Non-invasive Detection Of Diabetes Research Articles

Pilot study for non-invasive diabetes detection through classification of photoplethysmography signals using convolutional neural networks

Diabetes is a chronic disorder affecting vascular health, often altering pulse wave characteristics. Traditional pulse wave analysis (PWA) methods face challenges such as variability and complexity of signals. This study aims to overcome these limitations by leveraging deep learning models for more accurate and efficient classification. The methodology used in this study involves four key steps: data collection, data preprocessing, Convolutional Neural Network (CNN) model development, and model evaluation. Primary data were collected using a multipara patient monitor, including finger photoplethysmography (PPG) signals, blood pressure, mean arterial pressure, oxygen saturation, and pulse rate. Single pulse wave cycles from 60 healthy individuals and 60 patients with type 2 diabetes underwent preprocessing. The CNN model was trained using 50 PPG images from each group and achieved a training accuracy of 92%. The prediction capability of the model was evaluated using 20 unseen images, comprising 10 healthy and 10 diabetes PPG images. It attained a 90% overall test accuracy in distinguishing between PPG images of individuals with diabetes and those who are healthy. These findings suggest that CNN-based analysis of PPG signals provides a precise, non-invasive tool for diabetes screening. To further enhance accuracy, future studies should focus on increasing the dataset size and performing hyperparameter tuning to optimize the CNN model.

Analysis of Non-Invasive Diabetes Detection Technology

Analysis of Non-Invasive Diabetes Detection Technology

Photonic Nanochains for Continuous Glucose Monitoring in Physiological Environment.

Diabetes is a common disease that seriously endangers human health. Continuous glucose monitoring (CGM) is important for the prevention and treatment of diabetes. Glucose-sensing photonic nanochains (PNCs) have the advantages of naked-eye colorimetric readouts, short response time and noninvasive detection of diabetes, showing immense potential in CGM systems. However, the developed PNCs cannot disperse in physiological environment at the pH of 7.4 because of their poor hydrophilicity. In this study, we report a new kind of PNCs that can continuously and reversibly detect the concentration of glucose (Cg) in physiological environment at the pH of 7.4. Polyacrylic acid (PAA) added to the preparation of PNCs forms hydrogen bonds with polyvinylpyrrolidone (PVP) in Fe3O4@PVP colloidal nanoparticles and the hydrophilic monomer N-2-hydroxyethyl acrylamide (HEAAm), which increases the content of PHEAAm in the polymer shell of prepared PNCs. Moreover, 4-(2-acrylamidoethylcarbamoyl)-3-fluorophenylboronic acid (AFPBA), with a relatively low pKa value, is used as the glucose-sensing monomer to further improve the hydrophilicity and glucose-sensing performances of PNCs. The obtained Fe3O4@(PVP-PAA)@poly(AFPBA-co-HEAAm) PNCs disperse in artificial serum and change color from yellow-green to red when Cg increases from 3.9 mM to 11.4 mM, showing application potential for straightforward CGM.

Survey on electrocardiography signal analysis and diabetes mellitus: unraveling the complexities and complications

Electrocardiography (ECG) is crucial in the medical field to assess cardiovascular diseases. ECG signal generates information, i.e., QRS complexes that imply the cardiac health of the human body. It is depicted in the form of a graph with voltage versus time interval. A distorted, inverted, lagged, small waveform implies an abnormality in a cardiac system. This study highlights the generation of an ECG signal, QRS complexes undertoned towards different diseases, event detection, and signal processing methods. It has become crucial to highlight the possibilities and advances that can be derived from an ECG signal. Throughout this study, an instance of diabetes mellitus (DM) is considered for creating concrete awareness and understanding of an ECG signal in DM. This study focuses on finding the correlation between ECG and DM. Detection of DM from ECG signal is also studied. The findings of this survey paper conclude that the correlation between DM individuals with cardiovascular complications has autonomic neuropathy, which may lead to myocardial infarction. It is also found that the QRS complex and its abnormalities are not specific to complications in DM. However, non-invasive detection of diabetes through ECG signals demonstrates future research potential.

Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose.

Volatile organic compounds (VOCs) in exhaled human breath serve as pivotal biomarkers for disease identification and medical diagnostics. In the context of diabetes mellitus, the noninvasive detection of acetone, a primary biomarker using electronic noses (e-noses), has gained significant attention. However, employing e-noses requires pre-trained algorithms for precise diabetes detection, often requiring a computer with a programming environment to classify newly acquired data. This study focuses on the development of an embedded system integrating Tiny Machine Learning (TinyML) and an e-nose equipped with Metal Oxide Semiconductor (MOS) sensors for real-time diabetes detection. The study encompassed 44 individuals, comprising 22 healthy individuals and 22 diagnosed with various types of diabetes mellitus. Test results highlight the XGBoost Machine Learning algorithm's achievement of 95% detection accuracy. Additionally, the integration of deep learning algorithms, particularly deep neural networks (DNNs) and one-dimensional convolutional neural network (1D-CNN), yielded a detection efficacy of 94.44%. These outcomes underscore the potency of combining e-noses with TinyML in embedded systems, offering a noninvasive approach for diabetes mellitus detection.

NanoLC-timsTOF-Assisted Analysis of Glycated Albumin in Diabetes-Affected Plasma and Tears.

Glycation is a spontaneous and nonenzymatic glycosylation. Glycated albumin (GA), which serves as an important biomarker in plasma in the diagnosis and characterization of diabetes, can be passively filtered from the plasma to tears. Tears are important targets for research in clinical diagnostics due to the ability to collect this biofluid noninvasively and repeatably. Therefore, the analysis of GA in tear film provides information for monitoring diabetes progression independent of blood pathologies. Due to the limited volume (1-5 μL) of natural tear film, we developed a small volume assay using a nano liquid chromatography-trapped ion mobility spectrometry-time-of-flight MS (nanoLC-timsTOF) platform for the analysis of glycated albumin in human plasma and tear films affected by diabetes. The peptides containing lysine 525, which is the main glycation site in GA, were relatively quantified and represented as the GA level. The results of the measurements showed that GA levels were significantly higher in diabetes-affected plasma and tears compared to controls with a p-value < 0.01. A strong correlation of glycated albumin levels was observed for the plasma and tear film in diabetes samples (Pearson coefficient 0.92 with a p-value 0.0012). Moreover, the number of GA glycation sites was significantly higher in diabetes-affected plasma and tear comparatively to controls. Among all the glycation sites in plasma albumin, the GA level quantified by lysine 136/137 had a strong correlation with more commonly used lysine 525, suggesting that lysine 136 /137 is an alternative diabetes biomarker in plasma. Overall, our findings demonstrate GA in tears as a biomarker for monitoring diabetes progression, highlighting new possibilities for quick and noninvasive diabetes detection and monitoring.

Binary fire hawks optimizer with deep learning driven non-invasive diabetes detection and classification.

Non-invasive diabetes detection refers to the utilization and development of technologies and methods that can monitor and diagnose diabetes without requiring invasive procedures, namely invasive glucose monitoring or blood sampling. The objective is to provide a more convenient and less burdensome approach to screening and management of diabetes. It is noteworthy that while non-invasive method offers promising avenues for diabetes detection, they frequently require validation through clinical studies and might have limitation in terms of reliability and accuracy than classical invasive approaches. In recent times, deep learning (DL) and feature selection (FS) are used to monitor and diagnose diabetes accurately without requiring invasive procedures. This technique combines the FS method with the DL algorithm for making accurate predictions and extracting relevant features from non-invasive data. This article introduces a new Binary Fire Hawks Optimizer with Deep Learning-Driven Non-Invasive Diabetes Detection and Classification (BFHODL-NIDDC) technique. The major intention of the BFHODL-NIDDC technique focuses on the involvement of non-invasive procedures for the detection of diabetes. In the BFHODL-NIDDC technique, data preprocessing is initially performed to preprocess the input data. Next, the BFHO algorithm chooses an optimal subset of features and improves the classifier results. For the identification of diabetes, multichannel convolutional bidirectional long short-term memory (MC-BLSTM) model is used. At last, the beetle antenna search (BAS) algorithm is used for the hyperparameter selection of the MC-BLSTM method which in turn enhances the detection performance of the MC-BLSTM model. A series of simulations were conducted on the diabetes dataset to assess the diabetes detection performance of the BFHODL-NIDDC technique. The experimental outcomes illustrated better performance of the BFHODL-NIDDC method over other recent approaches in terms of different metrics (Tab. 4, Fig. 9, Ref. 23). Keywords: diabetes, non-invasive detection, binary fire hawks optimizer, deep learning, hyperparameter tuning.

A spectroscopy based prototype for the noninvasive detection of diabetes from human saliva using nanohybrids acting as nanozyme

The recent prediction of diabetes to be a global pandemic invites a detection strategy preferably non-invasive, and bloodless to manage the disease and the associated complications. Here, we have synthesized chitosan polymer functionalized, organic–inorganic bio-compatible nano-hybrids of Mn3O4 nanoparticles, and characterized it by utilizing several optical methodologies for the structural characterization which shows the Michaelis Menten (MM) kinetics for glucose and alpha-amylase protein (well-known diabetes biomarkers). We have also studied the potentiality for the detection of alpha-amylase in human salivary secretion which is reported to be strongly correlated with uncontrolled hyperglycemia. Finally, we have developed a prototype for the measurement of glucose (LOD of 0.38 mg/dL, LOQ of 1.15 mg/dL) and HbA1c (LOD of 0.15% and LOQ of 0.45%) utilizing the basic knowledge in the study for the detection of uncontrolled hyperglycemia at the point-of-care. With the limited number of clinical trials, we have explored the potential of our work in combating the diabetic pandemic across the globe in near future.

Monitoring saliva compositions for non-invasive detection of diabetes using a colorimetric-based multiple sensor

The increasing population of diabetic patients, especially in developing countries, has posed a serious risk to the health sector, so that the lack of timely diagnosis and treatment process of diabetes can lead to threatening complications for the human lifestyle. Here, a multiple sensor was fabricated on a paper substrate for rapid detection and controlling the progress of the diabetes disease. The proposed sensor utilized the sensing ability of porphyrazines, pH-sensitive dyes and silver nanoparticles in order to detect the differences in saliva composition of diabetic and non-diabetic patients. A unique color map (sensor response) was obtained for each studied group, which can be monitored by a scanner. Moreover, a good correlation was observed between the colorimetric response resulting from the analysis of salivary composition and the fasting blood glucose (FBG) value measured by standard laboratory instruments. It was also possible to classify participants into two groups, including patients caused by diabetes and those were non-diabetic persons with a total accuracy of 88.9%. Statistical evaluations show that the multiple sensor can be employed as an effective and non-invasive device for continuous monitoring of diabetes, substantially in the elderly.

Comment on "Feasibility of Raman spectroscopy as a potential in vivo tool to screen for pre-diabetes and diabetes".

This paper comments recent findings about Raman spectroscopy application for in vivo noninvasive diabetes detection, published in the Journal of Biophotonics by E. Guevara et al. (J. Biophotonics 2022, 15, e202200055). The proposed results may be not entirely correct due to possible overestimation of classification models and absence of additional information regarding age of tested volunteers.

ZnO/ZnSe heterojunction nanocomposites with oxygen vacancies for acetone sensing

Oxygen vacancies ZnO/ZnSe heterojunction was designed by incorporating ZnSe into ZIF-8 derived ZnO followed by an annealing process. The as-prepared material possessed excellent acetone sensing properties even at low concentrations and is expected to be used in the non-invasive detection of diabetes in patients. Using a facile hydrothermal method, pristine ZnO and ZnSe were prepared, and then they were mixed and thermally annealed to form the composite. Subsequently, the materials were characterized by using various techniques such as XRD, XPS, EPR, etc. According to the sensing study, the highest response of the material in 1 ppm acetone was as high as 5.8, which was 2.3 times that of pure ZnO. In addition, the as-prepared composite was less sensitive to interfering gases, which indicates the feasibility of developing highly sensitive acetone sensors based on this material. Thus, the material prepared in this work may be applied to the non-invasive detection of diabetes in patients, and hence it is worthy to conduct further in-depth research.

Non-invasive Diabetes Detection using Metabolic Heat Conformation Technology and Heart Rate

Screening and early detection of type 2 diabetes are important to prevent diabetic complications. Commonly, type 2 diabetes is detected by blood glucose measurement. However, the compliance for existing invasive devices is insufficient because these devices can potentially cause pain, infection, and tissue damage due to needle use. Thus, we have been developing a non-invasive diabetes detection method that uses metabolic heat conformation (MHC) technology. Our previous method using only MHC technology could not detect diabetes accurately, therefore, a novel non-invasive diabetes detection method using additional bio-signal needed to be developed to improve accuracy of early diabetes detection. Heart rate is considered as an additional bio-signal which can be measured by non-invasive devices. The previous studies report that there is a relation between heart rate and diabetes. The objective of this study is to propose a novel non-invasive diabetes detection method using both MHC technology and heart rate. The proposed method detects diabetes by machine learning technique using skin surface temperature data based on MHC technology and heart rate. In the experiment, the proposed method and our previous method were compared by using 95 samples bio-signal dataset obtained from 5 participants including 2 diabetes patients. The results showed that the proposed method could detect diabetes with accuracy higher than 90 %, which is significant improvement in comparison to our previous method, which detected diabetes with accuracy less than 80 %. The results support the possibility that the proposed method using both MHC technology and heart rate can be applied for non-invasive early diabetes detection.

Glucose-Sensing Photonic Nanochain Probes with Color Change in Seconds.

Glucose‐sensing photonic crystals are promising for the significant advance of continuous glucose monitoring systems due to the naked‐eye colorimetric readouts and noninvasive detection of diabetes, but the long response time hampers their practical applications. Here, for the first time probes of photonic nanochains (PNCs) are demonstrated that are capable of continuously and reversibly sensing glucose concentration ([glucose]) variation within seconds by color change without power consumption, much faster by 2–3 orders of magnitude than previous ones. They are comprised of 1D equidistant arrays of magnetic nanoparticles enveloped by tens‐of‐nanometer‐thick phenylboronic acid‐functionalized hydrogels, and fabricated by developing selective concentration polymerization of monomers in binary microheterogeneous solvents of dimethyl sulfoxide (DMSO) and H2O. In this process, both 3‐acrylamido phenylboronic acid (AAPBA) and N‐2‐hydroxyethyl acrylamide (HEAAm) are preferentially dissolved in the small volume of free DMSO concentrated in the vicinity of poly vinylpyrrolidone coated Fe3O4 colloidal nanoparticles (Fe3O4@PVP), yielding Fe3O4@PVP@poly(AAPBA‐co‐HEAAm) PNCs after UV irradiation under magnetic field. The PNCs in phosphate buffered solution have a wavelength‐shift range up to 130 nm when [glucose] changes from 0 to 20 × 10−3 m. The results can facilitate real‐time glucose monitoring and provide an alternative to produce functional organic–inorganic nanostructures.

Design of intelligent diabetes mellitus detection system using hybrid feature selection based XGBoost classifier

In this work, a non-invasive diabetes mellitus detection system is proposed based on the wristband photoplethysmography (PPG) signal and basic physiological parameters (PhyP) to enable easy detection of diabetes mellitus (DM). A dataset of 217 participants with diabetes, prediabetes and normal conditions is used to develop the system. The Mel frequency cepstral coefficients (MFCC) extracted from 5s PPG signal segments and the PhyP are used as input for the machine learning algorithms. The K-nearest neighbors, support vector machine, random forest and extreme gradient boost (XGBoost) classifiers are used for classification. In addition, a hybrid feature selection method (Hybrid FS) is proposed to reduce the size of the input data. The Hybrid FS-based XGBoost system achieves a high accuracy of 99.93 % for non-invasive diabetes detection with fewer features and less computational effort. The analysis suggests that the PPG signal from a wearable sensor is a good alternative for simple non-invasive blood glucose measurements in routine applications.

Room temperature acetone sensing performance of Pt/Sb2O3 impregnated Fe2O3 thin film: Noninvasive diabetes detection

In the present report, an enhanced sub-ppm level acetone sensing performance of a novel Pt and Sb2O3 impregnated nanocrystalline Fe2O3 thin film operating at room temperature has been explored. Starting from organic precursor sols, thin films of thickness ~ 6 µm were drop-casted on planar alumina substrates pre-attached with the platinum electrodes and cured at ~ 350°C. The characterizations of the materials have been carried out using X-ray Diffraction, FTIR, Raman Spectroscopy, micro structural study through FESEM and TEM as well as XPS analyses. The sensing characteristics including sensing response, lowest detection limit, recovery time etc. of these chemiresistive thin films were studied on exposing them to various concentrations (0.25 to 1 ppm) of acetone at room temperature. The sensing response of ~2.4 with ~ 95 s recovery time was observed on exposure to 1 ppm acetone for 10 s. Even at 0.25 ppm acetone, the response observed ~ 1.4. Selectivity study on different alcohols and other interfering gases of breath has also been tested. Additionally, a real time breath acetone measurement was carried out and acetone sensing mechanism has been elucidated.

Recent Advancements and Future Prospects on E-Nose Sensors Technology and Machine Learning Approaches for Non-Invasive Diabetes Diagnosis: A Review.

Diabetes mellitus, commonly measured through an invasive process which although is accurate, has manifold drawbacks especially when multiple reading are required at regular intervals. Accordingly, there is a need to develop a dependable non-invasive diabetes detection technique. Recent studies have observed that other human serums such as tears, saliva, urine and breath indicate the presence of glucose in them. These parameters open quite a few ways for non-invasive blood glucose level prediction. The analysis of a persons breath poses as a good non-invasive technique to monitor the glucose levels. It is seen that in breath, there are many bio-markers and monitoring the levels of these bio-markers indicate the possibility of various chronic diseases. Among these bio-markers, acetone a volatile organic compound found in breath has shown a good correlation to the glucose levels present in blood. Therefore, by evaluating the acetone levels in breath samples it is possible to monitor diabetes non-invasively. This paper reviews the various approaches and sensory techniques used to monitor diabetes though human breath samples.

Metal-organic frameworks derived ZnO@MoS2nanosheets core/shell heterojunctions for ppb-level acetone detection: Ultra-fast response and recovery

It is imperative to explore an accurate ppb-level acetone sensor for noninvasive detection of diabetes. In this work, two dimensional p-type MoS2 nanosheets are introduced on the surface of p-type ZnO derived from metal-organic frameworks (MOFs) to produce ZnO@MoS2 core/shell heterojunctions as a novel acetone sensor, showing a great enhancement of acetone response, about two orders of magnitude than that of pure ZnO derived from MOFs. For example, the ZnO@MoS2 exhibits about 80 times enhancement in response to 100 ppb acetone than that of pure ZnO. More importantly, this ZnO@MoS2 heterojunctions sensor exhibits an ultra-fast response/recovery to ultra-low concentration acetone (60 s/40 s @ 5 ppb), which is the best acetone sensing performance for the metal oxide-based materials reported to date. Moreover, the acetone sensing performances are negligibly affected by humidity and other gas, which is suitable for exhaled acetone detection. Finally, it is elucidated that the sharp increase of negative heterojunction interface resistance, ultra-fast gas diffusion rates in MoS2 nanosheets and strong interaction energy are key factors for the excellent acetone sensing properties of ZnO@MoS2. This work opens up a novel and efficient way for ultra-low concentration gas detection.

Non-invasive Diabetes Detection using Facial Texture Features Captured in a Less Restrictive Environment

The prevalence of Diabetes Mellitus (DM) worldwide has risen dramatically with 1 of 3 deaths happening in Western Pacific region according to the 2017 report of International Diabetes Federation. The Philippines ranks 5th in WP with the most cases of diabetes. Local experts and IDF estimate that half of the people with diabetes are unaware they have it and will likely remain undiagnosed. Conventional ways to detect if a person has diabetes are often invasive and painful such as puncturing fingers for blood sample. Though non-invasive DM detection techniques have gained consideration in more analysts, presently they have restrictive set-up for image capture. This paper explores the performance of using mobile device as a convenient tool for image capture of DM and healthy dataset for non-invasive detection using facial block texture features and Gabor filter. Filipino participants that undergo regular check-ups for diabetes monitoring were chosen within the age inclusion criteria of 20 to 79 years old in which surveys for Philippines assessed the occurrence of diabetes to be most prevalent according to IDF and World Health reports. For each subject, a mobile device 12mp and 7mp cameras were used to take the photo placed 30 cm in front of the face under normal lighting condition to ensure full coverage and avoid unnecessary background. A ratio of 70:30 training to testing set was maintained and extracted facial blocks were classified using SVM and KNN. A total of 100 images from each camera were captured, preprocessed, filtered and iterated to compare performance of data. 90% accuracy, 93% sensitivity and 93% specificity were achieved for 12mp with SVM. For the 7mp camera, an accuracy of 80% using SVM and 93% sensitivity using KNN were achieved after increasing the predictors obtained for classification.

Enhanced acetone sensing performance based on hollow coral-like SnO2–ZnO composite nanofibers

The acetone sensors are designed based on hollow coral-like SnO2–ZnO nanofibers (NFs) composite structure through a simple one-step electrospinning method in this paper. Compared with pure SnO2, SnO2–ZnO sensor has greatly enhanced acetone sensing performance including excellent sensitivity, rapid response which are due to its larger specific surface area, more oxygen vacancies and n–n composite structures. The response of SnO2–ZnO NFs sensor (110.95) is 20 times higher than that of the SnO2 sensor (5.52) and achieves a rapid response/recovery process (within 9/5 s) at 150 °C in 100 ppm acetone concentration which is expected to be applied in the non-invasive detection of diabetes. Moreover, the mechanism of the enhanced gas sensing based on hollow coral-like SnO2–ZnO NFs is analyzed in depth from energy band of n–n metal oxide semiconductors composite structures.

Diabetes detection using deep learning algorithms

Abstract Diabetes is a metabolic disease affecting a multitude of people worldwide. Its incidence rates are increasing alarmingly every year. If untreated, diabetes-related complications in many vital organs of the body may turn fatal. Early detection of diabetes is very important for timely treatment which can stop the disease progressing to such complications. RR-interval signals known as heart rate variability (HRV) signals (derived from electrocardiogram (ECG) signals) can be effectively used for the non-invasive detection of diabetes. This research paper presents a methodology for classification of diabetic and normal HRV signals using deep learning architectures. We employ long short-term memory (LSTM), convolutional neural network (CNN) and its combinations for extracting complex temporal dynamic features of the input HRV data. These features are passed into support vector machine (SVM) for classification. We have obtained the performance improvement of 0.03% and 0.06% in CNN and CNN-LSTM architecture respectively compared to our earlier work without using SVM. The classification system proposed can help the clinicians to diagnose diabetes using ECG signals with a very high accuracy of 95.7%.