Implicit HbA1c Achieving 87% Accuracy within 90 Days in Non-Invasive Fasting Blood Glucose Measurements Using Photoplethysmography.

To reduce the error induced by overfitting or underfitting in predicting non-invasive fasting blood glucose (NIBG) levels using photoplethysmography (PPG) data alone, we previously demonstrated that incorporating HbA1c led to a notable 10% improvement in NIBG prediction accuracy (the ratio in zone A of Clarke's error grid). However, this enhancement came at the cost of requiring an additional HbA1c measurement, thus being unfriendly to users. In this study, the enhanced HbA1c NIBG deep learning model (blood glucose level predicted from PPG and HbA1c) was trained with 1494 measurements, and we replaced the HbA1c measurement (explicit HbA1c) with "implicit HbA1c" which is reversely derived from pretested PPG and finger-pricked blood glucose levels. The implicit HbA1c is then evaluated across intervals up to 90 days since the pretest, achieving an impressive 87% accuracy, while the remaining 13% falls near the CEG zone A boundary. The implicit HbA1c approach exhibits a remarkable 16% improvement over the explicit HbA1c method by covering personal correction items automatically. This improvement not only refines the accuracy of the model but also enhances the practicality of the previously proposed model that relied on an HbA1c input. The nonparametric Wilcoxon paired test conducted on the percentage error of implicit and explicit HbA1c prediction results reveals a substantial difference, with a p-value of 2.75 × 10-7.

Visual Reassessment with Flux-Interval Plot Configuration after Automatic Classification for Accurate Atrial Fibrillation Detection by Photoplethysmography.

Atrial fibrillation (AFib) is a common type of arrhythmia that is often clinically asymptomatic, which increases the risk of stroke significantly but can be prevented with anticoagulation. The photoplethysmogram (PPG) has recently attracted a lot of attention as a surrogate for electrocardiography (ECG) on atrial fibrillation (AFib) detection, with its out-of-hospital usability for rapid screening or long-term monitoring. Previous studies on AFib detection via PPG signals have achieved good results, but were short of intuitive criteria like ECG p-wave absence or not, especially while using interval randomness to detect AFib suffering from conjunction with premature contractions (PAC/PVC). In this study, we newly developed a PPG flux (pulse amplitude) and interval plots-based methodology, simply comprising an irregularity index threshold of 20 and regression error threshold of 0.06 for the precise automatic detection of AFib. The proposed method with automated detection on AFib shows a combined sensitivity, specificity, accuracy, and precision of 1, 0.995, 0.995, and 0.952 across the 460 samples. Furthermore, the flux-interval plot configuration also acts as a very intuitive tool for visual reassessment to confirm the automatic detection of AFib by its distinctive plot pattern compared to other cardiac rhythms. The study demonstrated that exclusive 2 false-positive cases could be corrected after the reassessment. With the methodology's background theory well established, the detection process automated and visualized, and the PPG sensors already extensively used, this technology is very user-friendly and convincing for promoted to in-house AFib diagnostics.

Deduction learning for precise noninvasive measurements of blood glucose with a dozen rounds of data for model training.

Personalized modeling has long been anticipated to approach precise noninvasive blood glucose measurements, but challenged by limited data for training personal model and its unavoidable outlier predictions. To overcome these long-standing problems, we largely enhanced the training efficiency with the limited personal data by an innovative Deduction Learning (DL), instead of the conventional Induction Learning (IL). The domain theory of our deductive method, DL, made use of accumulated comparison of paired inputs leading to corrections to preceded measured blood glucose to construct our deep neural network architecture. DL method involves the use of paired adjacent rounds of finger pulsation Photoplethysmography signal recordings as the input to a convolutional-neural-network (CNN) based deep learning model. Our study reveals that CNN filters of DL model generated extra and non-uniform feature patterns than that of IL models, which suggests DL is superior to IL in terms of learning efficiency under limited training data. Among 30 diabetic patients as our recruited volunteers, DL model achieved 80% of test prediction in zone A of Clarke Error Grid (CEG) for model training with 12 rounds of data, which was 20% improvement over IL method. Furthermore, we developed an automatic screening algorithm to delete low confidence outlier predictions. With only a dozen rounds of training data, DL with automatic screening achieved a correlation coefficient ([Formula: see text]) of 0.81, an accuracy score ([Formula: see text]) of 93.5, a root mean squared error of 13.93 mg/dl, a mean absolute error of 12.07 mg/dl, and 100% predictions in zone A of CEG. The nonparametric Wilcoxon paired test on [Formula: see text] for DL versus IL revealed near significant difference with p-value 0.06. These significant improvements indicate that a very simple and precise noninvasive measurement of blood glucose concentration is achievable.

90% Accuracy for Photoplethysmography-Based Non-Invasive Blood Glucose Prediction by Deep Learning with Cohort Arrangement and Quarterly Measured HbA1c.

Previously published photoplethysmography-(PPG) based non-invasive blood glucose (NIBG) measurements have not yet been validated over 500 subjects. As illustrated in this work, we increased the number subjects recruited to 2538 and found that the prediction accuracy (the ratio in zone A of Clarke's error grid) reduced to undesirable 60.6%. We suspect the low prediction accuracy induced by larger sample size might arise from the physiological diversity of subjects, and one possibility is that the diversity might originate from medication. Therefore, we split the subjects into two cohorts for deep learning: with and without medication (1682 and 856 recruited subjects, respectively). In comparison, the cohort training for subjects without any medication had approximately 30% higher prediction accuracy over the cohort training for those with medication. Furthermore, by adding quarterly (every 3 months) measured glycohemoglobin (HbA1c), we were able to significantly boost the prediction accuracy by approximately 10%. For subjects without medication, the best performing model with quarterly measured HbA1c achieved 94.3% prediction accuracy, RMSE of 12.4 mg/dL, MAE of 8.9 mg/dL, and MAPE of 0.08, which demonstrates a very promising solution for NIBG prediction via deep learning. Regarding subjects with medication, a personalized model could be a viable means of further investigation.

Generation of Augmented Capillary Network Optical Coherence Tomography Image Data of Human Skin for Deep Learning and Capillary Segmentation.

The segmentation of capillaries in human skin in full-field optical coherence tomography (FF-OCT) images plays a vital role in clinical applications. Recent advances in deep learning techniques have demonstrated a state-of-the-art level of accuracy for the task of automatic medical image segmentation. However, a gigantic amount of annotated data is required for the successful training of deep learning models, which demands a great deal of effort and is costly. To overcome this fundamental problem, an automatic simulation algorithm to generate OCT-like skin image data with augmented capillary networks (ACNs) in a three-dimensional volume (which we called the ACN data) is presented. This algorithm simultaneously acquires augmented FF-OCT and corresponding ground truth images of capillary structures, in which potential functions are introduced to conduct the capillary pathways, and the two-dimensional Gaussian function is utilized to mimic the brightness reflected by capillary blood flow seen in real OCT data. To assess the quality of the ACN data, a U-Net deep learning model was trained by the ACN data and then tested on real in vivo FF-OCT human skin images for capillary segmentation. With properly designed data binarization for predicted image frames, the testing result of real FF-OCT data with respect to the ground truth achieved high scores in performance metrics. This demonstrates that the proposed algorithm is capable of generating ACN data that can imitate real FF-OCT skin images of capillary networks for use in research and deep learning, and that the model for capillary segmentation could be of wide benefit in clinical and biomedical applications.

Magnetic-composite-modified polycrystalline silicon nanowire field-effect transistor for vascular endothelial growth factor detection and cancer diagnosis.

This study proposes a vascular endothelial growth factor (VEGF) biosensor for diagnosing various stages of cervical carcinoma. In addition, VEGF concentrations at various stages of cancer therapy are determined and compared to data obtained by computed tomography (CT) and cancer antigen 125 (CA-125). The increase in VEGF concentrations during operations offers useful insight into dosage timing during cancer therapy. This biosensor uses Avastin as the biorecognition element for the potential cancer biomarker VEGF and is based on a n-type polycrystalline silicon nanowire field-effect transistor (poly-SiNW-FET). Magnetic nanoparticles with poly[aniline-co-N-(1-one-butyric acid) aniline]-Fe3O4 (SPAnH-Fe3O4) shell-core structures are used as carriers for Avastin loading and provide rapid purification due to their magnetic properties, which prevent the loss of bioactivity; furthermore, the high surface area of these structures increases the quantity of Avastin immobilized. Average concentrations in human blood for species that interfere with detection specificity are also evaluated. The detection range of the biosensor for serum samples covers the results expected from both healthy individuals and cancer patients.

Rapid (<5 min) identification of pathogen in human blood by electrokinetic concentration and surface-enhanced Raman spectroscopy.

This study reports a novel microfluidic platform for rapid and long-ranged concentration of rare-pathogen from human blood for subsequent on-chip surface-enhanced Raman spectroscopy (SERS) identification/discrimination of bacteria based on their detected fingerprints. Using a hybrid electrokinetic mechanism, bacteria can be concentrated at the stagnation area on the SERS-active roughened electrode, while blood cells were excluded away from this region at the center of concentric circular electrodes. This electrokinetic approach performs isolation and concentration of bacteria in about three minutes; the density factor is increased approximately a thousand fold in a local area of ~5000 µm(2) from a low bacteria concentration of 5 × 10(3) CFU/ml. Besides, three genera of bacteria, S. aureus, E. coli, and P. aeruginosa that are found in most of the isolated infections in bacteremia were successfully identified in less than one minute on-chip without the use of any antibody/chemical immobilization and reaction processes.

A CMOS-compatible poly-Si nanowire device with hybrid sensor/memory characteristics for System-on-Chip applications.

This paper reports a versatile nano-sensor technology using "top-down" poly-silicon nanowire field-effect transistors (FETs) in the conventional Complementary Metal-Oxide Semiconductor (CMOS)-compatible semiconductor process. The nanowire manufacturing technique reduced nanowire width scaling to 50 nm without use of extra lithography equipment, and exhibited superior device uniformity. These n type polysilicon nanowire FETs have positive pH sensitivity (100 mV/pH) and sensitive deoxyribonucleic acid (DNA) detection ability (100 pM) at normal system operation voltages. Specially designed oxide-nitride-oxide buried oxide nanowire realizes an electrically V(th)-adjustable sensor to compensate device variation. These nanowire FETs also enable non-volatile memory application for a large and steady V(th) adjustment window (>2 V Programming/Erasing window). The CMOS-compatible manufacturing technique of polysilicon nanowire FETs offers a possible solution for commercial System-on-Chip biosensor application, which enables portable physiology monitoring and in situ recording.