Đoàn Tiến, Chung Lê Duy, Đạt Lê Minh, Mai Bùi Thị, My Nguyễn Diệu, Hằng Nguyễn Thị, Thắng Tống Xuân, Anh Phạm Trần, Hạnh Phạm Thị Phương
DOI: 10.52163/yhc.v67iCD13.6408
0 Views
0 Downloads
Abstract

Objective: To evaluate the effectiveness of an artificial intelligence system integrated with a medical knowledge graph for the early detection of nasopharyngeal carcinoma.

Subjects and Methods: This multicenter study included 1,200 cases, comprising 600 patients with nasopharyngeal carcinoma and 600 controls, collected from five healthcare institutions representing different levels of care in Vietnam. The artificial intelligence system was developed using a multimodal framework integrating medical imaging and clinical data, combined with a medical knowledge graph. Model performance was evaluated on an independent test set using accuracy, sensitivity, specificity, and area under the ROC curve. Results: The male-to-female ratio was 2.5:1 in the nasopharyngeal carcinoma group, compared with 1.2:1 in the control group (p < 0.05). On the independent test set of 180 cases, the system achieved an accuracy of 94.5% (95% CI: 92.1–96.8), sensitivity of 96.2%, specificity of 92.8%, and an AUC of 0.97. The correct detection rate for early-stage disease increased from 60.0% to 85.0%, while the miss rate for lesions smaller than 1 cm decreased from 42.0% to 12.0%. Compared with the image-only model, the multimodal model integrated with a medical knowledge graph improved diagnostic accuracy from 82.4% to 94.5%. Conclusion: The artificial intelligence system integrated with a medical knowledge graph enabled early detection of nasopharyngeal carcinoma, reduced missed small lesions, and improved diagnostic accuracy.

References
[1]
1. International Agency for Research on Cancer. Viet Nam fact sheet. GLOBOCAN 2022, version 1.1; 2024. Google Scholar
[2]
2. Jiang W, Zheng B, Wei H. Recent advances in early detection of nasopharyngeal carcinoma. Discov Oncol. 2024;15:365. doi:10.1007/s12672-024-01242-3. Google Scholar
[3]
3. Yuan Y, Ye F, Wu JH, et al. Early screening of nasopharyngeal carcinoma. Head Neck. 2023;45(10):2700-2709. doi:10.1002/hed.27466. Google Scholar
[4]
4. Wang KH, Austin SA, Chen SH, Sonne DC, Gurushanthaiah D. Nasopharyngeal carcinoma diagnostic challenge in a nonendemic setting: our experience with 101 patients. Perm J. 2017;21:16-180. doi:10.7812/TPP/16-180. Google Scholar
[5]
5. Chen JW, Lin ST, Lin YC, Wang BS, Chien YN, Chiou HY. Early detection of nasopharyngeal carcinoma through machine-learning-driven prediction model in a population-based healthcare record database. Cancer Med. 2024;13(7):e7144. doi:10.1002/cam4.7144. Google Scholar
[6]
6. Xu J, Wang J, Bian X, Zhu JQ, Tie CW, Liu X, et al. Deep learning for nasopharyngeal carcinoma identification using both white light and narrow-band imaging endoscopy. Laryngoscope. 2022;132(5):999-1007. doi:10.1002/lary.29894. Google Scholar
[7]
7. Wang SX, et al. The detection of nasopharyngeal carcinomas using a deep convolutional neural network-based artificial intelligence system. Laryngoscope. 2024;134(1):127-135. doi:10.1002/lary.30781. Google Scholar
[8]
8. He Z, Zhang K, Zhao N, et al. Deep learning for real-time detection of nasopharyngeal carcinoma during nasopharyngeal endoscopy. iScience. 2023;26:107463. doi:10.1016/j.isci.2023.107463. Google Scholar
[9]
9. Yue Y, Zeng X, Lin H, et al. A deep learning based smartphone application for early detection of nasopharyngeal carcinoma using endoscopic images. npj Digit Med. 2024;7:384. doi:10.1038/s41746-024-01403-2. Google Scholar
[10]
10. Shi Y, et al. Artificial intelligence-assisted detection of nasopharyngeal carcinoma on endoscopic images: a national, multicentre, model development and validation study. Lancet Digit Health. 2025;7(6):100869. doi:10.1016/j.landig.2025.03.001. Google Scholar
[11]
11. Zhou HY, Yu Y, Wang C, et al. A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics. Nat Biomed Eng. 2023;7:743-755. doi:10.1038/s41551-023-01045-x. Google Scholar
[12]
12. Wang S, Lin M, Ghosal T, Ding Y, Peng Y. Knowledge graph applications in medical imaging analysis: a scoping review. Health Data Sci. 2022;2022:9841548. doi:10.34133/2022/9841548. Google Scholar
[13]
13. Huang Q, et al. Knowledge graph based reasoning in medical image analysis: a scoping review. Comput Biol Med. 2024;182:109100. doi:10.1016/j.compbiomed.2024.109100. Google Scholar
[14]
14. Sadeghi Z, Alizadehsani R, Cifci MA, et al. A review of explainable artificial intelligence in healthcare. Comput Electr Eng. 2024;122:109370. doi:10.1016/j.compeleceng.2024.109370. Google Scholar