Standardization process of continuous glucose monitoring: Traceability and performance

Journal of Healthcare Engineering

Gao

2022

Continuous noninvasive blood glucose monitoring and estimation management by using photoplethysmography (PPG) technology always have a series of problems, such as substantial time variability, inaccuracy, and complex nonlinearity. This paper proposes a blood glucose (BG) prediction model for more precise prediction based on BG series decomposition by complete aggregation empirical mode decomposition based on adaptive white noise (CEEMDAN) and the gated recurrent unit (GRU) that is optimized by improved bacterial foraging optimization (IBFO). Hierarchical clustering technology recombines the decomposed BG series according to their sample entropy and the correlations with the original BG trends. Dynamic BG trends are regressed separately for each recombined BG series by the GRU model to realize the more precise estimations, which are optimized by IBFO for its structure and superparameters. Through experiments, the optimized and basic LSTM, RNN, and support vector regression (SVR) are compared to evaluate the performance of the proposed model. The experimental results indicate that the root mean square error (RMSE) and mean absolute percentage error (MAPE) of the 15-min IBFO-GRU prediction is improved on average by about 13.1% and 18.4%, respectively, compared with those of the RNN and LSTM optimized by IBFO. Meanwhile, the proposed model improved the Clarke error grid results by about 2.6% and 5.0% compared with those of the IBFO-LSTM and IBFO-RNN in 30-min prediction and by 4.1% and 6.6% in 15-min ahead forecast, respectively. The evaluation outcomes of our proposed CEEMDAN-IBFO-GRU model have high accuracy and adaptability and can effectively provide early intervention control of the occurrence of hyperglycemic complications.

Section: Introductionmentioning

confidence: 99%

Optimization and Evaluation of an Intelligent Short-Term Blood Glucose Prediction Model Based on Noninvasive Monitoring and Deep Learning Techniques

Journal of Healthcare Engineering

Gao

2022

“…From the clinical chemistry perspective, a better understanding is needed about how to assure the accuracy of bloodless measurements by establishing traceability of their readings to a reference standard. 375 This challenge is currently unresolved because of the difficulty of obtaining comparator ISF samples for testing against blood. Also, the controversy about whether capillary blood or venous blood is the best comparator matrix for ISF measurements must be resolved.…”

Section: Discussionmentioning

confidence: 99%

“…Also, the controversy about whether capillary blood or venous blood is the best comparator matrix for ISF measurements must be resolved. 375 Overall, a convenient and reliable method for collecting representative samples of ISF would have a large positive impact on the advancements of these and future NIO-GM, NIFS-GM, and MI-GM products.…”

Section: Discussionmentioning

confidence: 99%

Products for Monitoring Glucose Levels in the Human Body With Noninvasive Optical, Noninvasive Fluid Sampling, or Minimally Invasive Technologies

Shang

Thomas³

et al. 2021

J Diabetes Sci Technol

Self Cite

Background: Conventional home blood glucose measurements require a sample of blood that is obtained by puncturing the skin at the fingertip. To avoid the pain associated with this procedure, there is high demand for medical products that allow glucose monitoring without blood sampling. In this review article, all such products are presented. Methods: In order to identify such products, four different sources were used: (1) PubMed, (2) Google Patents, (3) Diabetes Technology Meeting Startup Showcase participants, and (4) experts in the field of glucose monitoring. The information obtained were filtered by using two inclusion criteria: (1) regulatory clearance, and/or (2) significant coverage in Google News starting in the year 2016, unless the article indicated that the product had been discontinued. The identified bloodless monitoring products were classified into three categories: (1) noninvasive optical, (2) noninvasive fluid sampling, and (3) minimally invasive devices. Results: In total, 28 noninvasive optical, 6 noninvasive fluid sampling, and 31 minimally invasive glucose monitoring products were identified. Subsequently, these products were characterized according to their regulatory, technological, and consumer features. Products with regulatory clearance are described in greater detail according to their advantages and disadvantages, and with design images. Conclusions: Based on favorable technological features, consumer features, and other advantages, several bloodless products are commercially available and promise to enhance diabetes management. Paths for future products are discussed with an emphasis on understanding existing barriers related to both technical and non-technical issues.

“…Thus, the IFCC working group focuses on improving standardization of CGM performance measures. 141 Although, the MARD is currently the most common metric used to assess the performance of CGM system, several limitations of using MARD exist affecting traceability. 142,143 Notably, there are systematic differences not captured by MARD for example, based on blood sample comparison (venous from factory calibrated vs. capillary).…”

Section: Consensusmentioning

confidence: 99%

Diabetes Technology Meeting 2020

Shang

Bequette

et al. 2021

J Diabetes Sci Technol

Self Cite

Diabetes Technology Society hosted its annual Diabetes Technology Meeting on November 12 to November 14, 2020. This meeting brought together speakers to cover various perspectives about the field of diabetes technology. The meeting topics included artificial intelligence, digital health, telemedicine, glucose monitoring, regulatory trends, metrics for expressing glycemia, pharmaceuticals, automated insulin delivery systems, novel insulins, metrics for diabetes monitoring, and discriminatory aspects of diabetes technology. A live demonstration was presented.