Development and Evaluation of Personalized Explainable Machine Learning Models to Predict and Prevent Nocturnal Hypoglycemia in Type 1 Diabetes

开发和评估个性化可解释机器学习模型以预测和预防 1 型糖尿病夜间低血糖

• 批准号: 10491126
• 负责人: Clara Marcela Mosquera-Lopez
• 金额: $ 16.5万
• 依托单位: OREGON HEALTH & SCIENCE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-21 至 2024-07-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10491126
• 关键词: Accounting; Adult; Affect; Algorithms; Beds; Big Data; Carbohydrates; Cellular Phone; Cessation of life; Clinic; Clinical Research; Consumption; Cross-Over Studies; Dangerousness; Data; Data Set; Detection; Development; Emergency Care; Engineering; Evaluation; Event; Exercise; Fiber; Fright; Glucose; Human; Hyperglycemia; Hypoglycemia; Individual; Infusion Pumps; Injection of therapeutic agent; Injections; Injury; Insulin; Insulin-Dependent Diabetes Mellitus; Intervention; Learning; Macronutrients Nutrition; Measurement; Measures; Modeling; Nutrient; Outcome Measure; Participant; Persons; Phase; Physical activity; Pump; Randomized; Registries; Risk; Running; Seizures; Sensitivity and Specificity; Sleep; Specificity; Symptoms; Syndrome; System; Testing; Time; Training; Unconscious State; Update; base; blood glucose regulation; cohort; comparison intervention; data management; design; diabetes management; diabetes mellitus therapy; experience; glycemic control; high risk; hypoglycemia unawareness; improved; intervention effect; large datasets; machine learning model; machine learning prediction; personalized decision; poor sleep; population based; prediction algorithm; predictive modeling; prevent; primary outcome; recruit; secondary outcome; sensor; sensor technology; side effect; simulation; sleep quality; subcutaneous; support tools; transfer learning; wireless sensor

Development and Evaluation of Personalized Explainable Machine Learning Models to Predict and Prevent Nocturnal Hypoglycemia in Type 1 Diabetes Project Summary Hypoglycemia (glucose < 70 mg/dL) remains the limiting factor for achieving optimal glycemic control in type 1 diabetes (T1D), with nocturnal hypoglycemia being particularly dangerous. Nocturnal hypoglycemia may result in physical injury, poor sleep quality, fear of hypoglycemia, and hypoglycemia unawareness. Severe episodes can cause seizures and unconsciousness requiring emergency care, and even death (dead in bed syndrome). While automated insulin delivery (AID) systems have shown benefits in glucose control during the night, nighttime hypoglycemia still occurs. Moreover, many people with T1D manage their glucose with continuous subcutaneous infusion pump (CSII) therapy or multiple daily insulin injections (MDI) therapy. Data updated between 2013 and 2014 from 16,061 individuals with T1D participating in the T1D Exchange clinic registry showed that approximately 40% participants managed their glucose with MDI. In this project, we propose to develop and evaluate a personalized decision support tool that collects and analyzes glucose measurements, insulin, meals, and physical activity data to predict at bedtime the likelihood of overnight hypoglycemia and recommend a proactive carbohydrate intervention to substantially reduce nocturnal hypoglycemia. In the engineering development phase of the project, we will use unique datasets of time-matched glucose management data (i.e., continuous glucose measurements, insulin, meals, and exercise) from pump, closed- loop and MDI users to extract information about the major contributors to nocturnal hypoglycemia risk and train a population-based prediction model that will be personalized over time to better capture inter-subject variability. We will design a bedtime intervention consisting of a bedtime smart snack with variable nutrient content that can prevent nighttime hypoglycemia. Snacks will vary by macronutrient content and size to optimize time to peak post-prandial glycemia that will match the timing to predicted episode of hypoglycemia. We will conduct a randomized cross-over study to evaluate our smartphone-based decision support tool on a cohort of 20 people with T1D who are MDI users and are at higher risk of experiencing hypoglycemia. Participants will be randomly assigned to either first use CGM only (control period) followed by a smartphone- based decision support tool + nocturnal hypoglycemia intervention (intervention period), or vice-versa. The control and intervention periods will have a duration of three weeks each. We will measure the effect of the intervention by comparing the percent time in nocturnal hypoglycemia during the control period vs. the intervention period. We will also retrospectively measure the accuracy of the prediction model in predicting nocturnal hypoglycemia using data from the control period. We expect that the proposed bedtime intervention will lead to a significant reduction in time spent in hypoglycemia overnight of at least 50% reduction relative to baseline.

个性化可解释机器学习模型的开发和评估，以预测和 预防1型糖尿病的夜间低血糖 项目摘要 低血糖（血糖< 70 mg/dL）仍然是1型糖尿病患者实现最佳血糖控制的限制因素 糖尿病（T1 D），夜间低血糖特别危险。可能导致夜间低血糖 身体损伤、睡眠质量差、低血糖恐惧和低血糖无意识。重度发作 可导致癫痫发作和需要紧急护理的意识丧失，甚至死亡（床上死亡综合征）。 虽然自动胰岛素输送（AID）系统已经显示出在夜间血糖控制方面的益处， 夜间低血糖仍然发生。此外，许多患有T1 D的人通过持续的血糖控制来管理他们的血糖。 皮下输注泵（CSII）治疗或每日多次胰岛素注射（MDI）治疗。更新的数据 2013年至2014年期间，16，061名T1 D患者参加了T1 D Exchange诊所登记 结果显示，大约40%的参与者使用MDI管理血糖。在这个项目中，我们建议 开发和评估收集和分析葡萄糖测量结果的个性化决策支持工具， 胰岛素、膳食和体力活动数据，以预测睡前发生夜间低血糖的可能性， 建议积极的碳水化合物干预，以大大减少夜间低血糖。在 在项目的工程开发阶段，我们将使用时间匹配的葡萄糖的独特数据集 管理数据（即，连续葡萄糖测量、胰岛素、膳食和运动）， 循环和MDI用户提取有关夜间低血糖风险主要因素的信息，并进行培训 一个基于人群的预测模型，将随着时间的推移进行个性化，以更好地捕捉受试者间的 可变性我们将设计一个睡前干预，包括一个睡前智能零食与可变的营养 可以预防夜间低血糖的内容。零食将因常量营养素含量和大小而异， 优化达到餐后血糖峰值的时间，使其与预测的低血糖发作时间相匹配。 我们将进行一项随机交叉研究，以评估我们基于智能手机的决策支持工具， 20名MDI使用者和发生低血糖风险较高的T1 D患者队列。 受试者将被随机分配至仅首次使用CGM（对照期），随后使用智能手机- 基于决策支持工具+夜间低血糖干预（干预期），反之亦然。的 控制期和干预期各为期三周。我们将测量 通过比较对照期间夜间低血糖的时间百分比与 干预期。我们还将回顾性地测量预测模型在预测 使用对照期的数据进行夜间低血糖。我们希望拟议中的睡前干预 将导致低血糖过夜时间显著减少至少50%， 基线。

项目成果

Combining uncertainty-aware predictive modeling and a bedtime Smart Snack intervention to prevent nocturnal hypoglycemia in people with type 1 diabetes on multiple daily injections.

将不确定性感知预测模型与睡前智能零食干预相结合，预防每日多次注射的 1 型糖尿病患者出现夜间低血糖。

• DOI: 10.1093/jamia/ocad196
• 发表时间: 2023
• 期刊: Journal of the American Medical Informatics Association : JAMIA
• 作者: Mosquera-Lopez,Clara;Roquemen-Echeverri,Valentina;Tyler,NicholeS;Patton,SusanaR;Clements,MarkA;Martin,CorbyK;Riddell,MichaelC;Gal,RobinL;Gillingham,Melanie;Wilson,LeahM;Castle,JessicaR;Jacobs,PeterG
• 通讯作者: Jacobs,PeterG