AI Article Synopsis
- Self-monitoring of glucose is crucial for diabetes management, but current methods are often invasive and uncomfortable for users.
- This study tested a noninvasive glucose monitoring system that uses a wrist-mounted sensor and AI to predict glucose levels from microwave signal variations.
- Results showed an average predictive accuracy (MARD) of 10.3%, indicating that this new method could potentially rival existing commercial glucose monitoring options, providing a better experience for users.
Article Abstract
Background: Self-monitoring of glucose is important to the successful management of diabetes; however, existing monitoring methods require a degree of invasive measurement which can be unpleasant for users. This study investigates the accuracy of a noninvasive glucose monitoring system that analyses spectral variations in microwave signals.
Methods: An open-label, pilot design study was conducted with four cohorts (N = 5/cohort). In each session, a dial-resonating sensor (DRS) attached to the wrist automatically collected data every 60 seconds, with a novel artificial intelligence (AI) model converting signal resonance output to a glucose prediction. Plasma glucose was measured in venous blood samples every 5 minutes for Cohorts 1 to 3 and every 10 minutes for Cohort 4. Accuracy was evaluated by calculating the mean absolute relative difference (MARD) between the DRS and plasma glucose values.
Results: Accurate plasma glucose predictions were obtained across all four cohorts using a random sampling procedure applied to the full four-cohort data set, with an average MARD of 10.3%. A statistical analysis demonstrates the quality of these predictions, with a surveillance error grid (SEG) plot indicating no data pairs falling into the high-risk zones.
Conclusions: These findings show that MARD values approaching accuracies comparable to current commercial alternatives can be obtained from a multiparticipant pilot study with the application of AI. Microwave biosensors and AI models show promise for improving the accuracy and convenience of glucose monitoring systems for people with diabetes.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11571554 | PMC |
| http://dx.doi.org/10.1177/19322968241252819 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Genotype-negative multiple endocrine neoplasia type 1 with prolactinoma, hyperparathyroidism, and subclinical Cushing's syndrome accompanied by hyperglycemia: a case report.
Front Endocrinol (Lausanne)
December 2024
Diabetes Center, Ohta Nishinouchi Hospital, Koriyama, Fukushima, Japan.
Background: Multiple endocrine neoplasia type 1 (MEN1) is a rare autosomal dominant disorder, accompanied by multiple endocrine neoplasms of the parathyroid, pancreas, pituitary, and other neoplasms in the adrenal glands. However, in some cases, patients clinically diagnosed with MEN1 may be genotype-negative.
Case Presentation: A 56-year-old female was diagnosed with MEN1 based on a macroprolactinoma (19 mm in diameter), primary hyperparathyroidism, and a cortisol-producing adrenal adenoma, without a family history.
Anti-diabetic effects of GLP-1 receptor agonists on obese and overweight patients across diabetes status, administration routes, treatment duration and baseline characteristics: A systematic review.
Diabetes Obes Metab
December 2024
Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
Glucagon-like peptide-1 receptor agonists (GLP-1 RAs) are increasingly used for anti-obesity indications. However, little is known of the comparative effect of GLP-1 RAs and their glycemic impact across the different routes of administration, diabetic statuses and durations of prescription. PubMed, EMBASE and CENTRAL were searched from inception to 13 February 2024.
View Article and Find Full Text PDFLow-added sugar dietary intervention study to mitigate glucose intolerance and improve body composition in adults with cystic fibrosis: a protocol of a double-blind, randomised study.
BMJ Open
December 2024
Division of Endocrinology, Metabolism, and Lipids; Department of Medicine, Emory University School of Medicine, Atlanta, Georgia, USA
Introduction: People with cystic fibrosis (PwCF) are at high risk for developing cystic fibrosis (CF)-related diabetes (CFRD), which worsens morbidity and mortality. Although the pathological events leading to the development of CFRD are complex and not completely understood, dietary factors may play a role. For example, habitual intake of dietary added sugar (i.
View Article and Find Full Text PDFExploring insulin resistance and pancreatic function in individuals with overweight and obesity: Insights from OGTTs and IRTs.
Diabetes Res Clin Pract
December 2024
Department of Clinical Laboratory, Tianjin Medical University General Hospital, No.154 Anshan Road, Heping District, Tianjin 300052, China. Electronic address:
To investigate insulin resistance and pancreatic β-cell function in overweight or obese people under the same glucose tolerance conditions. The subjects were categorized based on the results of the oral glucose tolerance test (OGTT) and the BMI classification criteria. Basal and postprandial glucose concentrations, insulin concentrations, pancreatic β-cell function (HOMA-β), the insulin resistance index (HOMA-IR), and the insulin early secretion index (ΔI30/ΔG30) were compared between the different weight groups.
View Article and Find Full Text PDFReduced graphene oxide prepared by cold plasma green treatment in liquid phase for fluorescence biosensing of tropomyosin in shrimp.
Food Chem
December 2024
School of Food Science and Engineering, South China University of Technology, Guangzhou 510641, China; Academy of Contemporary Food Engineering, South China University of Technology, Guangzhou Higher Education Mega Centre, Guangzhou 510006, China; Engineering and Technological Research Centre of Guangdong Province on Intelligent Sensing and Process Control of Cold Chain Foods, & Guangdong Province Engineering Laboratory for Intelligent Cold Chain Logistics Equipment for Agricultural Products, Guangzhou Higher Education Mega Centre, Guangzhou 510006, China; Food Refrigeration and Computerized Food Technology (FRCFT), Agriculture and Food Science Centre, University College Dublin, National University of Ireland, Belfield Dublin 4, Ireland. Electronic address:
Graphene oxide (GO), renowned for its two-dimensional structure and exceptional fluorescence quenching capabilities, is a preferred choice for the construction of fluorescence biosensors. As the sensitivity demands for these sensors escalate, enhancing the fluorescence quenching performance of GO and reducing background fluorescence become paramount to optimize the sensor sensitivity. In this study, the use of cold plasma (CP) treatment with glucose solution as a reducing agent to refine GO into reduced graphene oxide (r-GO) with optimal fluorescence quenching abilities was explored.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!