Personalized LSTM-Based Alarm Systems for Hypoglycemia Prevention in an Intraperitoneal Artificial Pancreas.
Mediterranean Conference on Control and Automation(2024)
摘要
Prevention of hypoglycemia is a key aspect for efficient management of Type I diabetes. Alarm systems (ASs) are very useful to alert the patient in advance in case of hypo-glycemia, allowing early intervention to avoid or mitigate the potential critical situation. Model-based ASs use patient models to predict the future glucose concentration and trigger alarms. In recent years neural networks, in particular Personalized Long Short-Term Memory Networks (PLSTMs) have shown very promising performances in glucose prediction. In this work, PLSTM-based AS for the prevention of hypoglycemia for an Artificial Pancreas is proposed. Preliminary results on a subgroup of 71 patients show that this system is able to predict almost all the potentially critical events (median TPR = 100%) with a precision of 57%. These promising techniques are under study to include also the remaining 29 problematic patients.
更多查看译文
关键词
Alarm System,Artificial Pancreas,Prevention Of Hypoglycemia,Neural Network,Predictive Performance,Type 1 Diabetes Mellitus,Short-term Memory,Long Short-term Memory,Promising Performance,Long Short-term Memory Network,Critical Situations,Short-term Memory Network,Blood Glucose,Root Mean Square Error,Mean Square Error,Hyperglycemia,Artificial Neural Network,Insulin Sensitivity,Performance Metrics,Recurrent Neural Network,Inter-patient Variability,Continuous Subcutaneous Insulin Infusion,Correct Detection,Prediction Quality,Signal Of Interest,Insulin Delivery,Graphics Processing Unit,State Value,Glucose Values,Past Values
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要