Key result
Novel SE-MSC-KAN-CNN model improves classification accuracy by ~2 percentage points over standard CNN.
Why the study?
The behavior and interpretability of Kolmogorov-Arnold Networks combined with semi-supervised learning for single-lead ECG classification were not well understood.
Does the proposed SE-MSC-KAN-CNN model improve ECG classification accuracy and interpretability compared to standard CNN architectures?
Does the proposed SE-MSC-KAN-CNN model improve ECG classification accuracy and interpretability compared to standard CNN architectures?
Absolute Event Rate: 85.2% vs 83.1%
A hybrid Kolmogorov-Arnold Network (SE-MSC-KAN-CNN) achieves competitive accuracy and interpretability for single-lead ECG classification, though deployment on edge devices is limited by hardware conversion constraints.
Supports interpretable ECG AI development; leaves open prospective validation before clinical adoption.
This study investigates how Kolmogorov-Arnold Networks (KANs) behave when combined with semi-supervised learning for single-lead ECG analysis. Three architectures are compared: a standard CNN-BiLSTM-Attention model (accurate but uninterpretable), a minimal KAN with a simple CNN front-end (ablation), and the proposed SE-MSC-KAN-CNN. The proposed model uses multi-scale depthwise convolutions, Squeeze-and-Excitation attention, BiLSTM, and a B-spline KAN head. Interpretability is evaluated in three ways: visualising learned B-spline functions, applying Grad-CAM to highlight important signal regions, and measuring how the splines change when fewer labels are used (spline drift). On the PhysioNet 2017 dataset (8,528 recordings, four classes), the proposed model reaches 85.2% supervised accuracy (F1=0.851), outperforming the CNN baseline (83.1%) and matching much larger black-box models. With only 90% of the labels, it still achieves 85.1%. After training, we applied post-training TFLite INT8 conversion. Only the CNN-front-end KAN converted (measured size 422 KB). The proposed SE-MSC-KAN-CNN did not convert, because Bidirectional LSTM and custom attention lack TFLite kernels; its float32 footprint is about 9.8 MB (theoretical INT8 size about 806 KB). Classification metrics in this paper are float32; INT8 test accuracy was not measured. The spline drift metric summarises how KAN coefficients change under semi-supervised training; use as an on-device out-of-distribution detector is proposed but not validated here. These results show that competitive accuracy and inspectable KAN maps can be obtained in one hybrid architecture. Wearable deployment of the proposed SE-MSC-KAN-CNN is not yet achieved: TFLite INT8 conversion failed, and the present graph still requires float32 inference.
No takes yet. Share an insight, caveat, or question.
Baidillah et al. (2026) studied ECG classification (n=8,528). SE-MSC-KAN-CNN vs. Standard CNN-BiLSTM-Attention model was evaluated on Supervised accuracy.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: