Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection

• URL: http://arxiv.org/abs/2606.25434v1
• Date: Wed, 24 Jun 2026 05:54:44 GMT
• Title: Interpretable Concept-Guided Polynomial Tabular Kolmogorov-Arnold Network for EEG-Based Mild Cognitive Impairment Detection
• Abstract summary: Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge.<n>No existing work unifies physiologically organized concept encoders, cross-concept interaction modeling, and nonlinear tabular classification in a sleep EEG-based detection framework.<n>This study proposes Concept-guided Polynomial-transformed Tabular learning using Kolmogorov-Arnold Network (CPTabKAN)<n> CPTabKAN-Second Order achieved a weighted F1-score of 0.9 (SD 0.034), outperforming GradientBoosting by 5.65 percentage points.
• Score: 2.124023760378586
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Early and scalable detection of mild cognitive impairment (MCI) remains an unresolved clinical challenge. Existing EEG-based screening approaches are constrained by handcrafted feature pipelines that discard neurophysiologically meaningful domain structure and deep learning classifiers that sacrifice interpretability for performance. No existing work unifies physiologically organized concept encoders, cross-concept interaction modeling, and nonlinear tabular classification in a sleep EEG-based MCI detection framework. This study proposes Concept-guided Polynomial-transformed Tabular learning using Kolmogorov-Arnold Network (CPTabKAN), which maps heterogeneous EEG-derived features into domain-informed concept representations, expands them via degree-2 polynomial transformation to expose first- and second-order interactions, and applies a Fourier-parameterized TabKAN classifier to learn nonlinear decision boundaries. CPTabKAN was evaluated on the Study of Osteoporotic Fractures cohort (372 subjects, overnight polysomnography), using 1,379 features organized into ten physiologically motivated concept groups. Under 10-fold cross-validation, CPTabKAN-Second Order achieved a weighted F1-score of 0.9038 (SD 0.034), outperforming GradientBoosting by 5.65 percentage points (t(9)=1.934,p=0.043, one-sided paired test), with advantages persisting under SMOTE-based balancing. Ablation analysis confirmed independent contributions from each component. Concept importance analysis revealed that power spectral density, multi-scale entropy, and Hjorth parameters dominated first-order weights, while cross-concept interactions involving Lempel-Ziv-Welch complexity, statistics, demographics, and slow oscillations exceeded all first-order scores. These results demonstrate that concept-structured, interaction-aware tabular learning surfaces physiologically coherent reasoning, supporting clinical trust.

Related papers

• EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation Models [8.430851504111585]
  EEG foundation models such as BIOT, LaBraM, and EEGMamba have achieved remarkable performance in neural signal decoding.<n>We propose a unified attribution framework for interpreting EEG foundation models across heterogeneous architectures.
  arXiv  Detail & Related papers  (2026-09-14T14:56:07Z)
• ProCA: Progressive Contrastive Alignment for Robust EEG Visual Decoding [47.35612571473169]
  EEG visual decoding aims to recover visual semantics from non-invasive neural time-series signals.<n>Existing methods rely on fixed visual or textual anchors whose semantic relations may become misaligned with EEG representations that vary across trials, subjects, and learning stages.<n>We propose Progressive Contrastive Alignment (ProCA), a unified and model-agnostic framework for adaptive neural-semantic alignment.
  arXiv  Detail & Related papers  (2026-09-04T12:48:25Z)
• Taming foundation model with invariance-oriented pre-training for broad-spectrum EEG analysis across signal-level, brain-state, and brain-health tasks [46.533103231728724]
  INCEPT is an invariance-oriented EEG foundation model trained on over 11,000 hours of unlabelled clinical EEG.<n>We evaluate INCEPT on a broad-spectrum benchmark of ten datasets spanning three levels of post-acquisition EEG analysis.
  arXiv  Detail & Related papers  (2026-08-25T14:20:02Z)
• Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS [39.37223141220675]
  Multimodal neuroimaging enables non-invasive analysis of brain networks using graph neural networks.<n> demographic factors such as age and sex systematically confound the relationship between brain connectivity and clinical outcomes.<n>We propose Artemis, a region-level causal framework that bridges this gap with causal intervention at each brain region independently.
  arXiv  Detail & Related papers  (2026-06-10T05:10:36Z)
• Comparing Post-Hoc Explainable AI Methods for Interpreting Black-Box EEG Models in Depression Detection [0.0]
  This study investigates multiple post-hoc explainability methods applied to an InceptionTime architecture trained for EEG-based depression detection.<n>The evaluated methods revealed partially convergent attribution patterns, with recurring emphasis on frontal, temporal, and posterior EEG regions.<n>Overall, the results suggest that different post-hoc explainability approaches capture partially overlapping relevance structures in EEG-based deep learning models for depression detection.
  arXiv  Detail & Related papers  (2026-05-27T18:32:57Z)
• A Neuro-Symbolic System for Interpretable Multimodal Physiological Signals Integration in Human Fatigue Detection [3.430778683859764]
  We propose a neuro-symbolic architecture that learns four interpretable physiological concepts, oculomotor dynamics, gaze stability, prefrontal hemodynamics, and multimodal, from eye-tracking and neural hemodynamics, functional near-infrared spectroscopy, (fNIRS) windows using attention-based encoders, and combines them with differentiable approximate reasoning rules using learned weights and soft thresholds.<n>We apply this system to fatigue classification from multimodal physiological signals, a domain that requires models that are accurate and interpretable, with internal reasoning that can be inspected for safety-critical use.
  arXiv  Detail & Related papers  (2026-03-25T14:41:02Z)
• PathMoE: Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification [30.58342408480846]
  PathMoE is an interpretable multimodal framework that integrates H&E slides, pathology reports, and nuclei-level cell graphs.<n>We evaluate our framework on two dataset-specific classification tasks on an internal pediatric brain tumor dataset and external TCGA datasets.
  arXiv  Detail & Related papers  (2026-03-02T07:17:44Z)
• Learning Alzheimer's Disease Signatures by bridging EEG with Spiking Neural Networks and Biophysical Simulations [42.091774598477706]
  Conventional deep learning approaches for EEG-based Alzheimer's disease detection are computationally intensive and mechanistically opaque.<n>We propose a neuro-bridge framework that links data-driven learning with biophysically grounded simulations.
  arXiv  Detail & Related papers  (2026-01-30T21:54:16Z)
• Semantic NLP Pipelines for Interoperable Patient Digital Twins from Unstructured EHRs [3.914632811815449]
  This paper presents a semantic NLP-driven pipeline that transforms free-text EHR notes into digital twin representations.<n>The pipeline leverages named entity recognition (NER) to extract clinical concepts, concept normalization to map entities to SNOMED-CT or ICD-10, and relation extraction to capture structured associations between conditions, medications, and observations.
  arXiv  Detail & Related papers  (2026-01-09T15:20:11Z)
• CONFIDE: Hallucination Assessment for Reliable Biomolecular Structure Prediction and Design [46.12506067241116]
  We present CODE (Chain of Diffusion Embeddings), a self evaluating metric to quantify topological frustration.<n>We propose CONFIDE, a unified evaluation framework that combines energetic and topological perspectives.<n>By combining data driven embeddings with theoretical insight, CODE and CONFIDE outperform existing metrics across a wide range of biomolecular systems.
  arXiv  Detail & Related papers  (2025-11-20T03:38:46Z)
• Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks [56.75602443936853]
  One in five adolescents currently live with a diagnosed mental or behavioral health condition, such as anxiety, depression, or conduct disorder.<n>While prior works use graph neural network (GNN) approaches for disorder prediction, they remain black-boxes, limiting their reliability and clinical translation.<n>In this work, we propose a concept-based diagnosis framework that that encodes interpretable functional connectivity concepts.<n>Our design ensures predictions through clinically meaningful connectivity patterns, enabling both interpretability and strong predictive performance.
  arXiv  Detail & Related papers  (2025-10-02T19:38:46Z)
• Microelectrode Signal Dynamics as Biomarkers of Subthalamic Nucleus Entry on Deep Brain Stimulation: A Nonlinear Feature Approach [0.0]
  We propose a framework that leverages nonlinear dynamics and entropy-based metrics to classify neural activity recorded inside versus outside the STN.<n>Our results highlight the potential of nonlinear and entropy signal descriptors in supporting real-time, data-driven decision-making during DBS surgeries.
  arXiv  Detail & Related papers  (2025-06-14T23:23:26Z)
• AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs [62.60333833486799]
  AnesSuite is the first dataset suite specifically designed for anesthesiology reasoning in LLMs.<n>Morpheus is the first baseline model collection for anesthesiology reasoning.
  arXiv  Detail & Related papers  (2025-04-03T08:54:23Z)
• A Knowledge-Driven Cross-view Contrastive Learning for EEG Representation [48.85731427874065]
  This paper proposes a knowledge-driven cross-view contrastive learning framework (KDC2) to extract effective representations from EEG with limited labels. The KDC2 method creates scalp and neural views of EEG signals, simulating the internal and external representation of brain activity. By modeling prior neural knowledge based on neural information consistency theory, the proposed method extracts invariant and complementary neural knowledge to generate combined representations.
  arXiv  Detail & Related papers  (2023-09-21T08:53:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.