A GraphSAGE Approach to Hepatitis C Virus Detection from Biochemical Graph Representations

Öz

Hepatitis C Virus (HCV) is a common blood-borne pathogen and a leading contributor to chronic liver disease worldwide, including cirrhosis and hepatocellular carcinoma. Early and accurate diagnosis is essential to halt progression and improve outcomes, yet conventional approaches can be invasive and costly, highlighting the need for accessible, non-invasive decision support. This study examines whether representing routine clinical information as relational structure can enhance classification using the publicly available UCI Hepatitis C Virus (HCV) dataset, which contains standard biochemical and demographic variables. Rather than treating each patient independently, patients with similar laboratory profiles were connected through a patient–patient similarity graph, and a graph-based learning approach (GraphSAGE) was applied to leverage these relationships. For context and fairness, widely used non-graph machine learning methods were also evaluated on the same splits. Across repeated runs, the graph-based model achieves very high and stable performance (99.51% for both accuracy and macro-F1) and remains consistently competitive with, and in many cases slightly superior to, traditional models. Because the relational structure is derived directly from routine laboratory values, the learned representations reflect clinically meaningful similarity patterns without requiring additional inputs. Taken together, the findings suggest that reframing standard HCV data as a patient–patient network is a practical and effective strategy for non-invasive computer-aided diagnosis, complementing established baselines while offering a flexible path toward robust, clinically plausible deployment.

Anahtar Kelimeler

• Biochemical Data
• Diagnosis
• Graph Neural Networks
• HCV
• Machine Learning

Biyokimyasal Çizge Gösterimlerinden Hepatit C Virüsü Tespitine Yönelik Bir GraphSAGE Yaklaşımı

Öz

Hepatit C Virüsü (HCV), kan yoluyla bulaşan yaygın bir patojen olup siroz ve hepatoselüler karsinom dâhil olmak üzere dünya genelinde kronik karaciğer hastalıklarının önde gelen nedenleri arasındadır. Hastalığın ilerlemesini durdurmak ve klinik sonuçları iyileştirmek için erken ve doğru tanı esastır; ancak geleneksel yaklaşımlar çoğu zaman invaziv ve maliyetlidir ve bu durum, erişilebilir ve girişimsel olmayan karar destek gereksinimini ortaya koymaktadır. Bu çalışmada, rutin klinik bilginin ilişkisel bir yapı olarak temsil edilmesinin sınıflandırmayı iyileştirip iyileştirmediği, standart biyokimyasal ve demografik değişkenleri içeren kamuya açık UCI Hepatit C Virüsü (HCV) veri kümesi kullanılarak incelenmiştir. Her bir hasta bağımsız ele alınmak yerine, benzer laboratuvar profillerine sahip hastalar bir hasta–hasta benzerlik çizgesi üzerinden birbirine bağlanmış ve bu ilişkilerden yararlanmak üzere çizge tabanlı bir öğrenme yaklaşımı (GraphSAGE) uygulanmıştır. Bağlam ve adil karşılaştırma sağlamak amacıyla, yaygın kullanılan çizge dışı makine öğrenmesi yöntemleri de aynı veri bölünmeleri üzerinde değerlendirilmiştir. Tekrarlanan çalışmalarda, çizge tabanlı model hem doğruluk hem de makro-F1 için %99,51 düzeyinde çok yüksek ve istikrarlı bir performans sergilemekte; geleneksel modellerle tutarlı biçimde rekabetçi kalmakta ve birçok durumda onları az da olsa geride bırakmaktadır. İlişkisel yapının doğrudan rutin laboratuvar değerlerinden türetilmiş olması, ek girdilere ihtiyaç duyulmaksızın öğrenilen temsillerin klinik açıdan anlamlı benzerlik örüntülerini yansıtmasına olanak sağlamaktadır. Birlikte ele alındığında, bulgular standart HCV verisinin hasta–hasta ağı olarak yeniden çerçevelenmesinin girişimsel olmayan bilgisayar destekli tanı için pratik ve etkili bir strateji olduğunu; yerleşik taban modellerini tamamladığını ve sağlam, klinik açıdan makul bir uygulamaya doğru esnek bir yol sunduğunu göstermektedir.

Anahtar Kelimeler

• Biyokimyasal Veriler
• Çizge Sinir Ağları
• HCV
• Makine Öğrenimi
• Teşhis

Kaynakça

1. Jones, A. T., Briones, C., Tran, T., Moreno‐Walton, L., & Kissinger, P. J. (2022). Closing the hepatitis C treatment gap: United States strategies to improve retention in care. Journal of viral hepatitis, 29(8), 588-595. https://doi.org/10.1111/jvh.13685.
2. Stasi, C., Milli, C., Voller, F., & Silvestri, C. (2024). The epidemiology of chronic hepatitis C: where we are now. Livers, 4(2), 172-181. https://doi.org/10.3390/livers4020013.
3. Alizargar, A., Chang, Y. L., & Tan, T. H. (2023). Performance comparison of machine learning approaches on hepatitis C prediction employing data mining techniques. Bioengineering, 10(4), 481. https://doi.org/10.3390/bioengineering10040481.
4. Sharma, K., & Murthy, M. K. (2025). A review of historical landmarks and pioneering technologies for the diagnosis of Hepatitis C Virus (HCV). European Journal of Clinical Microbiology & Infectious Diseases, 1-15. https://doi.org/10.1007/s10096-025-05110-y.
5. Wang, Y., Jie, W., Ling, J., & Yuanshuai, H. (2021). HCV core antigen plays an important role in the fight against HCV as an alternative to HCV‐RNA detection. Journal of Clinical Laboratory Analysis, 35(6), e23755. https://doi.org/10.1002/jcla.23755.
6. Shahid, I., Alzahrani, A. R., Al-Ghamdi, S. S., Alanazi, I. M., Rehman, S., & Hassan, S. (2021). Hepatitis C diagnosis: simplified solutions, predictive barriers, and future promises. Diagnostics, 11(7), 1253. https://doi.org/10.3390/diagnostics11071253.
7. Chen, H., Gao, Y., Li, G., Alam, M., Udayakumar, S., Mateen, Q. N., Rostamian, S., Cilley, K., Kim, S., Cho, G., Gwak, J., Song, Y., Hardie, J. M., Kanakasabapathy, M. K., Kandula, H., Thirumalaraju, P., Song, Y., Parandakh, A., Bigdeli, A., ... Shafiee, H. (2025). Reducing hepatitis C diagnostic disparities with a fully automated deep learning–enabled microfluidic system for HCV antigen detection. Science Advances, 11(12), eadt3803. https://doi.org/10.1126/sciadv.adt3803.
8. Zilouchian, H., Faqah, O., Kabir, M. A., Gross, D., Pan, R., Shaifman, S., Younas, M. A., Haseeb, M. A., Thomas, E., & Asghar, W. (2025). Current and Future Diagnostics for Hepatitis C Virus Infection. Chemosensors, 13(2), 31. https://doi.org/10.3390/chemosensors13020031.

9. Kothawade, S., Padwal, V., Lodha, P., & Pande, V. (2025). Advanced nanotheranostic approaches for hepatocellular carcinoma management. Journal of Medicine, Surgery, and Public Health, 6, 100188. https://doi.org/10.1016/j.glmedi.2025.100188.
10. Türkoğlu, E., Parlak, Z., & Barut, H. Ş. (2022). Assessment of HCV-RNA test results and access rates to antiviral treatment in patients with anti-HCV positivity-a 10-year analysis. Turkish journal of medical sciences, 52(6), 1984-1990. https://doi.org/10.55730/1300-0144.5546.
11. Huang, W., Peng, Y., & Kang, L. (2024). Advancements of non‐invasive imaging technologies for the diagnosis and staging of liver fibrosis: Present and future. View, 5(4), 20240010. https://doi.org/10.1002/VIW.20240010.
12. Ahsan, M. M., Luna, S. A., & Siddique, Z. (2022). Machine-Learning-Based Disease Diagnosis: A Comprehensive Review. Healthcare, 10(3), 541. https://doi.org/10.3390/healthcare10030541
13. Sharma, P. (2022). Value of liver function tests in cirrhosis. Journal of clinical and experimental hepatology, 12(3), 948-964. https://doi.org/10.1016/j.jceh.2021.11.004.
14. Hoffmann, G., Bietenbeck, A., Lichtinghagen, R., & Klawonn, F. (2018). Using machine learning techniques to generate laboratory diagnostic pathways—a case study. Journal of Laboratory and Precision Medicine, 3(6). https://doi.org/10.21037/jlpm.2018.06.01.
15. Kwo, P. Y., Cohen, S. M., & Lim, J. K. (2017). ACG clinical guideline: evaluation of abnormal liver chemistries. Official journal of the American College of Gastroenterology| ACG, 112(1), 18-35. https://doi.org/10.1038/ajg.2016.517.
16. Fan, Y., Lu, X., & Sun, G. (2023). IHCP: interpretable hepatitis C prediction system based on black-box machine learning models. BMC bioinformatics, 24(1), 333. https://doi.org/10.1186/s12859-023-05456-0.
17. Yağanoğlu, M. (2022). Hepatitis C virus data analysis and prediction using machine learning. Data & Knowledge Engineering, 142, 102087. https://doi.org/10.1016/j.datak.2022.102087.
18. Lichtinghagen, R., Klawonn, F., & Hoffmann, G. (2020). HCV Data. UCI Machine Learning Repository, https://archive.ics.uci.edu/dataset/571/hcv+data, (06.06.2025).
19. Ripa, R., Uddin, K. M. M., Alam, M. J., & Rahman, M. M. (2025). Hepatitis C prediction using machine learning and deep learning-based hybrid approach with biomarker and clinical data. Biomedical Materials & Devices, 3(1), 558-575. https://doi.org/10.1007/s44174-024-00197-x.
20. Lilhore, U. K., Manoharan, P., Sandhu, J. K., Simaiya, S., Dalal, S., Baqasah, A. M., Alsafyani, M., Alroobaea, R., Keshta, I., & Raahemifar, K. (2023). Hybrid model for precise hepatitis-C classification using improved random forest and SVM method. Scientific Reports, 13(1), 12473. https://doi.org/10.1038/s41598-023-36605-3
21. Peng, J., Zou, K., Zhou, M., Teng, Y., Zhu, X., Zhang, F., & Xu, J. (2021). An explainable artificial intelligence framework for the deterioration risk prediction of hepatitis patients. Journal of medical systems, 45(5), 61. https://doi.org/10.1007/s10916-021-01736-5.
22. Blake, C. L. (1988). Hepatitis. UCI Machine Learning Repository, https://archive.ics.uci.edu/dataset/46/hepatitis, (01.11.2025).
23. Farghaly, H. M., Shams, M. Y., & Abd El-Hafeez, T. (2023). Hepatitis C virus prediction based on machine learning framework: A real-world case study in Egypt. Knowledge and Information Systems, 65(6), 2595–2617. https://doi.org/10.1007/s10115-023-01851-4.
24. Lu, H., Uddin, S., Hajati, F., Moni, M. A., & Khushi, M. (2022). A patient network-based machine learning model for disease prediction: The case of type 2 diabetes mellitus. Applied Intelligence, 52(3), 2411-2422. https://doi.org/10.1007/s10489-021-02533-w.
25. Zheng, S., Zhu, Z., Liu, Z., Guo, Z., Liu, Y., Yang, Y., & Zhao, Y. (2022). Multi-modal graph learning for disease prediction. IEEE Transactions on Medical Imaging, 41(9), 2207-2216. https://doi.org/10.1109/TMI.2022.3159264.
26. Ahmedt-Aristizabal, D., Armin, M. A., Denman, S., Fookes, C., & Petersson, L. (2021). Graph-based deep learning for medical diagnosis and analysis: past, present and future. Sensors, 21(14), 4758. https://doi.org/10.3390/s21144758.
27. Hoyt, G., Chatterjee, N., Battaglia, F., & Basu, P. (2025). Medical Applications of Graph Convolutional Networks Using Electronic Health Records: A Survey. arXiv preprint arXiv:2502.09781. https://doi.org/10.48550/arXiv.2502.09781.
28. Johnson, R., Li, M. M., Noori, A., Queen, O., & Zitnik, M. (2024). Graph artificial intelligence in medicine. Annual review of biomedical data science, 7(2024), 345-368. https://doi.org/10.1146/annurev-biodatasci-110723-024625.
29. Ramosaj, L., Bytyçi, A., Shala, B., & Bytyçi, E. (2023). Graph and Structured Data Algorithms in Electronic Health Records: A Scoping Review. In Research Conference on Metadata and Semantics Research (pp. 61-73). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-65990-4_6.
30. Defilippo, A., Hiram Guzzi, P., Veltri, P., & Liò, P. (2025). GraphNet: A Novel Method Based on Graph Neural Networks for Emergency Healthcare Management. In International Conference on Artificial Intelligence in Medicine (pp. 132-136). Springer, Cham. https://doi.org/10.1007/978-3-031-95841-0_25.
31. Kalas, M. A., Chavez, L., Leon, M., Taweesedt, P. T., & Surani, S. (2021). Abnormal liver enzymes: A review for clinicians. World journal of hepatology, 13(11), 1688. https://doi.org/10.4254/wjh.v13.i11.1688.
32. Defilippo, A., Veltri, P., Lió, P., & Guzzi, P. H. (2024). Leveraging graph neural networks for supporting automatic triage of patients. Scientific Reports, 14(1), 12548. https://doi.org/10.1038/s41598-024-63376-2.
33. Hamilton, W., Ying, Z., & Leskovec, J. (2017). Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
34. Wang, Z., Zhu, X., Adeli, E., Zhu, Y., Nie, F., Munsell, B., & Wu, G. (2017). Multi-modal classification of neurodegenerative disease by progressive graph-based transductive learning. Medical image analysis, 39, 218-230. https://doi.org/10.1016/j.media.2017.05.003.
35. Syama, K., Jothi, J. A. A., & Khanna, N. (2023). Automatic disease prediction from human gut metagenomic data using boosting GraphSAGE. BMC bioinformatics, 24(1), 126. https://doi.org/10.1186/s12859-023-05251-x.
36. Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16, 321-357. https://doi.org/10.1613/jair.953.
37. Zhang, S., Tong, H., Xu, J., & Maciejewski, R. (2019). Graph convolutional networks: a comprehensive review. Computational Social Networks, 6(1), 1-23. https://doi.org/10.1186/s40649-019-0069-y.
38. Xu, B., Wang, N., Chen, T., & Li, M. (2015). Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853. https://doi.org/10.48550/arXiv.1505.00853.
39. Loshchilov, I., & Hutter, F. (2017). Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101. https://doi.org/10.48550/arXiv.1711.05101.
40. Moulaei, K., Sharifi, H., Bahaadinbeigy, K., Haghdoost, A. A., & Nasiri, N. (2023). Machine learning for prediction of viral hepatitis: A systematic review and meta-analysis. International journal of medical informatics, 179, 105243. https://doi.org/10.1016/j.ijmedinf.2023.105243.
41. Powers, D. M. (2020). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. arXiv preprint arXiv:2010.16061. https://doi.org/10.48550/arXiv.2010.16061.
42. Qiu, X., Wang, F., Sun, Y., Lian, C., & Ma, J. (2024). Towards graph neural networks with domain-generalizable explainability for fMRI-Based brain disorder diagnosis. In International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 454-464). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72069-7_43.