首页/论文/2009.04524

arXiv 2009.045242020-09-08cs.LGq-bio.QM

Interpreting Deep Glucose Predictive Models for Diabetic People Using RETAIN

CNRS-LIMSI（法国国家科学研究中心-计算机科学与机械实验室）；Université Paris Saclay（巴黎萨克雷大学）；Samovar, CNRS, Télécom SudParis（萨莫瓦尔实验室，法国国家科学研究中心，南巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）；Université Paris 8（巴黎第八大学）

Maxime De Bois, Mounîm A. El Yacoubi, Mehdi Ammi

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Progress in the biomedical field through the use of deep learning is hindered by the lack of interpretability of the models. In this paper, we study the RETAIN architecture for the forecasting of future glucose values for diabetic people. Thanks to its two-level attention mechanism, the RETAIN model is interpretable while remaining as efficient as standard neural networks. We evaluate the model on a real-world type-2 diabetic population and we compare it to a random forest model and a LSTM-based recurrent neural network. Our results show that the RETAIN model outperforms the former and equals the latter on common accuracy metrics and clinical acceptability metrics, thereby proving its legitimacy in the context of glucose level forecasting. Furthermore, we propose tools to take advantage of the RETAIN interpretable nature. As informative for the patients as for the practitioners, it can enhance the understanding of the predictions made by the model and improve the design of future glucose predictive models.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Enhancing the Interpretability of Deep Models in Heathcare Through Attention: Application to Glucose Forecasting for Diabetic People

CNRS-LIMSI（法国国家科学研究中心-计算机科学与机械信息实验室）；Université Paris-Saclay（巴黎-萨克雷大学）；Samovar, CNRS, Télécom SudParis, Institut Polytechnique de Paris（萨莫瓦尔实验室，法国国家科学研究中心，南巴黎电信学院，巴黎综合理工学院）；Université Paris 8（巴黎第八大学）

The adoption of deep learning in healthcare is hindered by their "black box" nature. In this paper, we explore the RETAIN architecture for the task of glusose forecasting for diabetic people. By using a two-level attention mechanism, the recurrent-neural-network-based RETAIN model is interpretable. We evaluate the RETAIN model on the type-2 IDIAB and the type-1 OhioT1DM datasets by comparing its statistical and clinical performances against two deep models and three models based on decision trees. We show that the RETAIN model offers a very good compromise between accuracy and interpretability…

2020-09-08cs.AIcs.LGstat.ML

Integration of Clinical Criteria into the Training of Deep Models: Application to Glucose Prediction for Diabetic People

CNRS-LIMSI（法国国家科学研究中心-计算机科学与数学应用研究所）；Université Paris-Saclay（巴黎萨克雷大学）；Samovar（萨莫瓦尔实验室）；CNRS（法国国家科学研究中心）；Télécom SudParis（南巴黎电信学院）；Institut Polytechnique de Paris（巴黎理工学院）；Université Paris 8（巴黎第八大学）

Standard objective functions used during the training of neural-network-based predictive models do not consider clinical criteria, leading to models that are not necessarily clinically acceptable. In this study, we look at this problem from the perspective of the forecasting of future glucose values for diabetic people. In this study, we propose the coherent mean squared glycemic error (gcMSE) loss function. It penalizes the model during its training not only of the prediction errors, but also on the predicted variation errors which is important in glucose prediction. Moreover, it makes possib…

2020-09-23cs.LGq-bio.QM

基于深度学习的糖尿病血血糖预测方法

A deep learning approach to diabetic blood glucose prediction

Claremont Graduate University（克莱蒙特研究生大学）；Johann Radon Institute（约翰·拉东研究所）；Vanderbilt University（范德堡大学）

本文提出利用深度学习对糖尿病患者血糖进行30分钟预测，通过选取部分患者数据训练模型，验证深度学习在该任务中的优越性，并展示如何利用领域知识构建简洁的深度表示。

2017-07-18cs.LGcs.NAmath.NA

Personalized Understanding of Blood Glucose Dynamics via Mobile Sensor Data

New York University（纽约大学）

Continuous Blood Glucose (CGM) monitors have revolutionized the ability of diabetics to manage their blood glucose, and paved the way for artificial pancreas systems. In this paper we augment CGM data with sensor input collected by a smart phone and use it to provide analytical tools for patients and clinicians. We collected GPS data, activity classifications, and blood glucose data with a custom iOS application over a 9 month period from a single free-living type-1 diabetic patient. This data set is novel in terms of it's size, the inclusion of GPS data, and the fact that it was collected non…

2023-02-02cs.HCcs.LG

Adversarial Multi-Source Transfer Learning in Healthcare: Application to Glucose Prediction for Diabetic People

CNRS-LIMSI（法国国家科学研究中心-LIMSI）；Université Paris-Saclay（巴黎萨克雷大学）；Samovar；CNRS（法国国家科学研究中心）；Télécom SudParis（巴黎南部电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）；Université Paris 8（巴黎第八大学）

Deep learning has yet to revolutionize general practices in healthcare, despite promising results for some specific tasks. This is partly due to data being in insufficient quantities hurting the training of the models. To address this issue, data from multiple health actors or patients could be combined by capitalizing on their heterogeneity through the use of transfer learning. To improve the quality of the transfer between multiple sources of data, we propose a multi-source adversarial transfer learning framework that enables the learning of a feature representation that is similar across th…

2020-06-29cs.CVcs.LGeess.IV

Learning Insulin-Glucose Dynamics in the Wild

Apple（苹果公司）

We develop a new model of insulin-glucose dynamics for forecasting blood glucose in type 1 diabetics. We augment an existing biomedical model by introducing time-varying dynamics driven by a machine learning sequence model. Our model maintains a physiologically plausible inductive bias and clinically interpretable parameters -- e.g., insulin sensitivity -- while inheriting the flexibility of modern pattern recognition algorithms. Critical to modeling success are the flexible, but structured representations of subject variability with a sequence model. In contrast, less constrained models like …

2020-08-06cs.LGstat.APstat.ML

更多相关论文收起更多论文

基于相位图像表示学习的深度学习增强可穿戴实时葡萄糖监测

Enhancing Wearable based Real-Time Glucose Monitoring via Phasic Image Representation Learning based Deep Learning

University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；University of Massachusetts Chan Medical School（马萨诸塞大学陈医学院）；National Institute on Aging（国家衰老研究所）

针对可穿戴设备葡萄糖监测因数据集小而受限的问题，提出一种利用频域修改递归图结合机器学习的新方法，有效提取特征，将实时葡萄糖预测准确率提升至超越87%基准。

2024-06-12cs.LGeess.SP

用于时间序列预处理和糖尿病患者血糖水平预测的多任务VAE

A Multitask VAE for Time Series Preprocessing and Prediction of Blood Glucose Level

Air Liquide R&D（Air Liquide 研发）

本文提出了一种多任务VAE模型，用于时间序列数据预处理和糖尿病患者血糖水平预测，通过变分自编码器和循环VAE结合，提升了预测准确性。

2025-07-25cs.AIcs.LGeess.SP

GLYFE: Review and Benchmark of Personalized Glucose Predictive Models in Type-1 Diabetes

CNRS-LIMSI（法国国家科学研究中心-LIMSI）；Université Paris-Saclay（巴黎萨克雷大学）；Université Paris 8（巴黎第八大学）；Samovar；CNRS（法国国家科学研究中心）；Télécom SudParis（南巴黎电信学院）；Institut Polytechnique de Paris（巴黎综合理工学院）

Due to the sensitive nature of diabetes-related data, preventing them from being shared between studies, progress in the field of glucose prediction is hard to assess. To address this issue, we present GLYFE (GLYcemia Forecasting Evaluation), a benchmark of machine-learning-based glucose-predictive models. To ensure the reproducibility of the results and the usability of the benchmark in the future, we provide extensive details about the data flow. Two datasets are used, the first comprising 10 in-silico adults from the UVA/Padova Type 1 Diabetes Metabolic Simulator (T1DMS) and the second bein…

2020-06-29cs.LGeess.SPq-bio.QM

Forecasting blood sugar levels in Diabetes with univariate algorithms

University of Málaga（马拉加大学）

AI procedures joined with wearable gadgets can convey exact transient blood glucose level forecast models. Also, such models can learn customized glucose-insulin elements dependent on the sensor information gathered by observing a few parts of the physiological condition and every day movement of a person. Up to this point, the predominant methodology for creating information driven forecast models was to gather "however much information as could be expected" to help doctors and patients ideally change treatment. The goal of this work was to examine the base information assortment, volume, and…

2021-01-21cs.LG

LSTMs and Deep Residual Networks for Carbohydrate and Bolus Recommendations in Type 1 Diabetes Management

Ohio University（俄亥俄大学）；University of North Carolina at Charlotte（北卡罗来纳大学夏洛特分校）

To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based …

2021-03-06cs.LG

使用过采样和特征增强的深度学习技术进行糖尿病检测

Diabetes detection using deep learning techniques with oversampling and feature augmentation

Universidad de León（莱昂大学）

本文提出基于VAE数据增强、SAE特征增强和CNN分类的深度学习流程，在皮马印第安人数据集上达到92.31%准确率，较现有技术提升3.17%。

2024-02-03cs.CVcs.LGeess.IV