Implementation of XGBoost Algorithm in Zang Organs Syndrome Diagnosis and Therapy Recommendations

Yosefina Finsensia Riti; Andre Hartanto; Onny Priskila; Benaya Azareel Oentoro

doi:10.34148/teknika.v15i1.1430

Authors

Yosefina Finsensia Riti Informatics Department, Faculty of Engineering, Universitas Katolik Darma Cendika, Surabaya, East Java, Indonesia
Andre Hartanto Informatics Department, Faculty of Engineering, Universitas Katolik Darma Cendika, Surabaya, East Java, Indonesia
Onny Priskila Acupuncture and Herbal Medicine Department, Faculty of Engineering, Universitas Katolik Darma Cendika, Surabaya, East Java, Indonesia
Benaya Azareel Oentoro Informatics Department, Faculty of Engineering, Universitas Katolik Darma Cendika, Surabaya, East Java, Indonesia

DOI:

https://doi.org/10.34148/teknika.v15i1.1430

Keywords:

Syndrome, Zang Organ, Machine Learning, XGBoost

Abstract

In Traditional Chinese Medicine (TCM), syndrome is primarily categorized into Zang and Fu organ syndromes. Zang organs include the heart, liver, spleen, lungs, and kidneys, and diagnosis is derived from patient complaints, symptoms, and examination findings. However, Zang organ syndrome determination is highly dependent on clinical experience, resulting in diagnostic subjectivity and variability among practitioners. In addition, symptom overlap across different organs further complicates the diagnostic process and challenges standardization. To address these issues, this study proposes an artificial intelligence (AI)-based intelligent system to assist Zang organ syndrome diagnosis and provide acupuncture therapy recommendations. The system applies machine learning to improve diagnostic accuracy and consistency, utilizing the Extreme Gradient Boosting (XGBoost) algorithm due to its effectiveness in classifying complex and nonlinear patterns commonly found in TCM diagnostics. The dataset was constructed based on standardized TCM references and expert-defined symptom–syndrome relationships, consisting of 39 symptom indicators, 72 Zang organ syndrome classes, and 15,532 data instances. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) was applied during training. Experimental results show that the proposed model achieved an accuracy of 98.6% and a macro-average F1-score of 83% for both syndrome diagnosis and therapy recommendation tasks. The results demonstrate that the proposed AI approach effectively supports Zang organ syndrome identification and acupuncture point recommendation, contributing to improved diagnostic efficiency and decision support in TCM practice.

Downloads

Download data is not yet available.

References

[1] Z. Wang et al., “TCMEval-SDT: a benchmark dataset for syndrome differentiation thought of traditional Chinese medicine,” Sci Data, vol. 12, no. 1, p. 437, Mar. 2025, doi: 10.1038/s41597-025-04772-9.

[2] Z. Huang et al., “A Traditional Chinese Medicine Syndrome Classification Model Based on Cross-Feature Generation by Convolution Neural Network: Model Development and Validation,” JMIR Med Inform, vol. 10, no. 4, p. e29290, Apr. 2022, doi: 10.2196/29290.

[3] V. C. H. Chung, C. H. L. Wong, C. C. W. Zhong, Y. Y. Tjioe, T. H. Leung, and S. M. Griffiths, “Traditional and complementary medicine for promoting healthy ageing in WHO Western Pacific Region: Policy implications from utilization patterns and current evidence,” Integrative Medicine Research, vol. 10, no. 1, p. 100469, Mar. 2021, doi: 10.1016/j.imr.2020.100469.

[4] A. Xu, “Traditional Chinese Medicine in Modern Healthcare: A Bridge between Ancient Wisdom and Contemporary Practice,” IJEH, vol. 12, no. 1, pp. 69–72, Jan. 2024, doi: 10.54097/bwd69y85.

[5] L. C. Matos, J. P. Machado, F. J. Monteiro, and H. J. Greten, “Understanding Traditional Chinese Medicine Therapeutics: An Overview of the Basics and Clinical Applications,” Healthcare, vol. 9, no. 3, p. 257, Mar. 2021, doi: 10.3390/healthcare9030257.

[6] K. A. O’Brien et al., “An Investigation into the Reliability of Chinese Medicine Diagnosis According to Eight Guiding Principles and Zang-Fu Theory in Australians with Hypercholesterolemia,” The Journal of Alternative and Complementary Medicine, vol. 15, no. 3, pp. 259–266, Mar. 2009, doi: 10.1089/acm.2008.0204.

[7] Z. Chen et al., “Traditional Chinese medicine diagnostic prediction model for holistic syndrome differentiation based on deep learning,” Integrative Medicine Research, vol. 13, no. 1, p. 101019, Mar. 2024, doi: 10.1016/j.imr.2023.101019.

[8] L. Ding, X. Zhang, D. Wu, and M. Liu, “Application of an extreme learning machine network with particle swarm optimization in syndrome classification of primary liver cancer,” Journal of Integrative Medicine, vol. 19, no. 5, pp. 395–407, Sept. 2021, doi: 10.1016/j.joim.2021.08.001.

[9] J. Zheng et al., “Metabolic syndrome prediction model using Bayesian optimization and XGBoost based on traditional Chinese medicine features,” Heliyon, vol. 9, no. 12, p. e22727, Dec. 2023, doi: 10.1016/j.heliyon.2023.e22727.

[10] H. Gong, H. Zhang, L. Zhou, Y. Liu, and L. Zhang, “An Interpretable Artificial Intelligence Model of Chinese Medicine Treatment Based on XGBoost Algorithm,” in 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Seoul, Korea (South): IEEE, Dec. 2020, pp. 1550–1554. doi: 10.1109/bibm49941.2020.9313424.

[11] D. Yifeng, L. Jinsong, and M. Wentao, “Study on Breast Cancer Classification Prediction based on XGBoost,” in 2024 IEEE 6th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China: IEEE, May 2024, pp. 411–416. doi: 10.1109/IMCEC59810.2024.10575645.

[12] X. Y. Liew, N. Hameed, and J. Clos, “An investigation of XGBoost-based algorithm for breast cancer classification,” Machine Learning with Applications, vol. 6, p. 100154, Dec. 2021, doi: 10.1016/j.mlwa.2021.100154.

[13] S. Degadwala, D. Vyas, A. Jadeja, and D. D. Pandya, “Enhancing Prostate Cancer Diagnosis: Leveraging XGBoost for Accurate Classification,” in 2023 Second International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India: IEEE, Aug. 2023, pp. 1776–1781. doi: 10.1109/ICAISS58487.2023.10250511.

[14] S. Sankar, A. Potti, G. N. Chandrika, and S. Ramasubbareddy, “Thyroid Disease Prediction Using XGBoost Algorithms,” JMM, Feb. 2022, doi: 10.13052/jmm1550-4646.18322.

[15] Y. Dou and W. Meng, “Predicting Cancer Classification Based on the Improved XGBoost Algorithms,” in 2024 6th International Conference on Frontier Technologies of Information and Computer (ICFTIC), Qingdao, China: IEEE, Dec. 2024, pp. 1013–1016. doi: 10.1109/ICFTIC64248.2024.10913271.

[16] Rajitha. M and S. S. Megala, “A Novel Approach for Heart Disease Classification using Cascaded XGBoost Algorithm,” in 2024 3rd International Conference on Automation, Computing and Renewable Systems (ICACRS), Pudukkottai, India: IEEE, Dec. 2024, pp. 905–912. doi: 10.1109/ICACRS62842.2024.10841637.

[17] E. K. Attipoe, A. S. Yussiff, and M. G. Asante-Mensah, “A Comparative Analysis of Machine Learning Classification Algorithms for Cardiovascular Disease Prediction,” in 2024 IEEE 9th International Conference on Adaptive Science and Technology (ICAST), Accra, Ghana: IEEE, Oct. 2024, pp. 1–5. doi: 10.1109/ICAST61769.2024.10856496.