相关实验视频
Updated: Jun 8, 2025

12:08
Improving IV Insulin Administration in a Community Hospital
Published on: June 11, 2012
18.8K
从有限的CGM数据中预测个性化血糖,使用增量重新训练的LSTM
IEEE transactions on bio-medical engineering
|November 8, 2024
概括
精确的血糖预测1型糖尿病 (T1D) 管理是改进了新的增量训练堆叠LSTM (IS-LSTM) 深度学习模型. 这种方法通过减少预测错误和确保临床安全来提高人工胰腺系统的性能.
科学领域:
- 生物医学工程 生物医学工程
- 医疗保健中的人工智能
- 内分泌学 在内分泌学.
背景情况:
- 精确的血糖 (BG) 预测对于1型糖尿病 (T1D) 管理中的人工胰腺 (AP) 系统至关重要.
- 目前的深度学习模型,如使用连续血糖监测 (CGM) 数据进行BG预测的长期短期记忆 (LSTM),通常需要广泛的个性化训练数据,并与多样化的葡萄糖变化 (GV) 斗争.
- 现有的方法在与T1D患者之间实现一致的预测准确性方面面临挑战.
研究的目的:
- 引入一种新的深度学习框架,即增量重新训练堆叠的LSTM (IS-LSTM),旨在提高T1D的BG预测准确度.
- 解决现有方法在数据要求和个体葡萄糖变异性方面的局限性.
- 提高个性化BG预测模型的效率和适应性.
主要方法:
- 开发了增量重新训练堆叠的LSTM (IS-LSTM) 框架,该框架利用逐渐适应个人数据和参数传输来实现高效的学习.
- 将IS-LSTM方法与三个基准方法进行比较,包括堆叠的LSTM,使用来自T1D患者的两个独立的CGM数据集 (OpenAPS和Replace-BG).
- 使用根平均平方误差 (RMSE) 评估预测准确度,并通过在各种预测地平线 (PHs) 上通过克拉克错误网格分析评估临床可行性.
主要成果:
- 与堆叠LSTM相比,IS-LSTM显著降低了RMSE:在30分钟的PH下从14.55到10.23毫克/分升 (OpenAPS) 和17.15到13.41毫克/分升 (Replace-BG).
- 克拉克错误网格分析证实了临床可行性,超过98.81% (30分钟PH) 和97.25% (60分钟PH) 的预测属于临床安全区域.
- 该方法在冷启动场景中表现出有效性,在没有广泛的先前数据的情况下,为新的CGM用户提供了准确的预测.
结论:
- 该IS-LSTM框架为T1D管理提供了个性化的BG预测的重大进展,优于现有的最先进的方法.
- 这种方法提高了AP系统的可靠性和安全性,通过提供准确和临床可行的BG预测,即使数据有限.
- IS-LSTM的适应性和效率使其成为改善T1D患者日常生活的有希望的工具,包括新的CGM用户.
相关概念视频
Hypoglycemia and Glucagon
152
Without prolonged fasting, healthy individuals maintain blood glucose levels above 3.5 mM due to a well-adapted neuroendocrine counterregulatory system that effectively prevents acute hypoglycemia, a potentially life-threatening condition. The primary clinical scenarios for hypoglycemia encompass diabetes treatment, inappropriate production of endogenous insulin or insulin-like substances by tumors, and the use of glucose-lowering agents in non-diabetic individuals. Notably, hypoglycemia in the...
152
Glucagon-like Receptor Agonists
300
Incretins include glucagon-like peptide-1 (GLP-1) and glucose-dependent insulinotropic polypeptide (GIP), which stimulate insulin secretion post-meals. In type 2 diabetes, GIP's efficacy is reduced, making GLP-1 a viable drug target. GIP originates from preproGIP.
GLP-1, when administered in high doses intravenously, triggers insulin secretion, inhibits glucagon release, slows gastric emptying, reduces food intake, and restores normal insulin secretion. However, its rapid inactivation by...
GLP-1, when administered in high doses intravenously, triggers insulin secretion, inhibits glucagon release, slows gastric emptying, reduces food intake, and restores normal insulin secretion. However, its rapid inactivation by...
300
Errors occurring during blood pressure monitoring
605
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
605

