用脉冲神经网络实现低功耗胰岛素预测，适合可穿戴设备持续运行。
An Energy-Efficient Spiking Neural Network Architecture for Predictive Insulin Delivery
- 基于脉冲神经网络的事件驱动计算架构，支持低功耗实时预测。
- 在12.8万数据窗口上训练，验证准确率达85.90%，推理能耗仅为LSTM的1/79,267。
- 适合关注能效与边缘部署的医疗智能系统研究者参考。
全球超过537万名成人患糖尿病，依赖胰岛素治疗的患者需持续监测血糖并精准计算剂量，且受可穿戴设备严格功耗限制。本文提出PDDS——一种基于仿神经形态计算的事件驱动计算流水线原型，用于预测性胰岛素给药。核心为三层漏积分-放电（LIF）脉冲神经网络，在来自OhioT1DM（66.5%真实患者）和FDA认可的UVa/Padova生理模拟器（33.5%）的128,025个时间窗口上训练，验证准确率达85.90%。我们进行三项严谨评估：(1) 与ADA标准规则、双向LSTM（99.06%准确率）、MLP（99.00%）对比，脉冲神经网络达85.24%，表明差距源于随机编码权衡而非结构缺陷；(2) 在426个临床专家标注的低血糖窗口中，脉冲神经网络召回率仅9.2%，ADA规则为16.7%，暴露系统主要瓶颈与未来改进方向；(3) 功耗分析显示，该模型每次推理仅需1,551飞焦，相比LSTM的122.9纳焦，节能79,267倍，验证其适用于连续可穿戴部署。当前系统尚未连接物理硬件，是通往临床验证的五阶段路线图中的计算中间层。
原文摘要 · Abstract (English)
Diabetes mellitus affects over 537 million adults worldwide. Insulin-dependent patients require continuous glucose monitoring and precise dose calculation while operating under strict power budgets on wearable devices. This paper presents PDDS - an in-silico, software-complete research prototype of an event-driven computational pipeline for predictive insulin dose calculation. Motivated by neuromorphic computing principles for ultra-low-power wearable edge devices, the core contribution is a three-layer Leaky Integrate-and-Fire (LIF) Spiking Neural Network trained on 128,025 windows from OhioT1DM (66.5% real patients) and the FDA-accepted UVa/Padova physiological simulator (33.5%), achieving 85.90% validation accuracy. We present three rigorously honest evaluations: (1) a standard test-set comparison against ADA threshold rules, bidirectional LSTM (99.06% accuracy), and MLP (99.00%), where the SNN achieves 85.24% - we demonstrate this gap reflects the stochastic encoding trade-off, not architectural failure; (2) a temporal benchmark on 426 non-obvious clinician-annotated hypoglycemia windows where neither the SNN (9.2% recall) nor the ADA rule (16.7% recall) performs adequately, identifying the system's key limitation and the primary direction for future work; (3) a power-efficiency analysis showing the SNN requires 79,267x less energy per inference than the LSTM (1,551 Femtojoules vs. 122.9 nanojoules), justifying the SNN architecture for continuous wearable deployment. The system is not yet connected to physical hardware; it constitutes the computational middle layer of a five phase roadmap toward clinical validation. Keywords: spiking neural network, glucose severity classification, edge computing, hypoglycemia detection, event-driven architecture, LIF neuron, Poisson encoding, OhioT1DM, in-silico, neuromorphic, power efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。