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.

翻译：糖尿病影响着全球超过5.37亿成年人。依赖胰岛素的患者需要持续监测血糖，并在严格的功耗预算下，于可穿戴设备上进行精确的剂量计算。本文提出了PDDS——一种用于预测性胰岛素剂量计算的事件驱动计算管线的计算机内、软件完备的研究原型。受用于超低功耗可穿戴边缘设备的神经形态计算原理的启发，其核心贡献是一个三层漏集成-发放（LIF）脉冲神经网络，该网络在来自OhioT1DM数据集（66.5%为真实患者）和美国食品药品监督管理局批准的UVa/Padova生理仿真器（33.5%）的128,025个窗口上进行训练，达到了85.90%的验证准确率。我们进行了三项严谨诚实的评估：（1）一项与ADA阈值规则、双向长短期记忆网络（准确率99.06%）和多层感知机（准确率99.00%）进行对比的标准测试集评估，其中脉冲神经网络达到了85.24%——我们证明这一差距反映了随机编码的权衡，而非架构缺陷；（2）一项对426个非明显的、由临床医生标注的低血糖窗口的时间基准评估，其中脉冲神经网络（召回率9.2%）和ADA规则（召回率16.7%）均未取得足够表现，由此识别出系统的关键局限以及未来工作的主要方向；（3）一项能效分析，表明脉冲神经网络每次推理所需的能量比长短期记忆网络少79,267倍（1,551飞焦耳对比122.9纳焦耳），证实了脉冲神经网络架构适用于持续的可穿戴部署。该系统尚未连接到物理硬件；它是通向临床验证的五阶段路线图的计算中间层。关键词：脉冲神经网络，血糖严重程度分类，边缘计算，低血糖检测，事件驱动架构，LIF神经元，泊松编码，OhioT1DM，计算机内，神经形态，能效。