The Effectiveness of Kolmogorov–Arnold Networks in the Healthcare Domain
Source abstract
Abstract
Kolmogorov–Arnold Networks (KANs) have recently emerged as a powerful alternative to traditional Artificial Neural Networks (ANNs), offering superior accuracy and interpretability, which are two critical requirements in healthcare applications. This study investigates the effectiveness of KANs across a range of clinical tasks by applying them to diverse medical datasets, including structured clinical data and time-series physiological signals. Compared with conventional ANNs, KANs demonstrate significantly improved performance, achieving higher predictive accuracy even with smaller network architectures. Beyond performance gains, KANs offer a unique advantage: the ability to extract symbolic expressions from learned functions, enabling transparent, human-interpretable models—a key factor in clinical decision-making. Through comprehensive experiments and symbolic analysis, our results reveal that KANs not only outperform ANNs in modeling complex healthcare data but also provide interpretable insights that can support personalized medicine and early diagnosis. There is nothing specific about the datasets or the methods employed, so the findings are broadly applicable and position KANs as a compelling architecture for the future of AI in healthcare.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Economic and Technological Developments in Russia · Technology and Human Factors in Education and Health
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Applied Data Science, San Jose State University, San Jose, CA 95192, USA
References (26)
Show source-provided references
1. Pendyala, V.S. (2024, January 18–21). The impact of Artificial Intelligence on Ecojustice and Ethics. Proceedings of the 8th International Conference on Data Science and Management of Data (12th ACM IKDD CODS and 30th COMAD), CODS-COMAD’ 24, New York, NY, USA.10.1145/3703323.3704279 ↗
2. Pendyala, V., and Kim, H. (2024). Assessing the reliability of machine learning models applied to the mental health domain using explainable AI. Electronics, 13.10.20944/preprints202403.0134.v1 ↗
3. Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljačić, M., Hou, T.Y., and Tegmark, M. (2024). KAN: Kolmogorov-Arnold Networks. arXiv.
4. Sidharth, S.S., Keerthana, A.R., Gokul, R., and Anas, K.P. (2024). Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation. arXiv.
5. Yu, R., Yu, W., and Wang, X. (2024). KAN or MLP: A Fairer Comparison. arXiv.
6. Wang, Y., Sun, J., Bai, J., Anitescu, C., Eshaghi, M.S., Zhuang, X., Rabczuk, T., and Liu, Y. (2024). Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks. arXiv.10.2139/ssrn.4868150 ↗
7. Zhang, H., Huang, Z., and Wang, Y. (2025). AC-PKAN: Attention-Enhanced and Chebyshev Polynomial-Based Physics-Informed Kolmogorov–Arnold Networks. arXiv.
8. Raj, P. (2025). Structured and Informed Probabilistic Modeling with the Thermodynamic Kolmogorov–Arnold Model. arXiv.
9. Li, C., Liu, X., Li, W., Wang, C., Liu, H., Liu, Y., Chen, Z., and Yuan, Y. (2024). U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation. arXiv.10.1609/aaai.v39i5.32491 ↗
10. Vaca-Rubio, C.J., Blanco, L., Pereira, R., and Caus, M. (2024). Kolmogorov–Arnold Networks (KANs) for Time Series Analysis. arXiv.10.1109/GCWkshp64532.2024.11100692 ↗
11. Aghaei, A.A. (2024). fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions. arXiv.
12. Jahin, M.A., Masud, M.A., Mridha, M.F., Aung, Z., and Dey, N. (2024). KACQ-DCNN: Uncertainty-Aware Interpretable Kolmogorov-Arnold Classical-Quantum Dual-Channel Neural Network for Heart Disease Detection. arXiv.
13. Xu, K., Chen, L., and Wang, S. (2024). Kolmogorov-Arnold Networks for Time Series: Bridging Predictive Power and Interpretability. arXiv.
14. Doe, J., and Smith, J. (2024). Graph KANs for Multi-Cancer Classification with Biomarker Identification. arXiv.
15. Bozorgasl, Z., and Chen, H. (2024). Wav-KAN: Wavelet Kolmogorov-Arnold Networks. arXiv.10.2139/ssrn.4835325 ↗
16. Kiamari, M., Kiamari, M., and Krishnamachari, B. (2024). GKAN: Graph Kolmogorov–Arnold Networks. arXiv.
17. Ferdaus, M.M., Wahmie, S., and Uddin, N. (2024). KANICE: Kolmogorov–Arnold Networks with Interactive Convolutional Elements. arXiv.10.21079/11681/49791 ↗
18. Bodner, A.D., Tepsich, A.S., Spolski, J.N., and Pourteau, S. (2024). Convolutional Kolmogorov-Arnold Networks. arXiv.
19. Kich, V.A., Bottega, J.A., Steinmetz, R., Grando, R.B., Yorozu, A., and Ohya, A. (2024). Kolmogorov-Arnold Network for Online Reinforcement Learning. arXiv.10.23919/ICCAS63016.2024.10773080 ↗
20. Toscano, J.D., Wang, L.L., and Karniadakis, G.E. (2024). KKANs: Kurkova–Kolmogorov–Arnold Networks and Their Learning Dynamics. arXiv.10.1016/j.neunet.2025.107831 ↗
21. Somvanshi, S., Javed, S.A., Islam, M.M., Pandit, D., and Das, S. (2024). A Survey on Kolmogorov-Arnold Network. arXiv.10.1145/3743128 ↗
22. Theerthagiri, P., and J, V. (2021). Cardiovascular Disease Prediction using Recursive Feature Elimination and Gradient Boosting Classification Techniques. arXiv.10.1111/exsy.13064 ↗
23. Lai, Y., and Wang, H. (2024). AF-KAN: Attention-Free Kolmogorov–Arnold Network for Efficient Learning. arXiv.
24. Coffman, B., and Chen, L. (2025). MatrixKAN: Parallelized Kolmogorov-Arnold Network. arXiv.
25. Qiu, T., and Xu, W. (2024). PowerMLP: An Efficient Version of KAN. arXiv.
26. Raffel, C., and Chen, Y. (2025). FlashKAT: Understanding and Addressing Performance Bottlenecks in the Kolmogorov-Arnold Transformer. arXiv.