A comparative study of COVID-19 point-of-care detection across human biofluids using MEMS-based near-infrared spectroscopy and machine learning

IF 3.3 4区医学 Q3 ENGINEERING, BIOMEDICAL

Biomedical Microdevices Pub Date : 2026-04-13 DOI:10.1007/s10544-026-00806-0

Ahmed Abdelkhalik, Mazen Erfan, Bassem Mortada, Mohamed Gaber, Moataz Bellah Abdelaleem, Hala Hafez, Samia A. Girgis, Ossama Mansour, Bassam Saadany, Yasser M. Sabry, Diaa Khalil

{"title":"A comparative study of COVID-19 point-of-care detection across human biofluids using MEMS-based near-infrared spectroscopy and machine learning","authors":"Ahmed Abdelkhalik, Mazen Erfan, Bassem Mortada, Mohamed Gaber, Moataz Bellah Abdelaleem, Hala Hafez, Samia A. Girgis, Ossama Mansour, Bassam Saadany, Yasser M. Sabry, Diaa Khalil","doi":"10.1007/s10544-026-00806-0","DOIUrl":null,"url":null,"abstract":"<div>\n \n <p>This study explores the use of near-infrared (NIR) spectroscopy in the 1.3–2.6 μm wavelength range, employing a handheld miniaturized microelectromechanical systems (MEMS)-based spectrometer for the rapid, non-invasive detection of COVID-19 from various biofluids. A total of 238 samples—including nasopharyngeal (NSP) swabs, nasal swabs, and saliva—from both COVID-19 positive and negative individuals are analysed. Machine learning algorithms process the spectral data to develop predictive models for the disease classification. Models based on a single biofluid achieve detection accuracies between 75% and 80%, while combining scans from multiple biofluids of the same individual improves accuracy to 88%. The study highlights trade-offs between sample accessibility and diagnostic performance. Overall, the findings demonstrate that NIR spectroscopy serves as a viable low-cost, portable, and rapid point-of-care (POC) solution, with strong potential for scalable mass screening—particularly in resource-limited settings.</p>\n </div>","PeriodicalId":490,"journal":{"name":"Biomedical Microdevices","volume":"28 2","pages":""},"PeriodicalIF":3.3000,"publicationDate":"2026-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13076386/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Biomedical Microdevices","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10544-026-00806-0","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, BIOMEDICAL","Score":null,"Total":0}

引用次数: 0

Abstract

This study explores the use of near-infrared (NIR) spectroscopy in the 1.3–2.6 μm wavelength range, employing a handheld miniaturized microelectromechanical systems (MEMS)-based spectrometer for the rapid, non-invasive detection of COVID-19 from various biofluids. A total of 238 samples—including nasopharyngeal (NSP) swabs, nasal swabs, and saliva—from both COVID-19 positive and negative individuals are analysed. Machine learning algorithms process the spectral data to develop predictive models for the disease classification. Models based on a single biofluid achieve detection accuracies between 75% and 80%, while combining scans from multiple biofluids of the same individual improves accuracy to 88%. The study highlights trade-offs between sample accessibility and diagnostic performance. Overall, the findings demonstrate that NIR spectroscopy serves as a viable low-cost, portable, and rapid point-of-care (POC) solution, with strong potential for scalable mass screening—particularly in resource-limited settings.

查看原文本刊更多论文

基于mems的近红外光谱和机器学习在人体生物体液中检测COVID-19的比较研究

本研究探索了在1.3-2.6 μm波长范围内使用近红外（NIR）光谱，采用基于手持式小型化微机电系统（MEMS）的光谱仪，从各种生物体液中快速、无创地检测COVID-19。对来自COVID-19阳性和阴性个体的238份样本（包括鼻咽拭子、鼻拭子和唾液）进行了分析。机器学习算法处理光谱数据来开发疾病分类的预测模型。基于单一生物流体的模型的检测精度在75%到80%之间，而结合同一个体的多种生物流体的扫描将精度提高到88%。该研究强调了样本可访问性和诊断性能之间的权衡。总的来说，研究结果表明，近红外光谱技术是一种可行的低成本、便携、快速的医疗现场（POC）解决方案，具有强大的大规模筛查潜力，特别是在资源有限的环境中。

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

Biomedical Microdevices 工程技术-工程：生物医学

CiteScore

6.90

自引率

3.60%

发文量

审稿时长

6 months

期刊介绍： Biomedical Microdevices: BioMEMS and Biomedical Nanotechnology is an interdisciplinary periodical devoted to all aspects of research in the medical diagnostic and therapeutic applications of Micro-Electro-Mechanical Systems (BioMEMS) and nanotechnology for medicine and biology. General subjects of interest include the design, characterization, testing, modeling and clinical validation of microfabricated systems, and their integration on-chip and in larger functional units. The specific interests of the Journal include systems for neural stimulation and recording, bioseparation technologies such as nanofilters and electrophoretic equipment, miniaturized analytic and DNA identification systems, biosensors, and micro/nanotechnologies for cell and tissue research, tissue engineering, cell transplantation, and the controlled release of drugs and biological molecules. Contributions reporting on fundamental and applied investigations of the material science, biochemistry, and physics of biomedical microdevices and nanotechnology are encouraged. A non-exhaustive list of fields of interest includes: nanoparticle synthesis, characterization, and validation of therapeutic or imaging efficacy in animal models; biocompatibility; biochemical modification of microfabricated devices, with reference to non-specific protein adsorption, and the active immobilization and patterning of proteins on micro/nanofabricated surfaces; the dynamics of fluids in micro-and-nano-fabricated channels; the electromechanical and structural response of micro/nanofabricated systems; the interactions of microdevices with cells and tissues, including biocompatibility and biodegradation studies; variations in the characteristics of the systems as a function of the micro/nanofabrication parameters.