Noninvasive Monitoring of Blood Glucose Using Color-Coded Photoplethysmographic Images of the Illuminated Fingertip Within the Visible and Near-Infrared Range: Opportunities and Questions

In Vitro Glucose Measurement from NIR and MIR Spectroscopy: Comprehensive Benchmark of Machine Learning and Filtering Chemometrics

The quantitative analysis of glucose using spectroscopy is a topic of great significance and interest in science and industry. One conundrum in this area is deploying appropriate preprocessing and regression tools. To contribute to addressing this challenge, in this study, we conducted a comprehensive and novel comparative analysis of various machine learning and preprocessing filtering techniques applied to near-infrared, mid-infrared, and a combination of near-infrared and mid-infrared spectroscopy for glucose assay. Our objective was to evaluate the effectiveness of these techniques in accurately predicting glucose levels and to determine which approach was most optimal. Our investigation involved the acquisition of spectral data from samples of glucose solutions using the three aforementioned spectroscopy techniques. The data was subjected to several preprocessing filtering methods, including convolutional moving average, Savitzky-Golay, multiplicative scatter correction, and normalisation. We then applied representative machine learning algorithms from three categories: linear modelling, traditional nonlinear modelling, and artificial neural networks. The evaluation results revealed that linear models exhibited higher predictive accuracy than nonlinear models, whereas artificial neural network models demonstrated comparable performance. Additionally, the comparative analysis of various filtering methods demonstrated that the convolutional moving average and Savitzky-Golay filters yielded the most precise outcomes overall. In conclusion, our study provides valuable insights into the efficacy of different machine learning techniques for glucose measurement and highlights the importance of applying appropriate filtering methods in enhancing predictive accuracy. These findings have important implications for the development of new and improved glucose quantification technologies.

Guidelines and Recommendations for Laboratory Analysis in the Diagnosis and Management of Diabetes Mellitus

BACKGROUND

Numerous laboratory tests are used in the diagnosis and management of diabetes mellitus. The quality of the scientific evidence supporting the use of these assays varies substantially.

APPROACH

An expert committee compiled evidence-based recommendations for laboratory analysis in screening, diagnosis, or monitoring of diabetes. The overall quality of the evidence and the strength of the recommendations were evaluated. The draft consensus recommendations were evaluated by invited reviewers and presented for public comment. Suggestions were incorporated as deemed appropriate by the authors (see Acknowledgments). The guidelines were reviewed by the Evidence Based Laboratory Medicine Committee and the Board of Directors of the American Association for Clinical Chemistry and by the Professional Practice Committee of the American Diabetes Association.

CONTENT

Diabetes can be diagnosed by demonstrating increased concentrations of glucose in venous plasma or increased hemoglobin A1c (HbA1c) in the blood. Glycemic control is monitored by the people with diabetes measuring their own blood glucose with meters and/or with continuous interstitial glucose monitoring (CGM) devices and also by laboratory analysis of HbA1c. The potential roles of noninvasive glucose monitoring, genetic testing, and measurement of ketones, autoantibodies, urine albumin, insulin, proinsulin, and C-peptide are addressed.

SUMMARY

The guidelines provide specific recommendations based on published data or derived from expert consensus. Several analytes are found to have minimal clinical value at the present time, and measurement of them is not recommended.

Guidelines and Recommendations for Laboratory Analysis in the Diagnosis and Management of Diabetes Mellitus

BACKGROUND

Numerous laboratory tests are used in the diagnosis and management of diabetes mellitus. The quality of the scientific evidence supporting the use of these assays varies substantially.

APPROACH

An expert committee compiled evidence-based recommendations for laboratory analysis in screening, diagnosis, or monitoring of diabetes. The overall quality of the evidence and the strength of the recommendations were evaluated. The draft consensus recommendations were evaluated by invited reviewers and presented for public comment. Suggestions were incorporated as deemed appropriate by the authors (see Acknowledgments). The guidelines were reviewed by the Evidence Based Laboratory Medicine Committee and the Board of Directors of the American Association of Clinical Chemistry and by the Professional Practice Committee of the American Diabetes Association.

CONTENT

Diabetes can be diagnosed by demonstrating increased concentrations of glucose in venous plasma or increased hemoglobin A1c (Hb A1c) in the blood. Glycemic control is monitored by the people with diabetes measuring their own blood glucose with meters and/or with continuous interstitial glucose monitoring (CGM) devices and also by laboratory analysis of Hb A1c. The potential roles of noninvasive glucose monitoring, genetic testing, and measurement of ketones, autoantibodies, urine albumin, insulin, proinsulin, and C-peptide are addressed.

SUMMARY

The guidelines provide specific recommendations based on published data or derived from expert consensus. Several analytes are found to have minimal clinical value at the present time, and measurement of them is not recommended.

Non-Invasive Classification of Blood Glucose Level Based on Photoplethysmography Using Time–Frequency Analysis

Diabetes monitoring systems are crucial for avoiding potentially significant medical expenses. At this time, the only commercially viable monitoring methods that exist are invasive ones. Since patients are uncomfortable while blood samples are being taken, these techniques have significant disadvantages. The drawbacks of invasive treatments might be overcome by a painless, inexpensive, non-invasive approach to blood glucose level (BGL) monitoring. Photoplethysmography (PPG) signals obtained from sensor leads placed on specific organ tissues are collected using photodiodes and nearby infrared LEDs. Cardiovascular disease can be detected via photoplethysmography. These characteristics can be used to directly affect BGL monitoring in diabetic patients if PPG signals are used. The Guilin People’s Hospital’s open database was used to produce the data collection. The dataset was gathered from 219 adult respondents spanning an age range from 21 to 86 of which 48 percent were male. There were 2100 sampling points total for each PPG data segment. The methodology of feature extraction from data may assist in increasing the effectiveness of classifier training and testing. PPG data information is modified in the frequency domain by the instantaneous frequency (IF) and spectral entropy (SE) moments using the time–frequency (TF) analysis. Three different forms of raw data were used as inputs, and we investigated the original PPG signal, the PPG signal with instantaneous frequency, and the PPG signal with spectral entropy. According to the results of the model testing, the PPG signal with spectral entropy generated the best outcomes. Compared to decision trees, subspace k-nearest neighbor, and k-nearest neighbor, our suggested approach with the super vector machine obtains a greater level of accuracy. The super vector machine, with 91.3% accuracy and a training duration of 9 s, was the best classifier.

Is Raman the best strategy towards the development of non-invasive continuous glucose monitoring devices for diabetes management?

Diabetes has no well-established cure; thus, its management is critical for avoiding severe health complications involving multiple organs. This requires frequent glycaemia monitoring, and the gold standards for this are fingerstick tests. During the last decades, several blood-withdrawal-free platforms have been being studied to replace this test and to improve significantly the quality of life of people with diabetes (PWD). Devices estimating glycaemia level targeting blood or biofluids such as tears, saliva, breath and sweat, are gaining attention; however, most are not reliable, user-friendly and/or cheap. Given the complexity of the topic and the rise of diabetes, a careful analysis is essential to track scientific and industrial progresses in developing diabetes management systems. Here, we summarize the emerging blood glucose level (BGL) measurement methods and report some examples of devices which have been under development in the last decades, discussing the reasons for them not reaching the market or not being really non-invasive and continuous. After discussing more in depth the history of Raman spectroscopy-based researches and devices for BGL measurements, we will examine if this technique could have the potential for the development of a user-friendly, miniaturized, non-invasive and continuous blood glucose-monitoring device, which can operate reliably, without inter-patient variability, over sustained periods.

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

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.

Self-care activities among patients with type 2 diabetes mellitus: A cross-sectional study

AIMS

This study investigated self-care activities and identified their related factors in Chinese patients with type 2 diabetes mellitus.

METHODS

A cross-sectional study was conducted in Guangzhou, China, between September 2016 and February 2017, involving 202 Chinese patients with type 2 diabetes mellitus. Measures included the Summary of Diabetes Self-Care Activities Questionnaire and Revised Illness Perception Questionnaire.

RESULTS

Self-care activities in Chinese patients with type 2 diabetes mellitus were suboptimal overall. Foot care and blood sugar testing were the self-care activities that were performed the least. One fifth of patients smoked. Some subscales of illness perceptions, receiving health education on diabetes, employment status, education level, body mass index, age and time since type 2 diabetes mellitus diagnosis, were related to self-care activities in patients with type 2 diabetes mellitus.

CONCLUSION

Health-care providers and nurses should encourage greater engagement in self-care activities in patients with type 2 diabetes mellitus, especially foot care and blood sugar testing. Illness perceptions may be used as a framework to guide interventions.

Noninvasive Monitoring of Glucose Using Near-Infrared Reflection Spectroscopy of Skin-Constraints and Effective Novel Strategy in Multivariate Calibration

For many years, successful noninvasive blood glucose monitoring assays have been announced, among which near-infrared (NIR) spectroscopy of skin is a promising analytical method. Owing to the tiny absorption bands of the glucose buried among a dominating variable spectral background, multivariate calibration is required to achieve applicability for blood glucose self-monitoring. The most useful spectral range with important analyte fingerprint signatures is the NIR spectral interval containing combination and overtone vibration band regions. A strategy called science-based calibration (SBC) has been developed that relies on a priori information of the glucose signal ("response spectrum") and the spectral noise, i.e., estimates of the variance of a sample population with negligible glucose dynamics. For the SBC method using transcutaneous reflection skin spectra, the response spectrum requires scaling due to the wavelength-dependent photon penetration depth, as obtained by Monte Carlo simulations of photon migration based on estimates of optical tissue constants. Results for tissue glucose concentrations are presented using lip NIR-spectra of a type-1 diabetic subject recorded under modified oral glucose tolerance test (OGTT) conditions. The results from the SBC method are extremely promising, as statistical calibrations show limitations under the conditions of ill-posed equation systems as experienced for tissue measurements. The temporal profile differences between the glucose concentration in blood and skin tissue were discussed in detail but needed to be further evaluated.

Evaluation of Opportunities and Limitations of Mid-Infrared Skin Spectroscopy for Noninvasive Blood Glucose Monitoring

BACKGROUND

A wide range of optical techniques has recently been presented for the development of noninvasive methods for blood glucose sensing based on multivariate skin spectrum analysis, and most recent studies are reviewed in short by us. The vibrational spectral fingerprints of glucose, as especially found in the mid-infrared or Raman spectrum, have been suggested for achieving largest selectivity for the development of noninvasive blood glucose methods.

METHODS

Here, the different aspects on integral skin measurements are presented, which are much dependent on the absorption characteristics of water as the main skin constituent. In particular, different mid-infrared measurement techniques as realized recently are discussed. The limitations of the use of the attenuated total reflection technique in particular are elaborated, and confounding skin or saliva spectral features are illustrated and discussed in the light of recently published works, claiming that the attenuated total reflection technique can be utilized for noninvasive measurements.

RESULTS

It will be shown that the penetration depth of the infrared radiation with wavelengths around 10 µm is the essential parameter, which can be modulated by different measurement techniques as with photothermal or diffuse reflection. However, the law of physics is limiting the option of using the attenuated total reflection technique with waveguides from diamond or similar optical materials.

CONCLUSIONS

There are confounding features from mucosa, stratum corneum, or saliva, which have been misinterpreted for glucose measurements. Results of an earlier study with multivariate evaluation based on glucose fingerprint features are again referred to as a negative experimental proof.

Artificial Intelligence in Health Care: Current Applications and Issues

In recent years, artificial intelligence (AI) technologies have greatly advanced and become a reality in many areas of our daily lives. In the health care field, numerous efforts are being made to implement the AI technology for practical medical treatments. With the rapid developments in machine learning algorithms and improvements in hardware performances, the AI technology is expected to play an important role in effectively analyzing and utilizing extensive amounts of health and medical data. However, the AI technology has various unique characteristics that are different from the existing health care technologies. Subsequently, there are a number of areas that need to be supplemented within the current health care system for the AI to be utilized more effectively and frequently in health care. In addition, the number of medical practitioners and public that accept AI in the health care is still low; moreover, there are various concerns regarding the safety and reliability of AI technology implementations. Therefore, this paper aims to introduce the current research and application status of AI technology in health care and discuss the issues that need to be resolved.

Feasibility study of portable microwave microstrip open-loop resonator for non-invasive blood glucose level sensing: proof of concept

Self-management of blood glucose level is part and parcel of diabetes treatment, which involves invasive, painful, and uncomfortable methods. A proper non-invasive blood glucose monitor (NIBGM) is therefore desirable to deal better with it. Microwave resonators can potentially be used for such a purpose. Following the positive results from an in vitro previous work, a portable device based upon a microwave resonator was developed and assessed in a multicenter proof of concept. Its electrical response was analyzed when an individual's tongue was placed onto it. The study was performed with 352 individuals during their oral glucose tolerance tests, having four measurements per individual. The findings revealed that the accuracy must be improved before the diabetes community can make real use of the device. However, the relationship between the measuring parameter and the individual's blood glucose level is coherent with that from previous works, although with higher data dispersion. This is reflected in correlation coefficients between glycemia and the measuring magnitude consistently negative, although small, for the different datasets analyzed. Further research is proposed, focused on system improvements, individual calibration, and multitechnology approach. The study of the influence of other blood components different to glucose is also advised. Graphical abstract.

Non-invasive monitoring of blood glucose using optical methods for skin spectroscopy-opportunities and recent advances

Diabetes mellitus is a widespread disease with greatly rising patient numbers expected in the future, not only for industrialized countries but also for regions in the developing world. There is a need for efficient therapy, which can be via self-monitoring of blood glucose levels to provide tight glycemic control for reducing the risks of severe health complications. Advancements in diabetes technology can nowadays offer different sensor approaches, even for continuous blood glucose monitoring. Non-invasive blood glucose assays have been promised for many years and various vibrational spectroscopy-based methods of the skin are candidates for achieving this goal. Due to the small spectral signatures of the glucose hidden among a largely variable background, the largest signal-to-noise ratios and multivariate calibration are essential to provide the method applicability for self-monitoring of blood glucose. Besides multiparameter approaches, recently presented devices based on photoplethysmography with wavelengths in the visible and near-infrared range are evaluated for their potential of providing reliable blood glucose concentration predictions. Graphical abstract ᅟ.