{"ID":2868474,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16750","arxiv_id":"2509.16750","title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","abstract":"The increasing use of machine learning in clinical decision support has been limited by the lack of transparency of many high-performing models. In clinical settings, predictions must be interpretable, auditable, and actionable. This study investigates Kolmogorov-Arnold Networks (KANs) as intrinsically interpretable alternatives to conventional black-box models for clinical classification of tabular health data, aiming to balance predictive performance with clinically meaningful transparency. We introduce two KAN-based models: the Logistic KAN, a flexible generalization of logistic regression, and the Kolmogorov-Arnold Additive Model (KAAM), an additive variant that yields transparent symbolic representations through feature-wise decomposability. Both models are evaluated on multiple public clinical datasets and compared with standard linear, tree-based, and neural baselines. Across all datasets, the proposed models achieve predictive performance comparable to or exceeding that of commonly used baselines while remaining fully interpretable. Logistic-KAN obtains the highest overall ranking across evaluation metrics, with a mean reciprocal rank of 0.76, indicating consistently strong performance across tasks. KAAM provides competitive accuracy while offering enhanced transparency through feature-wise decomposability, patient-level visualizations, and nearest-patient retrieval, enabling direct inspection of individual predictions. KAN-based models provide a practical and trustworthy alternative to black-box models for clinical classification, offering a strong balance between predictive performance and interpretability for clinical decision support. By enabling transparent, patient-level reasoning and clinically actionable insights, the proposed models represent a promising step toward trustworthy AI in healthcare (code: https://github.com/Patricia-A-Apellaniz/classification_with_kans).","short_abstract":"The increasing use of machine learning in clinical decision support has been limited by the lack of transparency of many high-performing models. In clinical settings, predictions must be interpretable, auditable, and actionable. This study investigates Kolmogorov-Arnold Networks (KANs) as intrinsically interpretable al...","url_abs":"https://arxiv.org/abs/2509.16750","url_pdf":"https://arxiv.org/pdf/2509.16750v3","authors":"[\"Alejandro Almodóvar\",\"Patricia A. Apellániz\",\"Alba Garrido\",\"Fernando Fernández-Salvador\",\"Santiago Zazo\",\"Juan Parras\"]","published":"2025-09-20T17:21:58Z","proceeding":"cs.LG","tasks":"[\"cs.LG\"]","methods":"[]","has_code":false,"code_links":[{"ID":609594,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2868474,"paper_url":"https://arxiv.org/abs/2509.16750","paper_title":"Interpretable Clinical Classification with Kolmogorov-Arnold Networks","repo_url":"https://github.com/Patricia-A-Apellaniz/classification_with_kans","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}