相关实验视频
Updated: Jan 9, 2026

13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.9K
评估输入特征对深度学习模型对预测血糖的输入特征的影响
概括
对于1型糖尿病 (T1D) 血糖 (BG) 预测的深度学习模型随着更多的数据输入而得到改善. 添加餐,胰岛素和体力活动 (PA) 数据可以提高BG预测的准确性,尽管临床益处很小.
科学领域:
- 人工智能的人工智能
- 生物医学工程 生物医学工程
- 内分泌学 在内分泌学.
背景情况:
- 准确的血糖 (BG) 预测对于1型糖尿病 (T1D) 管理至关重要,特别是对于决策支持系统和人工胰腺设备.
- 深度学习 (DL) 模型对BG预测有希望,但各种输入特征对其性能的影响需要进一步调查.
研究的目的:
- 评估不同输入特征,包括持续血糖监测 (CGM),餐 (碳水化合物摄入量),胰岛素和体力活动 (PA) 数据,对DL模型在T1D中用于BG预测的性能的影响.
- 在五个DL模型中评估七种不同的输入配置,使用来自大型T1D队列的真实数据.
主要方法:
- 训练和评估了五个DL模型,使用497名T1D患者的四周日常生活数据.
- 对比了七种输入配置,从单变CGM到包括CGM,胰岛素,碳水化合物 (CHO) 摄入量,心率 (HR) 和运动数据在内的综合模型.
- 在30分钟预测地平线 (PH) 上使用根平均平方误差 (RMSE) 和时间增益 (TG) 评估模型性能.
主要成果:
- 结合额外的输入功能,在30分钟的PH时逐步提高了DL模型的性能.
- 该CNN-变压器模型显示了最大的改进;结合所有功能,RMSE从21.02 ± 3.5 mg/dL减少到18.63 ± 4.18 mg/dL,TG从10.38 ± 1.33 分钟增加到12.12 ± 2.64 分钟.
- 在运动期间的预测准确性只有在包括PA数据时才显著改善 (RMSE从28.72 ± 9.18 mg/dL减少到24.7 ± 7.8 mg/dL).
结论:
- 包括各种数据输入,如餐,胰岛素和PA,提高了DL模型在T1D中用于BG预测的性能.
- 虽然观察到有统计学意义的改善,但这些变化的适度大小表明直接临床益处有限.
- 需要进一步的研究来优化DL模型,并将性能增长转化为T1D管理的切实临床优势.
相关概念视频
Hormones Regulating Blood Glucose
6.3K
Insulin is released by beta cells of the pancreas when blood glucose levels are high. It facilitates glucose absorption and utilization in insulin-dependent cells with insulin receptors on their plasma membranes. Insulin promotes glucose uptake by increasing the number of glucose transport proteins in the cell membrane, allowing glucose to enter the cell. As a result, glucose utilization and ATP production are enhanced.
In addition to accelerating glucose uptake and utilization, insulin has...
In addition to accelerating glucose uptake and utilization, insulin has...
6.3K
Neural Regulation of Blood Pressure
6.8K
The neural regulation of blood pressure involves intricate interactions between the autonomic nervous system (ANS) and cardiovascular system, ensuring adequate perfusion of tissues. This regulation primarily occurs through baroreceptor and chemoreceptor reflexes, involving both short-term and long-term mechanisms.
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...
6.8K

