Detecting Respiratory Viruses Using a Portable NIR Spectrometer-A Preliminary Exploration with a Data Driven Approach.

Respiratory viruses' detection is vitally important in coping with pandemics such as COVID-19. Conventional methods typically require laboratory-based, high-cost equipment. An emerging alternative method is Near-Infrared (NIR) spectroscopy, especially a portable one of the type that has the benefits of low cost, portability, rapidity, ease of use, and mass deployability in both clinical and field settings. One obstacle to its effective application lies in its common limitations, which include relatively low specificity and general quality. Characteristically, the spectra curves show an interweaving feature for the virus-present and virus-absent samples. This then provokes the idea of using machine learning methods to overcome the difficulty. While a subsequent obstacle coincides with the fact that a direct deployment of the machine learning approaches leads to inadequate accuracy of the modelling results. This paper presents a data-driven study on the detection of two common respiratory viruses, the respiratory syncytial virus (RSV) and the Sendai virus (SEV), using a portable NIR spectrometer supported by a machine learning solution enhanced by an algorithm of variable selection via the Variable Importance in Projection (VIP) scores and its Quantile value, along with variable truncation processing, to overcome the obstacles to a certain extent. We conducted extensive experiments with the aid of the specifically developed algorithm of variable selection, using a total of four datasets, achieving classification accuracy of: (1) 0.88, 0.94, and 0.93 for RSV, SEV, and RSV + SEV, respectively, averaged over multiple runs, for the neural network modelling of taking in turn 3 sessions of data for training and the remaining one session of an 'unknown' dataset for testing. (2) the average accuracy of 0.94 (RSV), 0.97 (SEV), and 0.97 (RSV + SEV) for model validation and 0.90 (RSV), 0.93 (SEV), and 0.91 (RSV + SEV) for model testing, using two of the datasets for model training, one for model validation and the other for model testing. These results demonstrate the feasibility of using portable NIR spectroscopy coupled with machine learning to detect respiratory viruses with good accuracy, and the approach could be a viable solution for population screening.

The Monarch Initiative in 2024: an analytic platform integrating phenotypes, genes and diseases across species.

Bridging the gap between genetic variations, environmental determinants, and phenotypic outcomes is critical for supporting clinical diagnosis and understanding mechanisms of diseases. It requires integrating open data at a global scale. The Monarch Initiative advances these goals by developing open ontologies, semantic data models, and knowledge graphs for translational research. The Monarch App is an integrated platform combining data about genes, phenotypes, and diseases across species. Monarch's APIs enable access to carefully curated datasets and advanced analysis tools that support the understanding and diagnosis of disease for diverse applications such as variant prioritization, deep phenotyping, and patient profile-matching. We have migrated our system into a scalable, cloud-based infrastructure; simplified Monarch's data ingestion and knowledge graph integration systems; enhanced data mapping and integration standards; and developed a new user interface with novel search and graph navigation features. Furthermore, we advanced Monarch's analytic tools by developing a customized plugin for OpenAI's ChatGPT to increase the reliability of its responses about phenotypic data, allowing us to interrogate the knowledge in the Monarch graph using state-of-the-art Large Language Models. The resources of the Monarch Initiative can be found at monarchinitiative.org and its corresponding code repository at github.com/monarch-initiative/monarch-app.

Investigating Temporal Features of Carotid Intima-Media Thickness from Ultrasound Imaging with Recurrent Neural Networks.

Measuring carotid intima-media thickness (cIMT) of the Common Carotid Artery (CCA) via B-mode ultrasound imaging is a non-invasive yet effective way to monitor and assess cardiovascular risk. Recent studies using Convolutional Neural Networks (CNNs) to automate the process have mainly focused on the detection of regions of interest (ROI) in single frame images collected at fixed time points and have not exploited the temporal information captured in ultrasound imaging. This paper presents a novel framework to investigate the temporal features of cIMT, in which Recurrent Neural Networks (RNN) were deployed for ROI detection using consecutive frames from ultrasound imaging. The cIMT time series can be formed from estimates of cIMT in each frame of an ultrasound scan, from which additional information (such as min, max, mean, and frequency) on cIMT time series can be extracted. Results from evaluation show the best performance for ROI detection improved 4.75% by RNN compared to CNN-based methods. Furthermore, the heart rate estimated from the cIMT time series for seven patients was highly correlated with the patient's clinical records, which suggests the potential application of the cIMT time series and related features for clinical studies in the future.Clinical relevance- The temporal features extracted from cIMT time series provide additional information that can be potentially beneficial for clinical studies.

Data Mining and Fusion Framework for In-Home Monitoring Applications.

Sensor Data Fusion (SDT) algorithms and models have been widely used in diverse applications. One of the main challenges of SDT includes how to deal with heterogeneous and complex datasets with different formats. The present work utilised both homogenous and heterogeneous datasets to propose a novel SDT framework. It compares data mining-based fusion software packages such as RapidMiner Studio, Anaconda, Weka, and Orange, and proposes a data fusion framework suitable for in-home applications. A total of 574 privacy-friendly (binary) images and 1722 datasets gleaned from thermal and Radar sensing solutions, respectively, were fused using the software packages on instances of homogeneous and heterogeneous data aggregation. Experimental results indicated that the proposed fusion framework achieved an average Classification Accuracy of 84.7% and 95.7% on homogeneous and heterogeneous datasets, respectively, with the help of data mining and machine learning models such as Naïve Bayes, Decision Tree, Neural Network, Random Forest, Stochastic Gradient Descent, Support Vector Machine, and CN2 Induction. Further evaluation of the Sensor Data Fusion framework based on cross-validation of features indicated average values of 94.4% for Classification Accuracy, 95.7% for Precision, and 96.4% for Recall. The novelty of the proposed framework includes cost and timesaving advantages for data labelling and preparation, and feature extraction.

Effect of Selenium Nanoparticle Size on IL-6 Detection Sensitivity in a Lateral Flow Device.

Sepsis is the body's response to an infection. Existing diagnostic testing equipment is not available in primary care settings and requires long waiting times. Lateral flow devices (LFDs) could be employed in point-of-care (POC) settings for sepsis detection; however, they currently lack the required sensitivity. Herein, LFDs are constructed using 150-310 nm sized selenium nanoparticles (SeNPs) and are compared to commercial 40 nm gold nanoparticles (AuNPs) for the detection of the sepsis biomarker interleukin-6 (IL-6). Both 310 and 150 nm SeNPs reported a lower limit of detection (LOD) than 40 nm AuNPs (0.1 ng/mL compared to 1 ng/mL), although at the cost of test line visual intensity. This is to our knowledge the first use of larger SeNPs (>100 nm) in LFDs and the first comparison of the effect of the size of SeNPs on assay sensitivity in this context. The results herein demonstrate that large SeNPs are viable alternatives to existing commercial labels, with the potential for higher sensitivity than standard 40 nm AuNPs.

Assessment of hemodynamic indices of conjunctival microvascular function in patients with coronary microvascular dysfunction.

OBJECTIVE: Coronary microvascular dysfunction (CMD) is a cause of ischaemia with non-obstructive coronary arteries (INOCA). It is notoriously underdiagnosed due to the need for invasive microvascular function testing. We hypothesized that systemic microvascular dysfunction could be demonstrated non-invasively in the microcirculation of the bulbar conjunctiva in patients with CMD. METHODS: Patients undergoing coronary angiography for the investigation of chest pain or dyspnoea, with physiologically insignificant epicardial disease (fractional flow reserve ≥0.80) were recruited. All patients underwent invasive coronary microvascular function testing. We compared a cohort of patients with evidence of CMD (IMR ≥25 or CFR <2.0); to a group of controls (IMR <25 and CFR ≥2.0). Conjunctival imaging was performed using a previously validated combination of a smartphone and slit-lamp biomicroscope. This technique allows measurement of vessel diameter and other indices of microvascular function by tracking erythrocyte motion. RESULTS: A total of 111 patients were included (43 CMD and 68 controls). There were no differences in baseline demographics, co-morbidities or epicardial coronary disease severity. The mean number of vessel segments analysed per patient was 21.0 ± 12.8 (3.2 ± 3.5 arterioles and 14.8 ± 10.8 venules). In the CMD cohort, significant reductions were observed in axial/cross-sectional velocity, blood flow, wall shear rate and stress. CONCLUSION: The changes in microvascular function linked to CMD can be observed non-invasively in the bulbar conjunctiva. Conjunctival vascular imaging may have utility as a non-invasive tool to both diagnose CMD and augment conventional cardiovascular risk assessment.

Assessment of Indices of Conjunctival Microvascular Function in Patients With and Without Obstructive Coronary Artery Disease.

BACKGROUND: Atherosclerotic heart disease often remains asymptomatic until presentation with a major adverse cardiovascular event. Primary preventive therapies improve outcomes, but conventional screening often misattributes risk. Vascular imaging can be utilised to detect atherosclerosis, but often involves ionising radiation. The conjunctiva is a readily accessible vascular network allowing non-invasive hemodynamic evaluation. AIM: To compare conjunctival microcirculatory function in patients with and without obstructive coronary artery disease. METHODS: We compared the conjunctival microcirculation of myocardial infarction patients (MI-cohort) to controls with no obstructive coronary artery disease (NO-CAD cohort). Conjunctival imaging was performed using a smartphone and slit-lamp biomicroscope combination. Microvascular indices of axial (Va) and cross-sectional (Vcs) velocity; blood flow rate (Q); and wall shear rate (WSR) were compared in all conjunctival vessels between 5 and 45 µm in diameter. RESULTS: A total of 127 patients were recruited (66 MI vs 61 NO-CAD) and 3602 conjunctival vessels analysed (2414 MI vs 1188 NO-CAD). Mean Va, Vcs and Q were significantly lower in the MI vs NO-CAD cohort (Va 0.50 ± 0.17 mm/s vs 0.55 ± 0.15 mm/s, p < 0.001; Vcs 0.35 ± 0.12 mm/s vs 0.38 ± 0.10 mm/s, p < 0.001; Q 154 ± 116 pl/s vs 198 ± 130 pl/s, p < 0.001). To correct for differences in mean vessel diameter, WSR was compared in 10-36 µm vessels (3268/3602 vessels) and was lower in the MI-cohort (134 ± 64 s-1 vs 140 ± 63 s-1, p = 0.002). CONCLUSIONS: Conjunctival microcirculatory alterations can be observed in patients with obstructive coronary artery disease. The conjunctival microvasculature merits further evaluation in cardiovascular risk screening.

A novel patches-selection method for the classification of point-of-care biosensing lateral flow assays with cardiac biomarkers.

Cardiovascular Disease (CVD) is amongst the leading cause of death globally, which calls for rapid detection and treatment. Biosensing devices are used for the diagnosis of cardiovascular disease at the point-of-care (POC), with lateral flow assays (LFAs) being particularly useful. However, due to their low sensitivity, most LFAs have been shown to have difficulties detecting low analytic concentrations. Breakthroughs in artificial intelligence (AI) and image processing reduced this detection constraint and improved disease diagnosis. This paper presents a novel patches-selection approach for generating LFA images from the test line and control line of LFA images, analyzing the image features, and utilizing them to reliably predict and classify LFA images by deploying classification algorithms, specifically Convolutional Neural Networks (CNNs). The generated images were supplied as input data to the CNN model, a strong model for extracting crucial information from images, to classify the target images and provide risk stratification levels to medical professionals. With this approach, the classification model produced about 98% accuracy, and as per the literature review, this approach has not been investigated previously. These promising results show the proposed method may be useful for identifying a wide variety of diseases and conditions, including cardiovascular problems.

A Refined Hot Melt Printing Technique with Real-Time CT Imaging Capability.

Personalised drug delivery systems with the ability to offer real-time imaging and control release are an advancement in diagnostic and therapeutic applications. This allows for a tailored drug dosage specific to the patient with a release profile that offers the optimum therapeutic effect. Coupling this application with medical imaging capabilities, real-time contrast can be viewed to display the interaction with the host. Current approaches towards such novelty produce a drug burst release profile and contrasting agents associated with side effects as a result of poor encapsulation of these components. In this study, a 3D-printed drug delivery matrix with real-time imaging is engineered. Polycaprolactone (PCL) forms the bulk structure and encapsulates tetracycline hydrochloride (TH), an antibiotic drug and Iron Oxide Nanoparticles (IONP, Fe3O4), a superparamagnetic contrasting agent. Hot melt extrusion (HME) coupled with fused deposition modelling (FDM) is utilised to promote the encapsulation of TH and IONP. The effect of additives on the formation of micropores (10-20 µm) on the 3D-printed surface was investigated. The high-resolution process demonstrated successful encapsulation of both bioactive and nano components to present promising applications in drug delivery systems, medical imaging and targeted therapy.

Transcutaneous Pulsed RF Energy Transfer Mitigates Tissue Heating in High Power Demand Implanted Device Applications: In Vivo and In Silico Models Results.

This article presents the development of a power loss emulation (PLE) system device to study and find ways of mitigating skin tissue heating effects in transcutaneous energy transmission systems (TETS) for existing and next generation left ventricular assist devices (LVADs). Skin thermal profile measurements were made using the PLE system prototype and also separately with a TETS in a porcine model. Subsequent data analysis and separate computer modelling studies permit understanding of the contribution of tissue blood perfusion towards cooling of the subcutaneous tissue around the electromagnetic coupling area. A 2-channel PLE system prototype and a 2-channel TETS prototype were implemented for this study. The heating effects resulting from power transmission inefficiency were investigated under varying conditions of power delivery levels for an implanted device. In the part of the study using the PLE setup, the implanted heating element was placed subcutaneously 6-8 mm below the body surface of in vivo porcine model skin. Two operating modes of transmission coupling power losses were emulated: (a) conventional continuous transmission, and (b) using our proposed pulsed transmission waveform protocols. Experimental skin tissue thermal profiles were studied for various levels of LVAD power. The heating coefficient was estimated from the porcine model measurements (an in vivo living model and a euthanised cadaver model without blood circulation at the end of the experiment). An in silico model to support data interpretation provided reliable experimental and numerical methods for effective wireless transdermal LVAD energization advanced solutions. In the separate second part of the study conducted with a separate set of pigs, a two-channel inductively coupled RF driving system implemented wireless power transfer (WPT) to a resistive LVAD model (50 Ω) to explore continuous versus pulsed RF transmission modes. The RF-transmission pulse duration ranged from 30 ms to 480 ms, and the idle time (no-transmission) from 5 s to 120 s. The results revealed that blood perfusion plays an important cooling role in reducing thermal tissue damage from TETS applications. In addition, the results analysis of the in vivo, cadaver (R1Sp2) model, and in silico studies confirmed that the tissue heating effect was significantly lower in the living model versus the cadaver model due to the presence of blood perfusion cooling effects.

Device agnostic AI-based analysis of ambulatory ECG recordings.

Deep Convolutional Neural Networks (DCNNs) have been shown to provide improved performance over traditional heuristic algorithms for the detection of arrhythmias from ambulatory ECG recordings. However, these DCNNs have primarily been trained and tested on device-specific databases with standardized electrode positions and uniform sampling frequencies. This work explores the possibility of training a DCNN for Atrial Fibrillation (AF) detection on a database of single­lead ECG rhythm strips extracted from resting 12­lead ECGs. We then test the performance of the DCNN on recordings from ambulatory ECG devices with different recording leads and sampling frequencies. We developed an extensive proprietary resting 12­lead ECG dataset of 549,211 patients. This dataset was randomly split into a training set of 494,289 patients and a testing set of the remaining 54,922 patients. We trained a 34-layer convolutional DCNN to detect AF and other arrhythmias on this dataset. The DCNN was then validated on two Physionet databases commonly used to benchmark automated ECG algorithms (1) MIT-BIH Arrhythmia Database and (2) MIT-BIH Atrial Fibrillation Database. Validation was performed following the EC57 guidelines, with performance assessed by gross episode and duration sensitivity and positive predictive value (PPV). Finally, validation was also performed on a selection of rhythm strips from an ambulatory ECG patch that a committee of board-certified cardiologists annotated. On MIT-BIH, The DCNN achieved a sensitivity of 100% and 84% PPV in detecting episodes of AF. and 100% sensitivity and 94% PPV in quantifying AF episode duration. On AFDB, The DCNN achieved a sensitivity of 94% and PPV of 98% in detecting episodes of AF, and 98% sensitivity and 100% PPV in quantifying AF episode duration. On the patch database, the DCNN demonstrated performance that was closely comparable to that of a cardiologist. The results indicate that DCNN models can learn features that generalize between resting 12­lead and ambulatory ECG recordings, allowing DCNNs to be device agnostic for detecting arrhythmias from single­lead ECG recordings and enabling a range of clinical applications.

Effect of Functional Electrical Stimulation on Capillary Blood Flow to Muscle.

Functional electrical stimulation (FES) modifies red blood cells (RBCs) flux in blood capillaries of muscle. In this work, we aim to investigate changes in the RBC flux in small and large capillaries due to FES using zinc oxide nanowires (ZnO NWs) based electrode at different stimulation parameters. The RBC flux was significantly increased immediately after stimulation, which was evident from decreasing light intensity measured in the region of interest. Clinical Relevance- FES has numerous forms and functions. The benefit of FES is the increased blood flow to a muscle which is contracted abnormally. This work explores the use of FES to increase the blood flow and RBC flux in blood capillaries of stimulated muscle as FES generate muscle contraction and absorption.

Australian aquatic bio-optical dataset with applications for satellite calibration, algorithm development and validation.

The authors present bio-optical data spanning 316 sets of observations made at 34 inland waterbodies in Australia. The data was collected over the period 2013-2021 and comprise radiometric measurements of remote sensing reflectance (Rrs), diffuse attenuation extinction coefficient (Kd); optical backscattering; absorption of coloured dissolved organic matter (aCDOM), phytoplankton (aph) and non-algal particles (aNAP); HPLC analysis of algal pigments including chlorophyll-a (CHL-a); organic and inorganic total suspended solids (TSS); and total and dissolved organic carbon concentration. Data collection has been timed to coincide with either Landsat 8 or Sentinel-2 overpasses. The dataset covers a diverse range of optical water types and is suitable for algorithm development, satellite calibration and validation as well as machine learning applications.

Point-of-Care Monitoring of Respiratory Diseases Using Lateral Flow Assay and CMOS Camera Reader.

OBJECTIVE: Respiratory disease is a rapidly growing global health issue that impacts the quality of living of tens of millions of people around the world. Neutrophil elastase (NE) represents a key inflammatory biomarker and has previously been demonstrated to have the capability of predicting exacerbation risk related to respiratory diseases. This paper utilises a low-cost Point of Care (PoC) approach using Lateral Flow Assays (LFAs) to provide quantitative measurement of active NE in a patient's sputum. METHODS AND PROCEDURES: The main aim of this study is to develop a quantitative platform using a Complementary Metal-Oxide-Semiconductor (CMOS) to image the LFAs and with an adaptable image analysis algorithm to measure a target biomarker concentration. This result could be used to monitor a patient's health and quality of living. In the paper, NE is used as the target biomarker to determine if the patient is suffering from a high risk of exacerbations. RESULTS: The results presented in the paper indicate the CMOS reader approach is promising for rapid and low-cost PoC devices, with the current system able to provide quantitative trends of NE concentrations as low as 100 ng/ml and is comparable to a research-based laboratory lateral flow reader. CONCLUSION: The image analysis algorithm used in the CMOS reader can estimate the minimum NE concentration of 250 ng/ml to indicate the high-risk category for exacerbations from respiratory illnesses with the same accuracy as expensive a research-based laboratory reader but by using low-cost components and onboard image analysis. CLINICAL IMPACT: The image analysis algorithm is evaluated to analyse LFAs with NE biomarker to determine the patient in a high-risk category for exacerbations. The device communicates the analysis result to medical professionals for daily historical logging for daily health monitoring without regular hospital appointments. The low-cost approach of the proposed system and image analysis approach can be adapted to analyse different biomarkers for other health concerns including multiplex LFAs without additional hardware in the reader design.

Disposable Paper-Based Biosensors: Optimizing the Electrochemical Properties of Laser-Induced Graphene.

Laser-induced graphene (LIG) on paper substrates is a desirable material for single-use point-of-care sensing with its high-quality electrical properties, low fabrication cost, and ease of disposal. While a prior study has shown how the repeated lasing of substrates enables the synthesis of high-quality porous graphitic films, however, the process-property correlation of lasing process on the surface microstructure and electrochemical behavior, including charge-transfer kinetics, is missing. The current study presents a systematic in-depth study on LIG synthesis to elucidate the complex relationship between the surface microstructure and the resulting electroanalytical properties. The observed improvements were then applied to develop high-quality LIG-based electrochemical biosensors for uric acid detection. We show that the optimal paper LIG produced via a dual pass (defocused followed by focused lasing) produces high-quality graphene in terms of crystallinity, sp2 content, and electrochemical surface area. The highest quality LIG electrodes achieved a high rate constant k0 of 1.5 × 10-2 cm s-1 and a significant reduction in charge-transfer resistance (818 Ω compared with 1320 Ω for a commercial glassy carbon electrode). By employing square wave anodic stripping voltammetry and chronoamperometry on a disposable two-electrode paper LIG-based device, the improved charge-transfer kinetics led to enhanced performance for sensing of uric acid with a sensitivity of 24.35 ± 1.55 µA µM-1 and a limit of detection of 41 nM. This study shows how high-quality, sensitive LIG electrodes can be integrated into electrochemical paper analytical devices.

A Simple Standard for Sharing Ontological Mappings (SSSOM).

Despite progress in the development of standards for describing and exchanging scientific information, the lack of easy-to-use standards for mapping between different representations of the same or similar objects in different databases poses a major impediment to data integration and interoperability. Mappings often lack the metadata needed to be correctly interpreted and applied. For example, are two terms equivalent or merely related? Are they narrow or broad matches? Or are they associated in some other way? Such relationships between the mapped terms are often not documented, which leads to incorrect assumptions and makes them hard to use in scenarios that require a high degree of precision (such as diagnostics or risk prediction). Furthermore, the lack of descriptions of how mappings were done makes it hard to combine and reconcile mappings, particularly curated and automated ones. We have developed the Simple Standard for Sharing Ontological Mappings (SSSOM) which addresses these problems by: (i) Introducing a machine-readable and extensible vocabulary to describe metadata that makes imprecision, inaccuracy and incompleteness in mappings explicit. (ii) Defining an easy-to-use simple table-based format that can be integrated into existing data science pipelines without the need to parse or query ontologies, and that integrates seamlessly with Linked Data principles. (iii) Implementing open and community-driven collaborative workflows that are designed to evolve the standard continuously to address changing requirements and mapping practices. (iv) Providing reference tools and software libraries for working with the standard. In this paper, we present the SSSOM standard, describe several use cases in detail and survey some of the existing work on standardizing the exchange of mappings, with the goal of making mappings Findable, Accessible, Interoperable and Reusable (FAIR). The SSSOM specification can be found at http://w3id.org/sssom/spec. Database URL: http://w3id.org/sssom/spec.

A novel algorithm for cardiovascular screening using conjunctival microcirculatory parameters and blood biomarkers.

Microvascular haemodynamic alterations are associated with coronary artery disease (CAD). The conjunctival microcirculation can easily be assessed non-invasively. However, the microcirculation of the conjunctiva has not been previously explored in clinical algorithms aimed at identifying patients with CAD. This case-control study involved 66 patients with post-myocardial infarction and 66 gender-matched healthy controls. Haemodynamic properties of the conjunctival microcirculation were assessed with a validated iPhone and slit lamp-based imaging tool. Haemodynamic properties were extracted with semi-automated software and compared between groups. Biomarkers implicated in the development of CAD were assessed in combination with conjunctival microcirculatory parameters. The conjunctival blood vessel parameters and biomarkers were used to derive an algorithm to aid in the screening of patients for CAD. Conjunctival blood velocity measured in combination with the blood biomarkers (N-terminal pro-brain natriuretic peptide and adiponectin) had an area under receiver operator characteristic curve (AUROC) of 0.967, sensitivity 93.0%, specificity 91.5% for CAD. This study demonstrated that the novel algorithm which included a combination of conjunctival blood vessel haemodynamic properties, and blood-based biomarkers could be used as a potential screening tool for CAD and should be validated for potential utility in asymptomatic individuals.

WaSP-ECG: A Wave Segmentation Pretraining Toolkit for Electrocardiogram Analysis.

Introduction: Representation learning allows artificial intelligence (AI) models to learn useful features from large, unlabelled datasets. This can reduce the need for labelled data across a range of downstream tasks. It was hypothesised that wave segmentation would be a useful form of electrocardiogram (ECG) representation learning. In addition to reducing labelled data requirements, segmentation masks may provide a mechanism for explainable AI. This study details the development and evaluation of a Wave Segmentation Pretraining (WaSP) application. Materials and Methods: Pretraining: A non-AI-based ECG signal and image simulator was developed to generate ECGs and wave segmentation masks. U-Net models were trained to segment waves from synthetic ECGs. Dataset: The raw sample files from the PTB-XL dataset were downloaded. Each ECG was also plotted into an image. Fine-tuning and evaluation: A hold-out approach was used with a 60:20:20 training/validation/test set split. The encoder portions of the U-Net models were fine-tuned to classify PTB-XL ECGs for two tasks: sinus rhythm (SR) vs atrial fibrillation (AF), and myocardial infarction (MI) vs normal ECGs. The fine-tuning was repeated without pretraining. Results were compared. Explainable AI: an example pipeline combining AI-derived segmentation masks and a rule-based AF detector was developed and evaluated. Results: WaSP consistently improved model performance on downstream tasks for both ECG signals and images. The difference between non-pretrained models and models pretrained for wave segmentation was particularly marked for ECG image analysis. A selection of segmentation masks are shown. An AF detection algorithm comprising both AI and rule-based components performed less well than end-to-end AI models but its outputs are proposed to be highly explainable. An example output is shown. Conclusion: WaSP using synthetic data and labels allows AI models to learn useful features for downstream ECG analysis with real-world data. Segmentation masks provide an intermediate output that may facilitate confidence calibration in the context of end-to-end AI. It is possible to combine AI-derived segmentation masks and rule-based diagnostic classifiers for explainable ECG analysis.

IgG antibody production and persistence to 6 months following SARS-CoV-2 vaccination: A Northern Ireland observational study.

BACKGROUND: This study evaluates spike protein IgG antibody response following Oxford-AstraZeneca COVID-19 vaccination using the AbC-19™ lateral flow device. METHODS: Plasma samples were collected from n = 111 individuals from Northern Ireland. The majority were >50 years old and/or clinically vulnerable. Samples were taken at five timepoints from pre-vaccination until 6-months post-first dose. RESULTS: 20.3% of participants had detectable IgG responses pre-vaccination, indicating prior COVID-19. Antibodies were detected in 86.9% of participants three weeks after the first vaccine dose, falling to 74.7% immediately prior to the second dose, and rising to 99% three weeks post-second vaccine. At 6-months post-first dose, this decreased to 90.5%. At all timepoints, previously infected participants had significantly higher antibody levels than those not previously infected. CONCLUSION: This study demonstrates that strong anti-spike protein antibody responses are evoked in almost all individuals that receive two doses of Oxford-AstraZeneca vaccine, and which largely persist beyond six months after first vaccination.

High-Sensitive Detection and Quantitative Analysis of Thyroid-Stimulating Hormone Using Gold-Nanoshell-Based Lateral Flow Immunoassay Device.

Au nanoparticles (AuNPs) have been used as signal reporters in colorimetric lateral flow immunoassays (LFAs) for decades. However, it remains a major challenge to significantly improve the detection sensitivity of traditional LFAs due to the low brightness of AuNPs. As an alternative approach, we overcome this problem by utilizing 150 nm gold nanoshells (AuNSs) that were engineered by coating low-density silica nanoparticles with a thin layer of gold. AuNSs are dark green, have 14 times larger surface area, and are approximately 35 times brighter compared to AuNPs. In this study, we used detection of thyroid-stimulating hormone (TSH) in a proof-of-concept assay. The limit of detection (LOD) with AuNS-based LFA was 0.16 µIU/mL, which is 26 times more sensitive than the conventional colorimetric LFA that utilizes AuNP as a label. The dynamic range of the calibration curve was 0.16−9.5 µIU/mL, making it possible to diagnose both hyperthyroidism (<0.5 µIU/mL) and hypothyroidism (>5 µIU/mL) using AuNS-based LFA. Thus, the developed device has a strong potential for early screening and diagnosis of diseases related to the thyroid hormone.