Enhancing Liver Cirrhosis Staging Accuracy using Optuna-Optimized TabNet
DOI:
https://doi.org/10.30871/jaic.v9i5.11011Keywords:
Deep Learning, Liver Cirrhosis, Optuna, TabNet, Tabular DataAbstract
Liver cirrhosis is a progressive chronic disease whose early detection poses a clinical challenge, making accurate severity staging crucial for patient management. This research proposes and evaluates a TabNet deep learning model, specifically designed for tabular data, to address this challenge. In the initial evaluation, a baseline TabNet model with its default configuration achieved a baseline accuracy of 65.11% on a public clinical dataset. To enhance performance, hyperparameter optimization using Optuna was implemented, which successfully increased the accuracy significantly to 70.37%, with precision, recall, and F1-score metrics each reaching 70%. The model's discriminative ability was also validated as reliable in multiclass classification through AUC metric evaluation. In addition to accuracy improvements, the model's interpretability was validated through the identification of key predictive features such as Prothrombin and Hepatomegaly, which align with clinical indicators. This study demonstrates that Optuna-optimized TabNet is an effective and interpretable approach, possessing significant potential for integration into clinical decision support systems to support a more precise diagnosis of liver cirrhosis.
Downloads
References
[1] P. Ginès, A. Krag, J. G. Abraldes, E. Solà, N. Fabrellas, and P. S. Kamath, “Liver cirrhosis,” Oct. 2021, Elsevier B.V. doi: 10.1016/S0140-6736(21)01374-X.
[2] R. Davis, “Examining the immune response to infection in the context of Non-alcoholic fatty liver disease (NAFLD),” https://ucalgary.scholaris.ca/items/44ad3654-ae2e-4123-9cc4-66a0cdb5d2fe.
[3] Z. M. Younossi, G. Wong, Q. M. Anstee, and L. Henry, “The Global Burden of Liver Disease,” Jul. 2023, W.B. Saunders. doi: 10.1016/j.cgh.2023.04.015.
[4] B. P. Silaban, F. Lumongga, and H. Silitonga, “Karakteristik Penderita Sirosis Hati,” https://ejurnal.methodist.ac.id/index.php/jkm/article/view/1322.
[5] E. B. Tapper and N. D. Parikh, “Diagnosis and Management of Cirrhosis and Its Complications: A Review,” May 2023, American Medical Association. doi: 10.1001/jama.2023.5997.
[6] M. W. Sonderup et al., “Managing cirrhosis with limited resources: perspectives from sub-Saharan Africa,” Feb. 2024, Elsevier Ltd. doi: 10.1016/S2468-1253(23)00279-0.
[7] C. K. Kang, P. N. Brennan, and J. F. Dillon, “How to Effectively Monitor Aging Patients with Chronic Hepatitis B: A Review,” 2022, Dove Medical Press Ltd. doi: 10.2147/CIA.S366255.
[8] Yasmin Roni Mz, I Komang Gde Sukarsa, and I Gusti Ayu Made Srinadi, “Klasifikasi Penyakit Sirosis Hati Dengan CART,” Jurnal Cahaya Mandalika ISSN 2721-4796 (online), vol. 5, pp. 308–315, Mar. 2024, doi: 10.36312/jcm.v5i2.2123.
[9] V. Riskasari YR, I. P. E. N. Kencana, and I. K. G. Sukarsa, “Klasifikasi Penyakit Sirosis Menggunakan Support Vector Machine,” E-Jurnal Matematika, vol. 12, no. 2, p. 87, May 2023, doi: 10.24843/mtk.2023.v12.i02.p404.
[10] M. Mardewi and S. La Wungo, “Klasifikasi Liver Cirrhosis Menggunakan Teknik Ensemble: Studi Perbandingan Model Boosted Tree, Bagged Tree, dan Rusboosted Tree,” Journal of System and Computer Engineering (JSCE), vol. 5, pp. 219–225, Jul. 2024, doi: 10.61628/jsce.v5i2.1302.
[11] L. M. Cendani and A. Wibowo, “Perbandingan Metode Ensemble Learning pada Klasifikasi Penyakit Diabetes,” Jurnal Masyarakat Informatika, vol. 13, no. 1, pp. 33–44, 2022, doi: 10.14710/jmasif.13.1.42912.
[12] I. Shaik, P. V. Nagamani, Y. Manmode, S. Yadav, V. Degala, and G. S. Rao, “Mapping the dynamics of global sea surface nitrate using ocean color data,” Dec. 2024, Elsevier Ltd. doi: 10.1016/j.dynatmoce.2024.101507.
[13] M. A. Setitra and M. Fan, “Detection of DDoS attacks in SDN-based VANET using optimized TabNet,” Comput Stand Interfaces, vol. 90, Aug. 2024, doi: 10.1016/j.csi.2024.103845.
[14] P. S. Pravin, J. Z. M. Tan, K. S. Yap, and Z. Wu, “Hyperparameter optimization strategies for machine learning-based stochastic energy efficient scheduling in cyber-physical production systems,” Digital Chemical Engineering, vol. 4, Sep. 2022, doi: 10.1016/j.dche.2022.100047.
[15] S. Arık and T. Pfister, “TabNet: Attentive Interpretable Tabular Learning,” in 35th AAAI Conference on Artificial Intelligence, AAAI 2021, Association for the Advancement of Artificial Intelligence, 2021, pp. 6679–6687. doi: 10.1609/aaai.v35i8.16826.
[16] T. Kurniawan, L. Hermawanti, and A. N. Safriandono, “Interpretable Machine Learning with SHAP and XGBoost for Lung Cancer Prediction Insights,” Journal of Applied Informatics and Computing, vol. 8, no. 2 SE-Articles, pp. 296–303, Nov. 2024, doi: 10.30871/jaic.v8i2.8395.
[17] Y. Irawan, R. Pramitasari, W. M. Ashari, and A. N. H. Yansyah, “Support Vector Machine Classification Algorithm for Detecting DDoS Attacks on Network Traffic,” Journal of Applied Informatics and Computing, vol. 9, no. 4 SE-Articles, pp. 1945–1954, Aug. 2025, doi: 10.30871/jaic.v9i4.10003.
[18] W. Li, “TabNet for high-dimensional tabular data: advancing interpretability and performance with feature fusion,” IET Conference Proceedings, vol. 2025, pp. 168–173, Apr. 2025, doi: 10.1049/icp.2025.1030.
[19] M. Maftoun, N. Shadkam, S. Somayeh, S. Komamardakhi, Z. Mansor, and J. Hassannataj Joloudari, “Malicious URL Detection using optimized Hist Gradient Boosting Classifier based on grid search method,” 2024.
[20] T. Zhang, M. Da Huo, Z. Ma, J. Hu, Q. Liang, and H. Chen, “Prediction model of stock return on investment based on hybrid DNN and TabNet model,” PeerJ Comput Sci, vol. 10, pp. 1–23, 2024, doi: 10.7717/PEERJ-CS.2057.
[21] K. McDonnell, F. Murphy, B. Sheehan, L. Masello, and G. Castignani, “Deep learning in insurance: Accuracy and model interpretability using TabNet,” Expert Syst Appl, vol. 217, May 2023, doi: 10.1016/j.eswa.2023.119543.
[22] T. M. Arkan, A. Sugiharto, and H. A. Wibawa, “Optimizing VGG16 Architecture with Bayesian Hyperparameter Tuning for Tomato Leaf Disease Classification,” Jurnal Masyarakat Informatika, vol. 16, no. 2, pp. 162–173, 2025, doi: 10.14710/jmasif.16.2.73168.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Muhammad Farhan Arifin, Ika Novita Dewi, Abu Salam, Danang Wahyu Utomo, Sindhu Rakasiwi
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
