Multivariable Artificial Pancreas System to Detect and Mitigate the Effects of Unannounced Physical Activities and Acute Psychological Stress

IIT项目摘要/摘要 这项提议的目标是证明一种可行的、功能集成的多变量 人工胰腺将缓解饮食、体力活动和急性心理压力 在没有任何人工输入的情况下更好地调节糖尿病患者的血糖水平的挑战。 第一代人工胰腺(AP)系统--混合闭环式AP--收集数据 来自连续的血糖监测设备，并依赖于手动用户输入来缓解 饮食和体力活动的影响。急性心理应激和其他许多生理压力 除了有计划的锻炼外，其他活动也会影响血糖水平，并对 维持1型糖尿病患者的正常血糖。各种体力活动和急性 心理应激事件以不同的方式影响新陈代谢和对胰岛素的敏感性。 因此，它们的类型、强度和持续时间以及它们的单独和同时存在必须 以确定最佳的胰岛素给药方案。多变量人工智能 胰腺方法提供了一种集成良好且用户友好的技术，负担最小 并减轻意外体力活动和急性心理活动的影响 压力诱因。此外，这项技术将通过减少数量和 低血糖和高血糖事件的持续时间，与仅基于 连续血糖监测仪数据。这种多变量AP系统只能 通过使用复杂的多变量方法开发，该方法使用来自 从可穿戴设备获得的连续血糖监测设备和生理变量 自由生活日常生活中佩戴的设备。

IIT Project Summary/Abstract The objective of this proposal is to demonstrate a viable, functionally integrated multivariable artificial pancreas that will mitigate meal, physical activity and acute psychological stress challenges without any manual inputs to better regulate glucose levels of people with diabetes. The first generation of artificial pancreas (AP) systems, the hybrid closed-loop AP, collects data from continuous glucose monitoring devices and relies on manual user inputs for mitigating the effects of meals and physical activities. Acute psychological stress and many other physical activities besides planned exercise can affect blood glucose levels and cause challenges to maintaining euglycemia for people with type 1 diabetes. Various physical activities and acute psychological stress events affect the metabolism and sensitivity to insulin in different ways. Hence, their types, intensities and durations, and their individual and concurrent presence must be detected in order to determine the optimal insulin administration. The multivariable artificial pancreas approach provides a well-integrated and user-friendly technology with minimal burden on the user and mitigates the effects of unexpected physical activities and acute psychological stress inducements. Additionally, this technology would be safer by reducing the number and duration of hypoglycemic and hyperglycemic events, compared to APs based exclusively on continuous glucose monitoring device data. Such multivariable AP systems can only be developed by using a sophisticated multivariable approach that uses real-time information from continuous glucose monitoring devices and physiological variables obtained from wearable devices worn in free-living daily life.