Point-of-Care Serodiagnostic Test for Early-Stage Lyme Disease Using a Multiplexed Paper-Based Immunoassay and Machine Learning

A Paper-Based Multiplexed Serological Test to Monitor Immunity against SARS-COV-2 Using Machine Learning

The rapid spread of SARS-CoV-2 caused the COVID-19 pandemic and accelerated vaccine development to prevent the spread of the virus and control the disease. Given the sustained high infectivity and evolution of SARS-CoV-2, there is an ongoing interest in developing COVID-19 serology tests to monitor population-level immunity. To address this critical need, we designed a paper-based multiplexed vertical flow assay (xVFA) using five structural proteins of SARS-CoV-2, detecting IgG and IgM antibodies to monitor changes in COVID-19 immunity levels. Our platform not only tracked longitudinal immunity levels but also categorized COVID-19 immunity into three groups: protected, unprotected, and infected, based on the levels of IgG and IgM antibodies. We operated two xVFAs in parallel to detect IgG and IgM antibodies using a total of 40 μL of human serum sample in <20 min per test. After the assay, images of the paper-based sensor panel were captured using a mobile phone-based custom-designed optical reader and then processed by a neural network-based serodiagnostic algorithm. The serodiagnostic algorithm was trained with 120 measurements/tests and 30 serum samples from 7 randomly selected individuals and was blindly tested with 31 serum samples from 8 different individuals, collected before vaccination as well as after vaccination or infection, achieving an accuracy of 89.5%. The competitive performance of the xVFA, along with its portability, cost-effectiveness, and rapid operation, makes it a promising computational point-of-care (POC) serology test for monitoring COVID-19 immunity, aiding in timely decisions on the administration of booster vaccines and general public health policies to protect vulnerable populations.

Automatic offline-capable smartphone paper-based microfluidic device for efficient biomarker detection of Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is a prevalent neurodegenerative disease with no effective treatment. Efficient and rapid detection plays a crucial role in mitigating and managing AD progression. Deep learning-assisted smartphone-based microfluidic paper analysis devices (μPADs) offer the advantages of low cost, good sensitivity, and rapid detection, providing a strategic pathway to address large-scale disease screening in resource-limited areas. However, existing smartphone-based detection platforms usually rely on large devices or cloud servers for data transfer and processing. Additionally, the implementation of automated colorimetric enzyme-linked immunoassay (c-ELISA) on μPADs can further facilitate the realization of smartphone μPADs platforms for efficient disease detection.

RESULTS

This paper introduces a new deep learning-assisted offline smartphone platform for early AD screening, offering rapid disease detection in low-resource areas. The proposed platform features a simple mechanical rotating structure controlled by a smartphone, enabling fully automated c-ELISA on μPADs. Our platform successfully applied sandwich c-ELISA for detecting the β-amyloid peptide 1-42 (Aβ 1-42, a crucial AD biomarker) and demonstrated its efficacy in 38 artificial plasma samples (healthy: 19, unhealthy: 19, N = 6). Moreover, we employed the YOLOv5 deep learning model and achieved an impressive 97 % accuracy on a dataset of 1824 images, which is 10.16 % higher than the traditional method of curve-fitting results. The trained YOLOv5 model was seamlessly integrated into the smartphone using the NCNN (Tencent's Neural Network Inference Framework), enabling deep learning-assisted offline detection. A user-friendly smartphone application was developed to control the entire process, realizing a streamlined "samples in, answers out" approach.

SIGNIFICANCE

This deep learning-assisted, low-cost, user-friendly, highly stable, and rapid-response automated offline smartphone-based detection platform represents a good advancement in point-of-care testing (POCT). Moreover, our platform provides a feasible approach for efficient AD detection by examining the level of Aβ 1-42, particularly in areas with low resources and limited communication infrastructure.

Electrochemical Paper-Based Microfluidics: Harnessing Capillary Flow for Advanced Diagnostics

Electrochemical paper-based microfluidics has attracted much attention due to the promise of transforming point-of-care diagnostics by facilitating quantitative analysis with low-cost and portable analyzers. Such devices harness capillary flow to transport samples and reagents, enabling bioassays to be executed passively. Despite exciting demonstrations of capillary-driven electrochemical tests, conventional methods for fabricating electrodes on paper impede capillary flow, limit fluidic pathways, and constrain accessible device architectures. This account reviews recent developments in paper-based electroanalytical devices and offers perspective by revisiting key milestones in lateral flow tests and paper-based microfluidics engineering. The study highlights the benefits associated with electrochemical sensing and discusses how the detection modality can be leveraged to unlock novel functionalities. Particular focus is given to electrofluidic platforms that embed electrodes into paper for enhanced biosensing applications. Together, these innovations pave the way for diagnostic technologies that offer portability, quantitative analysis, and seamless integration with digital healthcare, all without compromising the simplicity of commercially available rapid diagnostic tests.

Artificial Intelligence in Point-of-Care Biosensing: Challenges and Opportunities

The integration of artificial intelligence (AI) into point-of-care (POC) biosensing has the potential to revolutionize diagnostic methodologies by offering rapid, accurate, and accessible health assessment directly at the patient level. This review paper explores the transformative impact of AI technologies on POC biosensing, emphasizing recent computational advancements, ongoing challenges, and future prospects in the field. We provide an overview of core biosensing technologies and their use at the POC, highlighting ongoing issues and challenges that may be solved with AI. We follow with an overview of AI methodologies that can be applied to biosensing, including machine learning algorithms, neural networks, and data processing frameworks that facilitate real-time analytical decision-making. We explore the applications of AI at each stage of the biosensor development process, highlighting the diverse opportunities beyond simple data analysis procedures. We include a thorough analysis of outstanding challenges in the field of AI-assisted biosensing, focusing on the technical and ethical challenges regarding the widespread adoption of these technologies, such as data security, algorithmic bias, and regulatory compliance. Through this review, we aim to emphasize the role of AI in advancing POC biosensing and inform researchers, clinicians, and policymakers about the potential of these technologies in reshaping global healthcare landscapes.

Microfluidic systems for infectious disease diagnostics

Microorganisms, encompassing both uni- and multicellular entities, exhibit remarkable diversity as omnipresent life forms in nature. They play a pivotal role by supplying essential components for sustaining biological processes across diverse ecosystems, including higher host organisms. The complex interactions within the human gut microbiota are crucial for metabolic functions, immune responses, and biochemical signalling, particularly through the gut-brain axis. Viruses also play important roles in biological processes, for example by increasing genetic diversity through horizontal gene transfer when replicating inside living cells. On the other hand, infection of the human body by microbiological agents may lead to severe physiological disorders and diseases. Infectious diseases pose a significant burden on global healthcare systems, characterized by substantial variations in the epidemiological landscape. Fast spreading antibiotic resistance or uncontrolled outbreaks of communicable diseases are major challenges at present. Furthermore, delivering field-proven point-of-care diagnostic tools to the most severely affected populations in low-resource settings is particularly important and challenging. New paradigms and technological approaches enabling rapid and informed disease management need to be implemented. In this respect, infectious disease diagnostics taking advantage of microfluidic systems combined with integrated biosensor-based pathogen detection offers a host of innovative and promising solutions. In this review, we aim to outline recent activities and progress in the development of microfluidic diagnostic tools. Our literature research mainly covers the last 5 years. We will follow a classification scheme based on the human body systems primarily involved at the clinical level or on specific pathogen transmission modes. Important diseases, such as tuberculosis and malaria, will be addressed more extensively.

Recent advances in point-of-care testing of COVID-19

Advances in microfluidic device miniaturization and system integration contribute to the development of portable, handheld, and smartphone-compatible devices. These advancements in diagnostics have the potential to revolutionize the approach to detect and respond to future pandemics. Accordingly, herein, recent advances in point-of-care testing (POCT) of coronavirus disease 2019 (COVID-19) using various microdevices, including lateral flow assay strips, vertical flow assay strips, microfluidic channels, and paper-based microfluidic devices, are reviewed. However, visual determination of the diagnostic results using only microdevices leads to many false-negative results due to the limited detection sensitivities of these devices. Several POCT systems comprising microdevices integrated with portable optical readers have been developed to address this issue. Since the outbreak of COVID-19, effective POCT strategies for COVID-19 based on optical detection methods have been established. They can be categorized into fluorescence, surface-enhanced Raman scattering, surface plasmon resonance spectroscopy, and wearable sensing. We introduced next-generation pandemic sensing methods incorporating artificial intelligence that can be used to meet global health needs in the future. Additionally, we have discussed appropriate responses of various testing devices to emerging infectious diseases and prospective preventive measures for the post-pandemic era. We believe that this review will be helpful for preparing for future infectious disease outbreaks.

Deep Learning-Enabled Multiplexed Point-of-Care Sensor using a Paper-Based Fluorescence Vertical Flow Assay

Multiplexed computational sensing with a point-of-care serodiagnosis assay to simultaneously quantify three biomarkers of acute cardiac injury is demonstrated. This point-of-care sensor includes a paper-based fluorescence vertical flow assay (fxVFA) processed by a low-cost mobile reader, which quantifies the target biomarkers through trained neural networks, all within <15 min of test time using 50 µL of serum sample per patient. This fxVFA platform is validated using human serum samples to quantify three cardiac biomarkers, i.e., myoglobin, creatine kinase-MB, and heart-type fatty acid binding protein, achieving less than 0.52 ng mL-1 limit-of-detection for all three biomarkers with minimal cross-reactivity. Biomarker concentration quantification using the fxVFA that is coupled to neural network-based inference is blindly tested using 46 individually activated cartridges, which shows a high correlation with the ground truth concentrations for all three biomarkers achieving >0.9 linearity and <15% coefficient of variation. The competitive performance of this multiplexed computational fxVFA along with its inexpensive paper-based design and handheld footprint makes it a promising point-of-care sensor platform that can expand access to diagnostics in resource-limited settings.

Advancing diagnostic efficacy using a computer vision-assisted lateral flow assay for influenza and SARS-CoV-2 detection

Lateral flow assays (LFAs) have emerged as indispensable tools for point-of-care testing during the pandemic era. However, the interpretation of results through unassisted visual inspection by untrained individuals poses inherent limitations. In our study, we propose a novel approach that combines computer vision (CV) and lightweight machine learning (ML) to overcome these limitations and significantly enhance the performance of LFAs. By incorporating CV-assisted analysis into the LFA assay, we achieved a remarkable three-fold improvement in analytical sensitivity for detecting Influenza A and for SARS-CoV-2 detection. The obtained R2 values reached approximately 0.95, respectively, demonstrating the effectiveness of our approach. Moreover, the integration of CV techniques with LFAs resulted in a substantial amplification of the colorimetric signal specifically for COVID-19 positive patient samples. Our proposed approach, which incorporates a simple machine learning algorithm, provides substantial enhancements in assay sensitivity, improving diagnostic efficacy and accessibility of point-of-care testing without requiring significant additional resources. Moreover, the simplicity of the machine learning algorithm enables its standalone use on a mobile phone, further enhancing its practicality for point-of-care testing.

Lyme rashes disease classification using deep feature fusion technique

Automatic classification of Lyme disease rashes on the skin helps clinicians and dermatologists' probe and investigate Lyme skin rashes effectively. This paper proposes a new in-depth features fusion system to classify Lyme disease rashes. The proposed method consists of two main steps. First, three different deep learning models, Densenet201, InceptionV3, and Exception, were trained independently to extract the deep features from the erythema migrans (EM) images. Second, a deep feature fusion mechanism (meta classifier) is developed to integrate the deep features before the final classification output layer. The meta classifier is a basic deep convolutional neural network trained on original images and features extracted from base level three deep learning models. In the feature fusion mechanism, the last three layers of base models are dropped out and connected to the meta classifier. The proposed deep feature fusion method significantly improved the classification process, where the classification accuracy was 98.97%, which is particularly impressive than the other state-of-the-art models.

From Tick to Test: A Comprehensive Review of Tick-Borne Disease Diagnostics and Surveillance Methods in the United States

Tick-borne diseases (TBDs) have become a significant public health concern in the United States over the past few decades. The increasing incidence and geographical spread of these diseases have prompted the implementation of robust surveillance systems to monitor their prevalence, distribution, and impact on human health. This comprehensive review describes key disease features with the geographical distribution of all known tick-borne pathogens in the United States, along with examining disease surveillance efforts, focusing on strategies, challenges, and advancements. Surveillance methods include passive and active surveillance, laboratory-based surveillance, sentinel surveillance, and a One Health approach. Key surveillance systems, such as the National Notifiable Diseases Surveillance System (NNDSS), TickNET, and the Tick-Borne Disease Laboratory Network (TBDLN), are discussed. Data collection and reporting challenges, such as underreporting and misdiagnosis, are highlighted. The review addresses challenges, including lack of standardization, surveillance in non-human hosts, and data integration. Innovations encompass molecular techniques, syndromic surveillance, and tick surveillance programs. Implications for public health cover prevention strategies, early detection, treatment, and public education. Future directions emphasize enhanced surveillance networks, integrated vector management, research priorities, and policy implications. This review enhances understanding of TBD surveillance, aiding in informed decision-making for effective disease prevention and control. By understanding the current surveillance landscape, public health officials, researchers, and policymakers can make informed decisions to mitigate the burden of (TBDs).

Modified polysulfone membrane facilitates rapid separation of plasma from whole blood for an effective anti-SARS-CoV-2-IgM diagnosis

During the outbreak of coronavirus, RT-PCR was the premier gold standard method for severe acute respiratory syndrome coronavirus 2 (SARSCoV-2) diagnosis. However, the sophisticated procedure of RT-PCR persuades researchers to develop sustainable point-of-need immunoassay methods for tracing unwitting carriers of SARSCoV-2. Herein, by fabricating a modified polysulfone (MPSF) membrane, we developed an integrated radial flow immunoassay (IRFIA) platform as a point-of-care system, capable of multiplying the immunoassays at a short run time. The target molecule is the SARSCoV-2 IgM in separated plasma. Although the lateral flow immunoassay kits for the rapid identification of Covid-19 have already been commercially developed but, the proposed method is superior to the conventional lateral flow immunoassay. In the newly designed membrane system, we have combined the five membranes of prevalent lateral flow immunoassay (LFIA) strips in one polymeric membrane. The MPSF membrane is capable of separating plasma from whole blood sample, which will reduce the interference of red colour of hemoglobin with generated signal and enhance the immunoassay precision. The efficiency of plasma separation, reached the mean value of 97.34 v/v% in 5 s. Furthermore, the gel electrophoresis results of the separated plasma contrasted with centrifuged plasma sample, demonstrated more efficient separation by the membrane. Using the MPSF membrane, signal generation time reduced from about 20 min in conventional rapid test strip for Covid-19 to about 7 min in IRFIA platform. The sensitivity and specificity of the membrane platform were determined to be 89% and 90%, respectively and a Kappa coefficient of 0.79 showed reliable agreement between the RT-PCR and the membrane system.

Lyme borreliosis diagnosis: state of the art of improvements and innovations

With almost 700 000 estimated cases each year in the United States and Europe, Lyme borreliosis (LB), also called Lyme disease, is the most common tick-borne illness in the world. Transmitted by ticks of the genus Ixodes and caused by bacteria Borrelia burgdorferi sensu lato, LB occurs with various symptoms, such as erythema migrans, which is characteristic, whereas others involve blurred clinical features such as fatigue, headaches, arthralgia, and myalgia. The diagnosis of Lyme borreliosis, based on a standard two-tiered serology, is the subject of many debates and controversies, since it relies on an indirect approach which suffers from a low sensitivity depending on the stage of the disease. Above all, early detection of the disease raises some issues. Inappropriate diagnosis of Lyme borreliosis leads to therapeutic wandering, inducing potential chronic infection with a strong antibody response that fails to clear the infection. Early and proper detection of Lyme disease is essential to propose an adequate treatment to patients and avoid the persistence of the pathogen. This review presents the available tests, with an emphasis on the improvements of the current diagnosis, the innovative methods and ideas which, ultimately, will allow more precise detection of LB.

Trends of respiratory virus detection in point-of-care testing: A review

In resource-limited conditions such as the COVID-19 pandemic, on-site detection of diseases using the Point-of-care testing (POCT) technique is becoming a key factor in overcoming crises and saving lives. For practical POCT in the field, affordable, sensitive, and rapid medical testing should be performed on simple and portable platforms, instead of laboratory facilities. In this review, we introduce recent approaches to the detection of respiratory virus targets, analysis trends, and prospects. Respiratory viruses occur everywhere and are one of the most common and widely spreading infectious diseases in the human global society. Seasonal influenza, avian influenza, coronavirus, and COVID-19 are examples of such diseases. On-site detection and POCT for respiratory viruses are state-of-the-art technologies in this field and are commercially valuable global healthcare topics. Cutting-edge POCT techniques have focused on the detection of respiratory viruses for early diagnosis, prevention, and monitoring to protect against the spread of COVID-19. In particular, we highlight the application of sensing techniques to each platform to reveal the challenges of the development stage. Recent POCT approaches have been summarized in terms of principle, sensitivity, analysis time, and convenience for field applications. Based on the analysis of current states, we also suggest the remaining challenges and prospects for the use of the POCT technique for respiratory virus detection to improve our protection ability and prevent the next pandemic.

Recent Approaches to Design and Analysis of Electrical Impedance Systems for Single Cells Using Machine Learning

Individual cells have many unique properties that can be quantified to develop a holistic understanding of a population. This can include understanding population characteristics, identifying subpopulations, or elucidating outlier characteristics that may be indicators of disease. Electrical impedance measurements are rapid and label-free for the monitoring of single cells and generate large datasets of many cells at single or multiple frequencies. To increase the accuracy and sensitivity of measurements and define the relationships between impedance and biological features, many electrical measurement systems have incorporated machine learning (ML) paradigms for control and analysis. Considering the difficulty capturing complex relationships using traditional modelling and statistical methods due to population heterogeneity, ML offers an exciting approach to the systemic collection and analysis of electrical properties in a data-driven way. In this work, we discuss incorporation of ML to improve the field of electrical single cell analysis by addressing the design challenges to manipulate single cells and sophisticated analysis of electrical properties that distinguish cellular changes. Looking forward, we emphasize the opportunity to build on integrated systems to address common challenges in data quality and generalizability to save time and resources at every step in electrical measurement of single cells.

Rapidly adaptable automated interpretation of point-of-care COVID-19 diagnostics

BACKGROUND

Point-of-care diagnostic devices, such as lateral-flow assays, are becoming widely used by the public. However, efforts to ensure correct assay operation and result interpretation rely on hardware that cannot be easily scaled or image processing approaches requiring large training datasets, necessitating large numbers of tests and expert labeling with validated specimens for every new test kit format.

METHODS

We developed a software architecture called AutoAdapt POC that integrates automated membrane extraction, self-supervised learning, and few-shot learning to automate the interpretation of POC diagnostic tests using smartphone cameras in a scalable manner. A base model pre-trained on a single LFA kit is adapted to five different COVID-19 tests (three antigen, two antibody) using just 20 labeled images.

RESULTS

Here we show AutoAdapt POC to yield 99% to 100% accuracy over 726 tests (350 positive, 376 negative). In a COVID-19 drive-through study with 74 untrained users self-testing, 98% found image collection easy, and the rapidly adapted models achieved classification accuracies of 100% on both COVID-19 antigen and antibody test kits. Compared with traditional visual interpretation on 105 test kit results, the algorithm correctly identified 100% of images; without a false negative as interpreted by experts. Finally, compared to a traditional convolutional neural network trained on an HIV test kit, the algorithm showed high accuracy while requiring only 1/50th of the training images.

CONCLUSIONS

The study demonstrates how rapid domain adaptation in machine learning can provide quality assurance, linkage to care, and public health tracking for untrained users across diverse POC diagnostic tests.

Single-tier point-of-care serodiagnosis of Lyme disease

Point-of-care (POC) serological testing provides actionable information for several difficult to diagnose illnesses, empowering distributed health systems. Accessible and adaptable diagnostic platforms that can assay the repertoire of antibodies formed against pathogens are essential to drive early detection and improve patient outcomes. Here, we report a POC serologic test for Lyme disease (LD), leveraging synthetic peptides tuned to be highly specific to the LD antibody repertoire across patients and compatible with a paper-based platform for rapid, reliable, and cost-effective diagnosis. A subset of antigenic epitopes conserved across Borrelia burgdorferi genospecies and targeted by IgG and IgM antibodies, were selected based on their seroreactivity to develop a multiplexed panel for a single-step measurement of combined IgM and IgG antibodies from LD patient sera. Multiple peptide epitopes, when combined synergistically using a machine learning-based diagnostic model, yielded a high sensitivity without any loss in specificity. We blindly tested the platform with samples from the U.S. Centers for Disease Control & Prevention (CDC) LD repository and achieved a sensitivity and specificity matching the lab-based two-tier results with a single POC test, correctly discriminating cross-reactive look-alike diseases. This computational LD diagnostic test can potentially replace the cumbersome two-tier testing paradigm, improving diagnosis and enabling earlier effective treatment of LD patients while also facilitating immune monitoring and surveillance of the disease in the community.

Deep learning-assisted ultra-accurate smartphone testing of paper-based colorimetric ELISA assays

Smartphone has long been considered as one excellent platform for disease screening and diagnosis, especially when combined with microfluidic paper-based analytical devices (μPADs) that feature low cost, ease of use, and pump-free operations. In this paper, we report a deep learning-assisted smartphone platform for ultra-accurate testing of paper-based microfluidic colorimetric enzyme-linked immunosorbent assay (c-ELISA). Different from existing smartphone-based μPAD platforms, whose sensing reliability is suffered from uncontrolled ambient lighting conditions, our platform is able to eliminate those random lighting influences for enhanced sensing accuracy. We first constructed a dataset that contains c-ELISA results (n = 2048) of rabbit IgG as the model target on μPADs under eight controlled lighting conditions. Those images are then used to train four different mainstream deep learning algorithms. By training with these images, the deep learning algorithms can well eliminate the influences of lighting conditions. Among them, the GoogLeNet algorithm gives the highest accuracy (>97%) in quantitative rabbit IgG concentration classification/prediction, which also provides 4% higher area under curve (AUC) value than that of the traditional curve fitting results analysis method. In addition, we fully automate the whole sensing process and achieve the "image in, answer out" to maximize the convenience of the smartphone. A simple and user-friendly smartphone application has been developed that controls the whole process. This newly developed platform further enhances the sensing performance of μPADs for use by laypersons in low-resource areas and can be facilely adapted to the real disease protein biomarkers detection by c-ELISA on μPADs.

Microfluidic Device for Patient-Centric Multiplexed Assays with Readout in Centralized Laboratories

Patient-centric sampling strategies, where the patient performs self-sampling and ships the sample to a centralized laboratory for readout, are on the verge of widespread adaptation. However, the key to a successful patient-centric workflow is user-friendliness, with few noncritical user interactions, and simple, ideally biohazard-free shipment. Here, we present a capillary-driven microfluidic device designed to perform the critical biomarker capturing step of a multiplexed immunoassay at the time of sample collection. On-chip sample drying enables biohazard-free shipment and allows us to make use of advanced analytics of specialized laboratories that offer the needed analytical sensitivity, reliability, and affordability. Using C-Reactive Protein, MCP1, S100B, IGFBP1, and IL6 as model blood biomarkers, we demonstrate the multiplexing capability and applicability of the device to a patient-centric workflow. The presented quantification of a biomarker panel opens up new possibilities for e-doctor and e-health applications.

Approaches for assessing performance of high-resolution mass spectrometry-based non-targeted analysis methods

Non-targeted analysis (NTA) using high-resolution mass spectrometry has enabled the detection and identification of unknown and unexpected compounds of interest in a wide range of sample matrices. Despite these benefits of NTA methods, standardized procedures do not yet exist for assessing performance, limiting stakeholders’ abilities to suitably interpret and utilize NTA results. Herein, we first summarize existing performance assessment metrics for targeted analyses to provide context and clarify terminology that may be shared between targeted and NTA methods (e.g., terms such as accuracy, precision, sensitivity, and selectivity). We then discuss promising approaches for assessing NTA method performance, listing strengths and key caveats for each approach, and highlighting areas in need of further development. To structure the discussion, we define three types of NTA study objectives: sample classification, chemical identification, and chemical quantitation. Qualitative study performance (i.e., focusing on sample classification and/or chemical identification) can be assessed using the traditional confusion matrix, with some challenges and limitations. Quantitative study performance can be assessed using estimation procedures developed for targeted methods with consideration for additional sources of uncontrolled experimental error. This article is intended to stimulate discussion and further efforts to develop and improve procedures for assessing NTA method performance. Ultimately, improved performance assessments will enable accurate communication and effective utilization of NTA results by stakeholders.

Global seroprevalence and sociodemographic characteristics of Borrelia burgdorferi sensu lato in human populations: a systematic review and meta-analysis

Introduction

Borrelia burgdorferi sensu lato (Bb) infection, the most frequent tick-transmitted disease, is distributed worldwide. This study aimed to describe the global seroprevalence and sociodemographic characteristics of Bb in human populations.

Methods

We searched PubMed, Embase, Web of Science and other sources for relevant studies of all study designs through 30 December 2021 with the following keywords: ‘Borrelia burgdorferi sensu lato’ AND ‘infection rate’; and observational studies were included if the results of human Bb antibody seroprevalence surveys were reported, the laboratory serological detection method reported and be published in a peer-reviewed journal. We screened titles/abstracts and full texts of papers and appraised the risk of bias using the Cochrane Collaboration-endorsed Newcastle-Ottawa Quality Assessment Scale. Data were synthesised narratively, stratified by different types of outcomes. We also conducted random effects meta-analysis where we had a minimum of two studies with 95% CIs reported. The study protocol has been registered with PROSPERO (CRD42021261362).

Results

Of 4196 studies, 137 were eligible for full-text screening, and 89 (158 287 individuals) were included in meta-analyses. The reported estimated global Bb seroprevalence was 14.5% (95% CI 12.8% to 16.3%), and the top three regions of Bb seroprevalence were Central Europe (20.7%, 95% CI 13.8% to 28.6%), Eastern Asia (15.9%, 95% CI 6.6% to 28.3%) and Western Europe (13.5%, 95% CI 9.5% to 18.0%). Meta-regression analysis showed that after eliminating confounding risk factors, the methods lacked western blotting (WB) confirmation and increased the risk of false-positive Bb antibody detection compared with the methods using WB confirmation (OR 1.9, 95% CI 1.6 to 2.2). Other factors associated with Bb seropositivity include age ≥50 years (12.6%, 95% CI 8.0% to 18.1%), men (7.8%, 95% CI 4.6% to 11.9%), residence of rural area (8.4%, 95% CI 5.0% to 12.6%) and suffering tick bites (18.8%, 95% CI 10.1% to 29.4%).

Conclusion

The reported estimated global Bb seropositivity is relatively high, with the top three regions as Central Europe, Western Europe and Eastern Asia. Using the WB to confirm Bb serological results could significantly improve the accuracy. More studies are needed to improve the accuracy of global Lyme borreliosis burden estimates.

PROSPERO registration number

CRD42021261362.

Innovations in infectious disease testing: Leveraging COVID-19 pandemic technologies for the future

Innovations in infectious disease testing have improved our abilities to detect and understand the microbial world. The 2019 novel coronavirus infectious disease (COVID-19) pandemic introduced new innovations including non-prescription “over the counter” infectious disease tests, mass spectrometry-based detection of COVID-19 host response, and the implementation of artificial intelligence (AI) and machine learning (ML) to identify individuals infected by the severe acute respiratory syndrome - coronavirus – 2 (SARS-CoV-2). As the world recovers from the COVID-19 pandemic; these innovative solutions will give rise to a new era of infectious disease tests extending beyond the detection of SARS-CoV-2. To this end, the purpose of this review is to summarize current trends in infectious disease testing and discuss innovative applications specifically in the areas of POC testing, MS, molecular diagnostics, sample types, and AI/ML.

Monitoring gestational diabetes at the point-of-care via dual glycated albumin lateral flow assays in conjunction with a handheld reader

A dual assay cartridge was developed and used in conjunction with a handheld reader for sensing % glycated albumin to monitor gestational diabetes at home.

Evolving Applications of Artificial Intelligence and Machine Learning in Infectious Diseases Testing

Background

Artificial intelligence (AI) and machine learning (ML) are poised to transform infectious disease testing. Uniquely, infectious disease testing is technologically diverse spaces in laboratory medicine, where multiple platforms and approaches may be required to support clinical decision-making. Despite advances in laboratory informatics, the vast array of infectious disease data is constrained by human analytical limitations. Machine learning can exploit multiple data streams, including but not limited to laboratory information and overcome human limitations to provide physicians with predictive and actionable results. As a quickly evolving area of computer science, laboratory professionals should become aware of AI/ML applications for infectious disease testing as more platforms are become commercially available.

Content

In this review we: (a) define both AI/ML, (b) provide an overview of common ML approaches used in laboratory medicine, (c) describe the current AI/ML landscape as it relates infectious disease testing, and (d) discuss the future evolution AI/ML for infectious disease testing in both laboratory and point-of-care applications.

Summary

The review provides an important educational overview of AI/ML technique in the context of infectious disease testing. This includes supervised ML approaches, which are frequently used in laboratory medicine applications including infectious diseases, such as COVID-19, sepsis, hepatitis, malaria, meningitis, Lyme disease, and tuberculosis. We also apply the concept of “data fusion” describing the future of laboratory testing where multiple data streams are integrated by AI/ML to provide actionable clinical knowledge.

Light People: Professor Aydogan Ozcan

In 2016, the news that Google's artificial intelligence (AI) robot AlphaGo, based on the principle of deep learning, won the victory over lee Sedol, the former world Go champion and the famous 9th Dan competitor of Korea, caused a sensation in both fields of AI and Go, which brought epoch-making significance to the development of deep learning. Deep learning is a complex machine learning algorithm that uses multiple layers of artificial neural networks to automatically analyze signals or data. At present, deep learning has penetrated into our daily life, such as the applications of face recognition and speech recognition. Scientists have also made many remarkable achievements based on deep learning. Professor Aydogan Ozcan from the University of California, Los Angeles (UCLA) led his team to research deep learning algorithms, which provided new ideas for the exploring of optical computational imaging and sensing technology, and introduced image generation and reconstruction methods which brought major technological innovations to the development of related fields. Optical designs and devices are moving from being physically driven to being data-driven. We are much honored to have Aydogan Ozcan, Fellow of the National Academy of Inventors and Chancellor's Professor of UCLA, to unscramble his latest scientific research results and foresight for the future development of related fields, and to share his journey of pursuing Optics, his indissoluble relationship with Light: Science & Applications (LSA), and his experience in talent cultivation.

Nanotechnology for modern medicine: next step towards clinical translation

The field of nanotechnology has been a significant research focus in the last thirty years. This emphasis is due to the unique optical, electrical, magnetic, chemical and biological properties of materials approximately ten thousand times smaller than the diameter of a hair strand. Researchers have developed methods to synthesize and characterize large libraries of nanomaterials and have demonstrated their preclinical utility. We have entered a new phase of nanomedicine development, where the focus is to translate these technologies to benefit patients. This review article provides an overview of nanomedicine's unique properties, the current state of the field, and discusses the challenge of clinical translation. Finally, we discuss the need to build and strengthen partnerships between engineers and clinicians to create a feedback loop between the bench and bedside. This partnership will guide fundamental studies on the nanoparticle-biological interactions, address clinical challenges and change the development and evaluation of new drug delivery systems, sensors, imaging agents and therapeutic systems.

Recent Progress in Lyme Disease and Remaining Challenges

Lyme disease (also known as Lyme borreliosis) is the most common vector-borne disease in the United States with an estimated 476,000 cases per year. While historically, the long-term impact of Lyme disease on patients has been controversial, mounting evidence supports the idea that a substantial number of patients experience persistent symptoms following treatment. The research community has largely lacked the necessary funding to properly advance the scientific and clinical understanding of the disease, or to develop and evaluate innovative approaches for prevention, diagnosis, and treatment. Given the many outstanding questions raised into the diagnosis, clinical presentation and treatment of Lyme disease, and the underlying molecular mechanisms that trigger persistent disease, there is an urgent need for more support. This review article summarizes progress over the past 5 years in our understanding of Lyme and tick-borne diseases in the United States and highlights remaining challenges.

Serologic response to Borrelia antigens varies with clinical phenotype in children and young adults with Lyme disease

Lyme disease is commonly diagnosed by serologic response to Borrelia burgdorferi and related species, but the relationship between serologic targets and clinical features is unknown. We developed a multi-antigen Luminex-based panel and evaluated IgG responses in 527 children 1 to 21 years of age assessed for Lyme disease across 4 Pedi Lyme Net emergency departments, including 127 Lyme cases defined by either an erythema migrans (EM) lesion or positive C6 enzyme immunoassay followed by immunoblot and 400 patients considered clinical mimics. Of 42 antigens tested, 26 elicited specific reactivity in Lyme patients, without marked age-dependent variation. Children with single EM lesions typically lacked Borrelia-specific IgG. By principal component analysis, children with early disseminated and late Lyme disease clustered separately from clinical mimics and also from each other. Neurological disease and arthritis exhibited distinct serologic responses, with OspC variants overrepresented in neurological disease and p100, BmpA, p58 and p45 overrepresented in arthritis. Machine learning identified a 3-antigen panel (VlsE_Bb, p41_Bb, OspC_Bafz) that distinguished Lyme disease from clinical mimics with a sensitivity of 86.6% (95% confidence interval [CI] 80.3-92.1) and a specificity of 95.5% (95% CI 93.4-97.4). Sensitivity was much lower in early Lyme disease (38.5%, 95% CI 15.4-69.2). Interestingly, 17 children classified as Lyme mimics had a positive 3-antigen panel, suggesting that more comprehensive serologic analysis could help refine Lyme diagnosis. In conclusion, multiplex antigen panels provide a novel approach to understanding the immune response in Lyme disease, potentially helping to facilitate accurate diagnosis and to understand differences between clinical stages.

Epitope mapping from Mycobacterium leprae proteins: Convergent data from in silico and in vitro approaches for serodiagnosis of leprosy

Knowledge of immunodominant B-cell epitopes is essential to design powerful diagnostic strategies aiming for antibody detection. Outstanding progress in computational prediction has achieved a significant contribution to the biomedical fields, including immunodiagnosis. In silico analysis may have an even more important role when information concerning antigens from etiologic agents of neglected diseases, such as leprosy, is scarce. The aim of this study was to provide mapping of B-cell epitopes from two Mycobacterium leprae-derived antigens (Ag85B and ML2055), confirm their antigenicity, and to assess the ability of in silico immunoinformatics tools to accurately predict them. Linear B-cell epitopes predicted by ABCpred and SVMTrip servers were compared to antigenic regions of synthetic overlapping peptides that exhibited reactivity to antibodies from patients with leprosy. Our in vitro results identified several immunodominant regions that had also been indicated by in silico prediction, providing agreement between experimental and simulated data. After chemical synthesis, we used enzyme-linked immunosorbent assays to determine the effectiveness of the first identified sequence (GTNVPAEFLENFVHG) which had 72 % sensitivity and 78 % specificity (AUC = 0.79) while the second one (PVSSEAQPGDPNAPS) had 72 % sensitivity and 93.8 % specificity (AUC = 0.85). Using dot blotting, an easy-to-read visual test, both peptides could distinguish sera from patients with leprosy from those with tuberculosis and from sera of healthy volunteers. Our findings suggest that these synthetic peptides, with some refinement, may be useful as serological diagnostic antigens for leprosy. In addition, it was displayed that immunoinformatics provides reliable information for mapping potential B-cell epitopes for development of peptide-based diagnostic assays for neglected diseases.

Recent progress in plasmonic nanoparticle-based biomarker detection and cytometry for the study of central nervous system disorders

Neurological disorders affect hundreds of millions of people around the world, are often life-threatening, untreatable, and can result in debilitating symptoms. The high prevalence of these disorders, which feature biochemical or structural abnormalities in neuronal systems, has spurned innovations in both rapid and early detection to assist in the selection of appropriate treatment strategies to improve the patients' quality of life. Plasmonic nanoparticles (PNPs), a versatile and promising class of nanomaterials, are widely utilized in numerous imaging techniques, drug delivery systems, and biomarker detection methods. Recently, PNP-based nanoprobes have attracted considerable attention for the early diagnosis of neurological disorders. Gold nanoparticles (AuNPs), with high local surface plasmon resonance (LSPR) signals, have been particularly well exploited as probes for dynamic biomarker detection, with quantification sensitivity demonstrated down to the single-molecule level. In this review, we will discuss the possibilities of PNPs in the methodological development for rapid neurological disease identification. In addition, we will also describe a new digital cytometry method that combines dark-field imaging and machine learning for precise biomarker enumeration on single cells. The aim of this review is to attract researchers working on the future development of new plasmonic nanoprobe-based strategies for the diagnosis of neurological disorders.

Comparative Cost and Effectiveness of a New Algorithm for Early Lyme Disease Diagnosis: Evaluation in US, Germany, and Italy

Purpose

This Lyme disease early detection economic model, for patients with suspected Lyme disease without erythema migrans (EM), compares outcomes of standard two-tier testing (sTTT), modified two-tier testing (mTTT) and the DiaSorin Lyme Detection Algorithm (LDA), a combination of both serology tests and Interferon-ɤ Release Assay.

Patients and Methods

A patient-level simulation model was built to incorporate effectiveness estimation from a structured focused literature review, and health-care cost inputs for the United States, Germany, and Italy. Simulated clinical outcomes were 1) percent of patients with timely and correct diagnosis, 2) patients appropriately treated and exposed to antibiotics therapy, and 3) patients with late Lyme disease manifestations. Expected health outcomes were expressed in terms of differences in quality-adjusted life years (QALYs) due to disseminated Lyme disease and persisting symptoms, and economic outcomes were analyzed from a third-party payer perspective.

Results

The DiaSorin LDA resulted in a better sensitivity compared to sTTT and mTTT, 84% vs 49% and 45%, respectively, in the base case (13% of infected patients in the tested population). Due to the improved diagnostic performance, the LDA-based strategy is expected to be more effective, providing mean incremental 0.024 QALYs per tested patient, or 0.19 per infected patient. Furthermore, from a third-party payer perspective, the adoption of the LDA-based strategy would reduce the expected health-care cost for suspected and confirmed Lyme disease by roughly 40%, ie about $410, €130, and €170 per tested patient in the United States, Germany, and Italy, respectively, compared to sTTT. The results are most sensitive to the infection rate in the tested population, with LDA maintaining a cost advantage for Lyme disease active infection rates ≥0.8-2.5%.

Conclusion

LDA early diagnostic testing and subsequent treatment of subjects with early Lyme disease without EM are expected to outperform traditional management strategies both clinically and economically in the US, Germany, and Italy.

Point-of-care detection of cytokines in cytokine storm management and beyond: Significance and challenges

Cytokines are signaling molecules between cells in immune system. Cytokine storm, due to the sudden acute increase in levels of pro‐inflammatory circulating cytokines, can result in disease severity and major‐organ damage. Thus, there is urgent need to develop rapid, sensitive, and specific methods for monitoring of cytokines in biology and medicine. Undoubtedly, point‐of‐care testing (POCT) will provide clinical significance in disease early diagnosis, management, and prevention. This review aims to summarize and discuss the latest technologies for detection of cytokines with a focus on POCT. The overview of diseases resulting from imbalanced cytokine levels, such as COVID‐19, sepsis and other cytokine release syndromes are presented. The clinical cut‐off levels of cytokine as biomarkers for different diseases are summarized. The challenges and perspectives on the development of cytokine POCT devices are also proposed and discussed. Cytokine POCT devices are expected to be the ongoing spotlight of disease management and prevention during COVID‐19 pandemic and also the post COVID‐19 pandemic era.

Point-of-care diagnostics for infectious diseases: From methods to devices

The current widespread of COVID-19 all over the world, which is caused by SARS-CoV-2 virus, has again emphasized the importance of development of point-of-care (POC) diagnostics for timely prevention and control of the pandemic. Compared with labor- and time-consuming traditional diagnostic methods, POC diagnostics exhibit several advantages such as faster diagnostic speed, better sensitivity and specificity, lower cost, higher efficiency and ability of on-site detection. To achieve POC diagnostics, developing POC detection methods and correlated POC devices is the key and should be given top priority. The fast development of microfluidics, micro electro-mechanical systems (MEMS) technology, nanotechnology and materials science, have benefited the production of a series of portable, miniaturized, low cost and highly integrated POC devices for POC diagnostics of various infectious diseases. In this review, various POC detection methods for the diagnosis of infectious diseases, including electrochemical biosensors, fluorescence biosensors, surface-enhanced Raman scattering (SERS)-based biosensors, colorimetric biosensors, chemiluminiscence biosensors, surface plasmon resonance (SPR)-based biosensors, and magnetic biosensors, were first summarized. Then, recent progresses in the development of POC devices including lab-on-a-chip (LOC) devices, lab-on-a-disc (LOAD) devices, microfluidic paper-based analytical devices (μPADs), lateral flow devices, miniaturized PCR devices, and isothermal nucleic acid amplification (INAA) devices, were systematically discussed. Finally, the challenges and future perspectives for the design and development of POC detection methods and correlated devices were presented. The ultimate goal of this review is to provide new insights and directions for the future development of POC diagnostics for the management of infectious diseases and contribute to the prevention and control of infectious pandemics like COVID-19.

Noninvasive Precision Screening of Prostate Cancer by Urinary Multimarker Sensor and Artificial Intelligence Analysis

Screening for prostate cancer relies on the serum prostate-specific antigen test, which provides a high rate of false positives (80%). This results in a large number of unnecessary biopsies and subsequent overtreatment. Considering the frequency of the test, there is a critical unmet need of precision screening for prostate cancer. Here, we introduced a urinary multimarker biosensor with a capacity to learn to achieve this goal. The correlation of clinical state with the sensing signals from urinary multimarkers was analyzed by two common machine learning algorithms. As the number of biomarkers was increased, both algorithms provided a monotonic increase in screening performance. Under the best combination of biomarkers, the machine learning algorithms screened prostate cancer patients with more than 99% accuracy using 76 urine specimens. Urinary multimarker biosensor leveraged by machine learning analysis can be an important strategy of precision screening for cancers using a drop of bodily fluid.

From Diagnosis to Treatment: Recent Advances in Patient-Friendly Biosensors and Implantable Devices

Patient-friendly medical diagnostics and treatments have been receiving a great deal of interest due to their rapid and cost-effective health care applications with minimized risk of infection, which has the potential to replace conventional hospital-based medical procedures. In particular, the integration of recently developed materials into health care devices allows the rapid development of point-of-care (POC) sensing platforms and implantable devices with special functionalities. In this review, the recent advances in biosensors for patient-friendly diagnosis and implantable devices for patient-friendly treatment are discussed. Comprehensive analysis of portable and wearable biosensing platforms for patient-friendly health monitoring and disease diagnosis is provided, including topics such as materials selection, device structure and integration, and biomarker detection strategies. Moreover, specific challenges related to each biological fluid for wearable biosensor-based POC applications are presented. Also, advances in implantable devices, including recent materials development and wireless communication strategies, are discussed. Furthermore, various patient-friendly surgical and treatment approaches are reviewed, such as minimally invasive insertion and mounting, in vivo electrical and optical modulations, and post-operation health monitoring. Finally, the challenges and future perspectives toward the development of the patient-friendly diagnosis and treatment are provided.

Deep Learning for Biospectroscopy and Biospectral Imaging: State-of-the-Art and Perspectives

With the advances in instrumentation and sampling techniques, there is an explosive growth of data from molecular and cellular samples. The call to extract more information from the large data sets has greatly challenged the conventional chemometrics method. Deep learning, which utilizes very large data sets for finding hidden features therein and for making accurate predictions for a wide range of applications, has been applied in an unbelievable pace in biospectroscopy and biospectral imaging in the recent 3 years. In this Feature, we first introduce the background and basic knowledge of deep learning. We then focus on the emerging applications of deep learning in the data preprocessing, feature detection, and modeling of the biological samples for spectral analysis and spectroscopic imaging. Finally, we highlight the challenges and limitations in deep learning and the outlook for future directions.

Kaleidoscopic fluorescent arrays for machine-learning-based point-of-care chemical sensing

Multiplexed analysis allows simultaneous measurements of multiple targets, improving the detection sensitivity and accuracy. However, highly multiplexed analysis has been challenging for point-of-care (POC) sensing, which requires a simple, portable, robust, and affordable detection system. In this work, we developed paper-based POC sensing arrays consisting of kaleidoscopic fluorescent compounds. Using an indolizine structure as a fluorescent core skeleton, named Kaleidolizine (KIz), a library of 75 different fluorescent KIz derivatives were designed and synthesized. These KIz derivatives are simultaneously excited by a single ultraviolet (UV) light source and emit diverse fluorescence colors and intensities. For multiplexed POC sensing system, fluorescent compounds array on cellulose paper was prepared and the pattern of fluorescence changes of KIz on array were specific to target chemicals adsorbed on that paper. Furthermore, we developed a machine-learning algorithm for automated, rapid analysis of color and intensity changes of individual sensing arrays. We showed that the paper sensor arrays could differentiate 35 different volatile organic compounds using a smartphone-based handheld detection system. Powered by the custom-developed machine-learning algorithm, we achieved the detection accuracy of 97% in the VOC detection. The highly multiplexed paper sensor could have favorable applications for monitoring a broad-range of environmental toxins, heavy metals, explosives, pathogens.

Decoding Optical Data with Machine Learning

Optical spectroscopy and imaging techniques play important roles in many fields such as disease diagnosis, biological study, information technology, optical science, and materials science. Over the past decade, machine learning (ML) has proved promising in decoding complex data, enabling rapid and accurate analysis of optical spectra and images. This review aims to shed light on various ML algorithms for optical data analysis with a focus on their applications in a wide range of fields. The goal of this work is to sketch the validity of ML-based optical data decoding. The review concludes with an outlook on unaddressed problems and opportunities in this emerging subject that interfaces optics, data science and ML.

Laboratory Diagnosis of Lyme Borreliosis

Lyme borreliosis is caused by a growing list of related, yet distinct, spirochetes with complex biology and sophisticated immune evasion mechanisms. It may result in a range of clinical manifestations involving different organ systems, and can lead to persistent sequelae in a subset of cases. The pathogenesis of Lyme borreliosis is incompletely understood, and laboratory diagnosis, the focus of this review, requires considerable understanding to interpret the results correctly. Direct detection of the infectious agent is usually not possible or practical, necessitating a continued reliance on serologic testing. Still, some important advances have been made in the area of diagnostics, and there are many promising ideas for future assay development. This review summarizes the state of the art in laboratory diagnostics for Lyme borreliosis, provides guidance in test selection and interpretation, and highlights future directions.

Terahertz pulse shaping using diffractive surfaces

Recent advances in deep learning have been providing non-intuitive solutions to various inverse problems in optics. At the intersection of machine learning and optics, diffractive networks merge wave-optics with deep learning to design task-specific elements to all-optically perform various tasks such as object classification and machine vision. Here, we present a diffractive network, which is used to shape an arbitrary broadband pulse into a desired optical waveform, forming a compact and passive pulse engineering system. We demonstrate the synthesis of various different pulses by designing diffractive layers that collectively engineer the temporal waveform of an input terahertz pulse. Our results demonstrate direct pulse shaping in terahertz spectrum, where the amplitude and phase of the input wavelengths are independently controlled through a passive diffractive device, without the need for an external pump. Furthermore, a physical transfer learning approach is presented to illustrate pulse-width tunability by replacing part of an existing network with newly trained diffractive layers, demonstrating its modularity. This learning-based diffractive pulse engineering framework can find broad applications in e.g., communications, ultra-fast imaging and spectroscopy.

Machine learning-enabled multiplexed microfluidic sensors

High-throughput, cost-effective, and portable devices can enhance the performance of point-of-care tests. Such devices are able to acquire images from samples at a high rate in combination with microfluidic chips in point-of-care applications. However, interpreting and analyzing the large amount of acquired data is not only a labor-intensive and time-consuming process, but also prone to the bias of the user and low accuracy. Integrating machine learning (ML) with the image acquisition capability of smartphones as well as increasing computing power could address the need for high-throughput, accurate, and automatized detection, data processing, and quantification of results. Here, ML-supported diagnostic technologies are presented. These technologies include quantification of colorimetric tests, classification of biological samples (cells and sperms), soft sensors, assay type detection, and recognition of the fluid properties. Challenges regarding the implementation of ML methods, including the required number of data points, image acquisition prerequisites, and execution of data-limited experiments are also discussed.

Lyme Disease Biosensors: A Potential Solution to a Diagnostic Dilemma

Over the past four decades, Lyme disease has remained a virulent and pervasive illness, persisting throughout North America and many other regions of the world. Recent increases in illness in many countries has sparked a renewed interest in improved Lyme diagnostics. While current standards of diagnosis are acceptable for the late stages of the disease, it remains difficult to accurately diagnose early forms of the illness. In addition, current diagnostic methods tend to be relatively expensive and require a large degree of laboratory-based analysis. Biosensors represent the fusion of biological materials with chemical techniques to provide simple, inexpensive alternatives to traditional diagnostic methods. Lyme disease biosensors have the potential to better diagnose early stages of the illness and provide possible patients with an inexpensive, commercially available test. This review examines the current state of Lyme disease biosensing, with a focus on previous biosensor development and essential future considerations.

Deep learning-enabled point-of-care sensing using multiplexed paper-based sensors

We present a deep learning-based framework to design and quantify point-of-care sensors. As a use-case, we demonstrated a low-cost and rapid paper-based vertical flow assay (VFA) for high sensitivity C-Reactive Protein (hsCRP) testing, commonly used for assessing risk of cardio-vascular disease (CVD). A machine learning-based framework was developed to (1) determine an optimal configuration of immunoreaction spots and conditions, spatially-multiplexed on a sensing membrane, and (2) to accurately infer target analyte concentration. Using a custom-designed handheld VFA reader, a clinical study with 85 human samples showed a competitive coefficient-of-variation of 11.2% and linearity of R 2 = 0.95 among blindly-tested VFAs in the hsCRP range (i.e., 0-10 mg/L). We also demonstrated a mitigation of the hook-effect due to the multiplexed immunoreactions on the sensing membrane. This paper-based computational VFA could expand access to CVD testing, and the presented framework can be broadly used to design cost-effective and mobile point-of-care sensors.