aiqbench analysis
This research demonstrates that Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) can classify ECG arrhythmias with high accuracy while consuming three to six orders of magnitude fewer FLOPs than current state-of-the-art methods. By leveraging FPGA implementation, the study achieves ultra-low power consumption suitable for implantable devices, addressing critical constraints in edge AI applications for healthcare. The findings suggest a viable path toward deploying interpretable, efficient neural architectures on resource-constrained medical hardware without sacrificing performance on unseen patient data.
Inter-patient ECG Arrhythmia Classification with LGNs and LUTNs
arXiv:2601.11433v2 Announce Type: replace Abstract: Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of electrocardiograms (ECGs) using the inter-patient paradigm. The methods are benchmarked using the MIT-BIH arrhythmia data set, achieving up to 94.28% accuracy and a $j\kappa$ index of 0.683 on a four-class classification problem. Our models use between 2.89k and 6.17k FLOPs, including preprocessing and readout, which is three to six orders of magnitude less compared to SOTA methods. A novel preprocessing method is utilized that attains superior performance compared to existing methods for both the mixed-patient and inter-patient paradigms. In addition, a novel method for training the Lookup Tables (LUTs) in LUTNs is devised that uses the Boolean equation of a multiplexer (MUX). Additionally, rate coding was utilized for the first time in these LGNs and LUTNs, enhancing the performance of LGNs. Furthermore, it is the first time that LGNs and LUTNs have been benchmarked on the MIT-BIH arrhythmia dataset using the inter-patient paradigm. Using an Artix 7 FPGA, between 2000 and 2990 LUTs were needed, and between 5 to 7 mW (i.e. 50 pJ to 70 pJ per inference) was estimated for running these models. The performance in terms of both accuracy and $j\kappa$-index is significantly higher compared to previous LGN results. These positive results suggest that one can utilize LGNs and LUTNs for the detection of arrhythmias at extremely low power and high speeds in heart implants or wearable devices, even for patients not included in the training set.
Abstract:Deep Differentiable Logic Gate Networks (LGNs) and Lookup Table Networks (LUTNs) are demonstrated to be suitable for the automatic classification of electrocardiograms (ECGs) using the inter-patient paradigm. The methods are benchmarked using the MIT-BIH arrhythmia data set, achieving up to 94.28% accuracy and a $j\kappa$ index of 0.683 on a four-class classification problem. Our models use between 2.89k and 6.17k FLOPs, including preprocessing and readout, which is three to six orders of magnitude less compared to SOTA methods. A novel preprocessing method is utilized that attains superior performance compared to existing methods for both the mixed-patient and inter-patient paradigms. In addition, a novel method for training the Lookup Tables (LUTs) in LUTNs is devised that uses the Boolean equation of a multiplexer (MUX). Additionally, rate coding was utilized for the first time in these LGNs and LUTNs, enhancing the performance of LGNs. Furthermore, it is the first time that LGNs and LUTNs have been benchmarked on the MIT-BIH arrhythmia dataset using the inter-patient paradigm. Using an Artix 7 FPGA, between 2000 and 2990 LUTs were needed, and between 5 to 7 mW (i.e. 50 pJ to 70 pJ per inference) was estimated for running these models. The performance in terms of both accuracy and $j\kappa$-index is significantly higher compared to previous LGN results. These positive results suggest that one can utilize LGNs and LUTNs for the detection of arrhythmias at extremely low power and high speeds in heart implants or wearable devices, even for patients not included in the training set.
The paper has undergone major changes, leading to different results. Hence it seems most suitable to publish a new one at: https://arxiv.org/abs/2609.32854
Machine Learning (cs.LG)
arXiv:2601.11433 [cs.LG]
(or arXiv:2601.11433v2 [cs.LG] for this version)
Full text under the publisher's open licence · 284 words
Related coverage
Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification
arXiv · Sep 30, 2026
Few-Shot Prototype Head Adaptation for On-Device ECG Personalization on PSoC~6
arXiv · Oct 7, 2026
A Vision-Language Foundation Model for Precise and Comprehensive Brain Tumor Diagnosis from Preoperative Multimodal Data
arXiv · Sep 16, 2026
FedSPM: Routing-Enabled Federated Learning under Dual Heterogeneity via Semiparametric Mixture
arXiv · Oct 1, 2026