Newly diagnosed Type 1 Diabetes (T1D) patients often struggle to obtain
effective Blood Glucose (BG) prediction models due to the lack of sufficient BG
data from Continuous Glucose Monitoring (CGM), presenting a significant "cold
start" problem in patient care. Utilizing population models to address this
challenge is a potential solution, but collecting patient data for training
population models in a privacy-conscious manner is challenging, especially
given that such data is often stored on personal devices. Considering the
privacy protection and addressing the "cold start" problem in diabetes care, we
propose "GluADFL", blood Glucose prediction by Asynchronous Decentralized
Federated Learning. We compared GluADFL with eight baseline methods using four
distinct T1D datasets, comprising 298 participants, which demonstrated its
superior performance in accurately predicting BG levels for cross-patient
analysis. Furthermore, patients' data might be stored and shared across various
communication networks in GluADFL, ranging from highly interconnected (e.g.,
random, performs the best among others) to more structured topologies (e.g.,
cluster and ring), suitable for various social networks. The asynchronous
training framework supports flexible participation. By adjusting the ratios of
inactive participants, we found it remains stable if less than 70% are
inactive. Our results confirm that GluADFL offers a practical,
privacy-preserving solution for BG prediction in T1D, significantly enhancing
the quality of diabetes management.

通过异步去中心化联邦学习来解决糖尿病患者面临的高质量血糖预测模型的难题以及隐私保护的问题。GluADFL 方法在四个不同的 T1D 数据集上经过与八种对照方法的比较，展示了在跨患者分析中准确预测血糖水平的优越性能，同时适用于各种社交网络的通讯网络中的数据存储和分享，提供了实际应用的隐私保护解决方案，显著提高了糖尿病管理的质量。

隐私保护的血糖水平交叉预测：一种异步去中心化联邦学习方法

Privacy Preserved Blood Glucose Level Cross-Prediction: An Asynchronous  Decentralized Federated Learning Approach

Precise glucose level management is pivotal for individuals with diabetes,
averting severe complications. In this work, we introduce a novel neural
control system for continuous glucose monitoring and maintenance, utilizing
differential predictive control. Our system, guided by a sophisticated neural
policy and differentiable modeling, dynamically adjusts insulin delivery in
real-time, enhancing glucose optimization. This end-to-end approach maximizes
efficiency, ensuring personalized care and improved health outcomes, as
affirmed by empirical findings.

通过神经控制系统和差分预测控制，实时调整胰岛素递送以提高葡萄糖优化，从而确保个性化关怀和改善健康结果。

连续血糖监测与维护的神经控制系统

Neural Control System for Continuous Glucose Monitoring and Maintenance

In the UK, approximately 400,000 people with type 1 diabetes (T1D) rely on
insulin delivery due to insufficient pancreatic insulin production. Managing
blood glucose (BG) levels is crucial, with continuous glucose monitoring (CGM)
playing a key role. CGM, tracking BG every 5 minutes, enables effective blood
glucose level prediction (BGLP) by considering factors like carbohydrate intake
and insulin delivery.
Recent research has focused on developing sequential models for BGLP using
historical BG data, incorporating additional attributes such as carbohydrate
intake, insulin delivery, and time. These methods have shown notable success in
BGLP, with some providing temporal explanations. However, they often lack clear
correlations between attributes and their impact on BGLP. Additionally, some
methods raise privacy concerns by aggregating participant data to learn
population patterns.
Addressing these limitations, we introduced a graph attentive memory (GAM)
model, combining a graph attention network (GAT) with a gated recurrent unit
(GRU). GAT applies graph attention to model attribute correlations, offering
transparent, dynamic attribute relationships. Attention weights dynamically
gauge attribute significance over time. To ensure privacy, we employed
federated learning (FL), facilitating secure population pattern analysis.
Our method was validated using the OhioT1DM'18 and OhioT1DM'20 datasets from
12 participants, focusing on 6 key attributes. We demonstrated our model's
stability and effectiveness through hyperparameter impact analysis.

使用图注意力内存模型和联邦学习方法进行血糖水平预测，在类型 1 糖尿病患者中取得了稳定而有效的结果。

血糖水平预测：基于图像的可解释方法与联邦学习

Blood Glucose Level Prediction: A Graph-based Explainable Method with  Federated Learning

A task of vital clinical importance, within Diabetes management, is the
prevention of hypo/hyperglycemic events. Increasingly adopted Continuous
Glucose Monitoring (CGM) devices offer detailed, non-intrusive and real time
insights into a patient's blood glucose concentrations. Leveraging advanced
Machine Learning (ML) Models as methods of prediction of future glucose levels,
gives rise to substantial quality of life improvements, as well as providing a
vital tool for monitoring diabetes.
A regression based prediction approach is implemented recursively, with a
series of Machine Learning Models: Linear Regression, Hidden Markov Model,
Long-Short Term Memory Network. By exploiting a patient's past 11 hours of
blood glucose (BG) concentration measurements, a prediction of the 60 minutes
is made. Results will be assessed using performance metrics including: Root
Mean Squared Error (RMSE), normalised energy of the second-order differences
(ESOD) and F1 score.
Research of past and current approaches, as well as available dataset, led to
the establishment of an optimal training methodology for the CITY dataset,
which may be leveraged by future model development. Performance was aligned
with similar state-of-art ML models, with LSTM having RMSE of 28.55, however no
significant advantage was observed over classical Auto-regressive AR models.
Compelling insights into LSTM prediction behaviour could increase public and
legislative trust and understanding, progressing the certification of ML models
in Artificial Pancreas Systems (APS).

该研究探讨利用连续血糖监测设备和机器学习模型进行血糖浓度的预测，旨在为糖尿病治疗提供便利以及为人工胰腺系统认证和监管提供可靠性支持。