Interpretable Clinical Classification with Kolgomorov-Arnold Networks

2025-09-20

AI Summary

Clinical AI systems face limited adoption due to their intrinsic lack of interpretability, undermining physician trust. To address this, we propose two inherently interpretable neural models—Logistic-KAN and Kolmogorov-Arnold Additive Model (KAAM)—grounded in the Kolmogorov-Arnold representation theorem. These models employ functionally explicit, symbolic network architectures that yield fully transparent predictions: no post-hoc explanation tools are required, as outputs consist directly of human-readable mathematical formulas and patient-level similar-case retrieval. Evaluated on multiple public healthcare datasets, both models achieve accuracy competitive with or superior to state-of-the-art black-box methods—including XGBoost and deep neural networks—while ensuring end-to-end auditability of decision pathways. This work establishes a novel paradigm for clinically trustworthy AI, uniquely reconciling high predictive performance with strong, built-in interpretability.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Why should a clinician trust an Artificial Intelligence (AI) prediction? Despite the increasing accuracy of machine learning methods in medicine, the lack of transparency continues to hinder their adoption in clinical practice. In this work, we explore Kolmogorov-Arnold Networks (KANs) for clinical classification tasks on tabular data. Unlike traditional neural networks, KANs are function-based architectures that offer intrinsic interpretability through transparent, symbolic representations. We introduce Logistic-KAN, a flexible generalization of logistic regression, and Kolmogorov-Arnold Additive Model (KAAM), a simplified additive variant that delivers transparent, symbolic formulas. Unlike black-box models that require post-hoc explainability tools, our models support built-in patient-level insights, intuitive visualizations, and nearest-patient retrieval. Across multiple health datasets, our models match or outperform standard baselines, while remaining fully interpretable. These results position KANs as a promising step toward trustworthy AI that clinicians can understand, audit, and act upon.

Problem

• Addressing lack of transparency in AI predictions for clinical practice
• Providing interpretable classification models instead of black-box approaches
• Enabling clinician trust through transparent, symbolic representations

Innovation

• Kolmogorov-Arnold Networks for clinical classification tasks
• Logistic-KAN as flexible generalization of logistic regression
• Kolmogorov-Arnold Additive Model delivers transparent symbolic formulas