Using machine learning methods to predict the risk of exercise-induced hypoglycemia in people with Type 1 diabetes

Exercise offers a number of benefits to individuals with type 1 diabetes (T1D) (1), including reduced risk of coronary artery disease and stroke, as well as improved blood pressure (2,3), lowered daily insulin requirements (3), and reduced diabetic complications, such as retinopathy and neuropathy (4). The American Diabetic Association recommends 150 minutes of aerobic exercise a week for people with T1D (5) but few are reaching this target (3,6,7). One of the main reasons for this is fear of exercise-induced hypoglycaemia (8–11). Hypoglycemia occurs when blood glucose (BG) drops below 3.9 mmol/L and can vary in severity, with side effects ranging from dizziness, anxiety and nausea to unconsciousness, seizures and even death (12). Exercised-induced hypoglycaemia can occur not only during exercise, but for up to 36 after exercise and also overnight (6,13). In addition, understanding glycaemic response to exercise is challenging for people with T1D since it is affected by so many factors. Firstly, different types of exercise will have different effects on BG levels, for example aerobic exercise will decrease BG levels whereas anaerobic exercise will increase levels (1). The glycemic response is also affected by duration and intensity of exercise, amount of insulin on board, location of insulin delivery, the starting BG before exercise, and the last meal or snack (14). This is further complicated by the fact that people with T1D often will not notice their symptoms when exercising (15). This complex interaction of factors make hypoglycaemia around exercise very difficult to predict and prevent. It is therefore understandable that people with T1D are less active and reluctant to exercise, when in addition to common barriers to exercise reported in the general population, they may also experience the discomfort of changes in glucose levels and heightened risk of hypoglycaemia. Wearable sensors are becoming increasingly common tools in the management of T1D. From continuous glucose monitors (CGMs) and insulin pumps, to smartphone apps, heart rate (HR) monitors, and physical activity trackers available (16), the accessibility of these devices is opening up many opportunities to get relevant data. If we can harness data from these devices to effectively predict hypoglycaemia around exercise, we can offer people with T1D practical guidance for effectively avoiding hypoglycaemia around exercise, enabling them to feel more confident about exercising. Our goal is to utilise wearable technology paired with machine learning techniques to develop a tool that predicts whether hypoglycaemia is going to occur during or after exercise and provide them with simple, actionable guidance. With this, we hope to assist people with T1D allow patients to take action to avoid hypoglycaemia and thus exercise more safely.

运动对1型糖尿病（Type 1 Diabetes, T1D）患者具有多重获益（1）：可降低冠状动脉疾病与脑卒中的发病风险，改善血压水平（2,3），减少每日胰岛素需求量（3），并减轻糖尿病并发症（如视网膜病变与神经病变）的发生（4）。美国糖尿病协会（American Diabetes Association, ADA）建议1型糖尿病患者每周进行150分钟有氧运动（5），但仅有少数患者能达到这一目标（3,6,7）。其中主要原因之一是对运动诱发性低血糖（exercise-induced hypoglycaemia）的恐惧（8–11）。当血糖（blood glucose, BG）低于3.9 mmol/L时即发生低血糖，其严重程度不一，不良反应可表现为头晕、焦虑、恶心，乃至意识丧失、抽搐甚至死亡（12）。运动诱发性低血糖不仅可在运动过程中发生，还可在运动后长达36小时内乃至夜间出现（6,13）。此外，1型糖尿病患者难以把握运动后的血糖应答，因其受诸多因素影响：首先，不同运动类型对血糖水平的影响各异——有氧运动可降低血糖，而无氧运动则会升高血糖（1）；血糖应答还受运动时长、运动强度、体内胰岛素存量、胰岛素注射部位、运动前初始血糖水平以及末次进餐或加餐情况的影响（14）。而1型糖尿病患者在运动时常无法察觉自身症状，这进一步加剧了上述情况的复杂性（15）。这些因素间的复杂相互作用使得运动前后的低血糖极难预测和预防。因此，1型糖尿病患者活动量较少且不愿运动便不难理解：除了普通人群普遍存在的运动障碍外，他们还可能承受血糖变化带来的不适，并面临更高的低血糖风险。可穿戴传感器正逐渐成为1型糖尿病管理中愈发常用的工具。目前已有的设备包括连续血糖监测仪（continuous glucose monitor, CGM）、胰岛素泵、智能手机应用程序、心率（heart rate, HR）监测仪以及运动追踪器等（16），这些设备的普及为获取相关数据提供了诸多契机。若能利用这些设备产生的数据有效预测运动前后的低血糖情况，便可为1型糖尿病患者提供切实可行的指导，帮助其有效规避运动相关低血糖风险，从而提升其运动信心。本研究的目标是结合可穿戴技术与机器学习技术，开发一款可预测运动过程中或运动后是否会发生低血糖的工具，并为患者提供简单易用、可落地的指导。借此，我们期望助力1型糖尿病患者采取措施规避低血糖，进而更安全地开展运动。