Non-Invasive Glucose Prediction System Enhanced by Mixed Linear Models and Meta-Forests for Domain Generalization

arXiv - CS - Machine Learning Pub Date : 2024-09-11 DOI:arxiv-2409.07308

Yuyang Sun, Panagiotis Kosmas

{"title":"Non-Invasive Glucose Prediction System Enhanced by Mixed Linear Models and Meta-Forests for Domain Generalization","authors":"Yuyang Sun, Panagiotis Kosmas","doi":"arxiv-2409.07308","DOIUrl":null,"url":null,"abstract":"In this study, we present a non-invasive glucose prediction system that\nintegrates Near-Infrared (NIR) spectroscopy and millimeter-wave (mm-wave)\nsensing. We employ a Mixed Linear Model (MixedLM) to analyze the association\nbetween mm-wave frequency S_21 parameters and blood glucose levels within a\nheterogeneous dataset. The MixedLM method considers inter-subject variability\nand integrates multiple predictors, offering a more comprehensive analysis than\ntraditional correlation analysis. Additionally, we incorporate a Domain\nGeneralization (DG) model, Meta-forests, to effectively handle domain variance\nin the dataset, enhancing the model's adaptability to individual differences.\nOur results demonstrate promising accuracy in glucose prediction for unseen\nsubjects, with a mean absolute error (MAE) of 17.47 mg/dL, a root mean square\nerror (RMSE) of 31.83 mg/dL, and a mean absolute percentage error (MAPE) of\n10.88%, highlighting its potential for clinical application. This study marks a\nsignificant step towards developing accurate, personalized, and non-invasive\nglucose monitoring systems, contributing to improved diabetes management.","PeriodicalId":501301,"journal":{"name":"arXiv - CS - Machine Learning","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Machine Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07308","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

Abstract

In this study, we present a non-invasive glucose prediction system that integrates Near-Infrared (NIR) spectroscopy and millimeter-wave (mm-wave) sensing. We employ a Mixed Linear Model (MixedLM) to analyze the association between mm-wave frequency S_21 parameters and blood glucose levels within a heterogeneous dataset. The MixedLM method considers inter-subject variability and integrates multiple predictors, offering a more comprehensive analysis than traditional correlation analysis. Additionally, we incorporate a Domain Generalization (DG) model, Meta-forests, to effectively handle domain variance in the dataset, enhancing the model's adaptability to individual differences. Our results demonstrate promising accuracy in glucose prediction for unseen subjects, with a mean absolute error (MAE) of 17.47 mg/dL, a root mean square error (RMSE) of 31.83 mg/dL, and a mean absolute percentage error (MAPE) of 10.88%, highlighting its potential for clinical application. This study marks a significant step towards developing accurate, personalized, and non-invasive glucose monitoring systems, contributing to improved diabetes management.

查看原文本刊更多论文

利用混合线性模型和元森林实现领域泛化的非侵入式葡萄糖预测系统

在本研究中，我们介绍了一种集成了近红外（NIR）光谱和毫米波（mm-wave）传感技术的无创血糖预测系统。我们采用混合线性模型（MixedLM）来分析异构数据集中毫米波频率 S_21 参数与血糖水平之间的关联。混合线性模型方法考虑了受试者之间的变异性，并整合了多个预测因子，提供了比传统相关分析更全面的分析。我们的研究结果表明，该方法对非受试者的血糖预测准确性很高，平均绝对误差（MAE）为 17.47 mg/dL，均方根误差（RMSE）为 31.83 mg/dL，平均绝对百分比误差（MAPE）为 10.88%，这突出表明该方法具有临床应用潜力。这项研究标志着在开发精确、个性化和无创葡萄糖监测系统方面迈出了重要一步，有助于改善糖尿病管理。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

arXiv - CS - Machine Learning

自引率

0.00%

发文量