Deep learning of HIV field-based rapid tests

Latex microspheres lateral flow immunoassay with smartphone-based device for rapid detection of Cryptococcus

Cryptococcus is a pathogenic fungus that poses a threat to human health. Conventional detection methods have limited the rapid and accurate qualitative and quantitative analysis of Cryptococcus, affecting early diagnosis and treatment. In this study, we developed a Point-of-Care Testing (POCT) platform that integrates lateral flow immunoassay (LFIA) with smartphones, enabling both rapid qualitative and quantitative detection of Cryptococcus. The LFIA strip utilizes latex microspheres (LMs) as labeling probes, achieving a detection limit of 3000 CFU/mL and presenting higher sensitivity than the Colloidal Gold Nanoparticles Lateral Flow Immunoassay (AuNPs-LFIA) strip, and approximately eight times that of the AuNPs-LFIA strip. Additionally, it exhibiting no cross-reactivity with over 24 common pathogens and validated in clinical samples. For quantitative analysis, artificial intelligence algorithms were employed to convert smartphone-captured images into grayscale values. Eleven feature values were utilized as a dataset for machine learning to construct a linear regression model, with Mean Squared Error (MSE) and R2 reaching 0.45 and 0.91, respectively. Moreover, the recovery rates in the serum samples ranged from 90.0 % to 108 %, indicating a good practicability. This research presents a rapid diagnostic technology for Cryptococcus and lays the theoretical and technical groundwork for detecting other pathogens.

Efficacy of the mLab App: a randomized clinical trial for increasing HIV testing uptake using mobile technology

OBJECTIVE

To determine the efficacy of the mLab App, a mobile-delivered HIV prevention intervention to increase HIV self-testing in MSM and TGW.

MATERIALS AND METHODS

This was a randomized (2:2:1) clinical trial of the efficacy the mLab App as compared to standard of care vs mailed home HIV test arm among 525 MSM and TGW aged 18-29 years to increase HIV testing.

RESULTS

The mLab App arm participants demonstrated an increase from 35.1% reporting HIV testing in the prior 6 months compared to 88.5% at 6 months. In contrast, 28.8% of control participants reported an HIV test at baseline, which only increased to 65.1% at 6 months. In a generalized linear mixed model estimating this change and controlling for multiple observations of participants, this equated to control participants reporting a 61.2% smaller increase in HIV testing relative to mLab participants (P = .001) at 6 months. This difference was maintained at 12 months with control participants reporting an 82.6% smaller increase relative to mLab App participants (P < .001) from baseline to 12 months.

DISCUSSION AND CONCLUSION

Findings suggest that the mLab App is well-supported, evidence-based, behavioral risk-reduction intervention for increasing HIV testing rates as compared to the standard of care, suggesting that this may be a useful behavioral risk-reduction intervention for increasing HIV testing among young MSM.

TRIAL REGISTRATION

This trial was registered with Clinicaltrials.gov NCT03803683.

Microfluidic platforms for monitoring cardiomyocyte electromechanical activity

Cardiovascular diseases account for ~40% of global deaths annually. This situation has revealed the urgent need for the investigation and development of corresponding drugs for pathogenesis due to the complexity of research methods and detection techniques. An in vitro cardiomyocyte model is commonly used for cardiac drug screening and disease modeling since it can respond to microphysiological environmental variations through mechanoelectric feedback. Microfluidic platforms are capable of accurate fluid control and integration with analysis and detection techniques. Therefore, various microfluidic platforms (i.e., heart-on-a-chip) have been applied for the reconstruction of the physiological environment and detection of signals from cardiomyocytes. They have demonstrated advantages in mimicking the cardiovascular structure and function in vitro and in monitoring electromechanical signals. This review presents a summary of the methods and technologies used to monitor the contractility and electrophysiological signals of cardiomyocytes within microfluidic platforms. Then, applications in common cardiac drug screening and cardiovascular disease modeling are presented, followed by design strategies for enhancing physiology studies. Finally, we discuss prospects in the tissue engineering and sensing techniques of microfluidic platforms.

Updated Appropriate Use Criteria for Amyloid and Tau PET: A Report from the Alzheimer's Association and Society for Nuclear Medicine and Molecular Imaging Workgroup

The Alzheimer's Association and the Society of Nuclear Medicine and Molecular Imaging convened a multidisciplinary workgroup to update appropriate use criteria (AUC) for amyloid positron emission tomography (PET) and to develop AUC for tau PET. Methods: The workgroup identified key research questions that guided a systematic literature review on clinical amyloid/tau PET. Building on this review, the workgroup developed 17 clinical scenarios in which amyloid or tau PET may be considered. A modified Delphi approach was used to rate each scenario by consensus as "rarely appropriate," "uncertain," or "appropriate." Ratings were performed separately for amyloid and tau PET as stand-alone modalities. Results: For amyloid PET, 7 scenarios were rated as appropriate, 2 as uncertain, and 8 as rarely appropriate. For tau PET, 5 scenarios were rated as appropriate, 6 as uncertain, and 6 as rarely appropriate. Conclusion: AUC for amyloid and tau PET provide expert recommendations for clinical use of these technologies in the evolving landscape of diagnostics and therapeutics for Alzheimer's disease.

Rapid and automated interpretation of CRISPR-Cas13-based lateral flow assay test results using machine learning

CRISPR-Cas-based lateral flow assays (LFAs) have emerged as a promising diagnostic tool for ultrasensitive detection of nucleic acids, offering improved speed, simplicity and cost-effectiveness compared to polymerase chain reaction (PCR)-based assays. However, visual interpretation of CRISPR-Cas-based LFA test results is prone to human error, potentially leading to false-positive or false-negative outcomes when analyzing test/control lines. To address this limitation, we have developed two neural network models: one based on a fully convolutional neural network and the other on a lightweight mobile-optimized neural network for automated interpretation of CRISPR-Cas-based LFA test results. To demonstrate proof of concept, these models were applied to interpret results from a CRISPR-Cas13-based LFA for the detection of the SARS-CoV-2 N gene, a key marker for COVID-19 infection. The models were trained, evaluated, and validated using smartphone-captured images of LFA devices in various orientations with different backgrounds, lighting conditions, and image qualities. A total of 3146 images (1569 negative, 1577 positive) captured using an iPhone 13 or Samsung Galaxy A52 Android smartphone were analyzed using the trained models, which classified the LFA results within 0.2 s with 96.5% accuracy compared to the ground truth. These results demonstrate the potential of machine learning to accurately interpret test results of CRISPR-Cas-based LFAs using smartphone-captured images in real-world settings, enabling the practical use of CRISPR-Cas-based diagnostic tools for self- and at-home testing.

HIV-1 M group subtype classification using deep learning approach

Traditionally, the classification of HIV-1 M group subtypes has depended on statistical methods constrained by sample sizes. Here HIV-1-M-SPBEnv was proposed as the first deep learning-based method for classifying HIV-1 M group subtypes via env gene sequences. This approach overcomes sample size challenges by utilizing artificial molecular evolution techniques to generate a synthetic dataset suitable for machine learning. Employing a convolutional Autoencoder embedded with two residual blocks and two transpose residual blocks, followed by a full connected neural network block, HIV-1-M-SPBEnv simplifies complex, high-dimensional DNA sequence data into concise, information-rich, low-dimensional representations, achieving exceptional classification accuracy. Through independent data set validation, the precision, accuracy, recall and F1 score of the HIV-1-M-SPBEnv model predictions were all 100 %, confirming its capability to accurately identify all 12 subtypes of the HIV-1 M group. Deployed through a web server, it provides seamless HIV-1 M group subtype prediction capabilities for researchers and clinicians. HIV-1-M-SPBEnv web server is accessible at http://www.hivsubclass.com and all the code is available at https://github.com/pengsihua2023/HIV-1-M-SPBEnv.

Role of Machine Learning Assisted Biosensors in Point-of-Care-Testing For Clinical Decisions

Point-of-Care-Testing (PoCT) has emerged as an essential component of modern healthcare, providing rapid, low-cost, and simple diagnostic options. The integration of Machine Learning (ML) into biosensors has ushered in a new era of innovation in the field of PoCT. This article investigates the numerous uses and transformational possibilities of ML in improving biosensors for PoCT. ML algorithms, which are capable of processing and interpreting complicated biological data, have transformed the accuracy, sensitivity, and speed of diagnostic procedures in a variety of healthcare contexts. This review explores the multifaceted applications of ML models, including classification and regression, displaying how they contribute to improving the diagnostic capabilities of biosensors. The roles of ML-assisted electrochemical sensors, lab-on-a-chip sensors, electrochemiluminescence/chemiluminescence sensors, colorimetric sensors, and wearable sensors in diagnosis are explained in detail. Given the increasingly important role of ML in biosensors for PoCT, this study serves as a valuable reference for researchers, clinicians, and policymakers interested in understanding the emerging landscape of ML in point-of-care diagnostics.

The global geography of artificial intelligence in life science research

Artificial intelligence (AI) promises to transform medicine, but the geographic concentration of AI expertize may hinder its equitable application. We analyze 397,967 AI life science research publications from 2000 to 2022 and 14.5 million associated citations, creating a global atlas that distinguishes productivity (i.e., publications), quality-adjusted productivity (i.e., publications stratified by field-normalized rankings of publishing outlets), and relevance (i.e., citations). While Asia leads in total publications, Northern America and Europe contribute most of the AI research appearing in high-ranking outlets, generating up to 50% more citations than other regions. At the global level, international collaborations produce more impactful research, but have stagnated relative to national research efforts. Our findings suggest that greater integration of global expertize could help AI deliver on its promise and contribute to better global health.

High-Throughput and Integrated CRISPR/Cas12a-Based Molecular Diagnosis Using a Deep Learning Enabled Microfluidic System

CRISPR/Cas-based molecular diagnosis demonstrates potent potential for sensitive and rapid pathogen detection, notably in SARS-CoV-2 diagnosis and mutation tracking. Yet, a major hurdle hindering widespread practical use is its restricted throughput, limited integration, and complex reagent preparation. Here, a system, microfluidic multiplate-based ultrahigh throughput analysis of SARS-CoV-2 variants of concern using CRISPR/Cas12a and nonextraction RT-LAMP (mutaSCAN), is proposed for rapid detection of SARS-CoV-2 and its variants with limited resource requirements. With the aid of the self-developed reagents and deep-learning enabled prototype device, our mutaSCAN system can detect SARS-CoV-2 in mock swab samples below 30 min as low as 250 copies/mL with the throughput up to 96 per round. Clinical specimens were tested with this system, the accuracy for routine and mutation testing (22 wildtype samples, 26 mutational samples) was 98% and 100%, respectively. No false-positive results were found for negative (n = 24) samples.

Pixel embedding for grayscale medical image classification

In our paper, we present an extension of text embedding architectures for grayscale medical image classification. We introduce a mechanism that combines n-gram features with an efficient pixel flattening technique to preserve spatial information during feature representation generation. Our approach involves flattening all pixels in grayscale medical images using a combination of column-wise, row-wise, diagonal-wise, and anti-diagonal-wise orders. This ensures that spatial dependencies are captured effectively in the feature representations. To evaluate the effectiveness of our method, we conducted a benchmark using 5 grayscale medical image datasets of varying sizes and complexities. 10-fold cross-validation showed that our approach achieved test accuracy score of 99.92 % on the Medical MNIST dataset, 90.06 % on the Chest X-ray Pneumonia dataset, 96.94 % on the Curated Covid CT dataset, 79.11 % on the MIAS dataset and 93.17 % on the Ultrasound dataset. The framework and reproducible code can be found on GitHub at https://github.com/xizhou/pixel_embedding.

Mobile-linked point-of-care diagnostics in community-based healthcare: a scoping review of user experiences

BACKGROUND

While mobile-linked point-of-care diagnostics may circumvent geographical and temporal barriers to efficient communication, the use of such technology in community settings will depend on user experience. We conducted a scoping review to systematically map evidence on user experiences of mobile-linked point-of-care diagnostics in community healthcare settings published from the year 2016 up to the year 2022.

METHODOLOGY

We conducted a comprehensive search of the following electronic databases: Scopus, Web of Science, and EBSCOhost (Medline, CINAHL, Africa-wide, Academic Search Complete). The inter-reviewer agreement was determined using Cohen's kappa statistic. Data quality was appraised using the mixed method appraisal tool version 2018, and the results were reported according to the preferred reporting items for systematic reviews and meta-analyses for scoping reviews (PRISMA-ScR).

RESULTS

Following the abstract and full article screening, nine articles were found eligible for inclusion in data extraction. Following the quality appraisal, one study scored 72.5%, one study scored 95%, and the remaining seven studies scored 100%. Inter-rater agreement was 83.54% (Kappa statistic = 0.51, p < 0.05). Three themes emerged from the articles: approaches to implementing mobile-linked point-of-care diagnostics, user engagement in community-based healthcare settings, and limited user experiences in mobile-linked point-of-care diagnostics. User experiences are key to the sustainable implementation of mobile-linked point-of-care diagnostics. User experiences have been evaluated in small community healthcare settings. There is limited evidence of research aimed at evaluating the usability of mobile-linked diagnostics at the community level.

CONCLUSION

More studies are needed to assess the user experience of mobile-linked diagnostics in larger communities. This scoping review revealed gaps that need to be addressed to improve user experiences of mobile-linked diagnostics, including language barriers, privacy issues, and clear instructions.

An instrument-free, integrated micro-platform for rapid and multiplexed detection of dairy adulteration in resource-limited environments

In dairy industry, expensive yak's milk, camel's milk, and other specialty dairy products are often adulterated with low-cost cow's milk, goat's milk and so on. Currently, the detection of specialty dairy products typically requires laboratory settings and relies on skilled operators. Therefore, there is an urgent need to develop a multi-detection technology and on-site rapid detection technique to enhance the efficiency and accuracy of the detection of specialty dairy products. In this study, we introduced a fully integrated and portable microfluidic detection platform called Sector Self-Driving Microfluidics (SDM), designed to simultaneously detect eight common species-specific components in milk. SDM integrated nucleic acid extraction, purification, loop-mediated isothermal amplification (LAMP), and lateral flow strip (LFS) detection functions into a closed microfluidic system, enabling contamination-free visual detection. The SDM platform used a constant-temperature heating plate, powered by a mobile battery, eliminated the need for additional power support. The SDM platform achieved nucleic acid enrichment and transfer through magnetic force and liquid flow driven by capillary forces, operating without external pumps. The standalone SDM platform could detect dairy components with as low as 1% content within 1 h. Validation with 35 commercially available samples demonstrated 100% specificity and accuracy compared to the gold standard real-time PCR. The SDM platform provided the dairy industry with an efficient, convenient, and accurate detection tool, enabling rapid on-site testing at production facilities or sales points. This facilitated real-time monitoring of quality issues during the production process, quickly identifying potential risks and preventing substandard products from entering the market.

Measuring the performance of computer vision artificial intelligence to interpret images of HIV self-testing results

Introduction

HIV self-testing (HIVST) is highly sensitive and specific, addresses known barriers to HIV testing (such as stigma), and is recommended by the World Health Organization as a testing option for the delivery of HIV pre-exposure prophylaxis (PrEP). Nevertheless, HIVST remains underutilized as a diagnostic tool in community-based, differentiated HIV service delivery models, possibly due to concerns about result misinterpretation, which could lead to inadvertent onward transmission of HIV, delays in antiretroviral therapy (ART) initiation, and incorrect initiation on PrEP. Ensuring that HIVST results are accurately interpreted for correct clinical decisions will be critical to maximizing HIVST's potential. Early evidence from a few small pilot studies suggests that artificial intelligence (AI) computer vision and machine learning could potentially assist with this task. As part of a broader study that task-shifted HIV testing to a new setting and cadre of healthcare provider (pharmaceutical technologists at private pharmacies) in Kenya, we sought to understand how well AI technology performed at interpreting HIVST results.

Methods

At 20 private pharmacies in Kisumu, Kenya, we offered free blood-based HIVST to clients ≥18 years purchasing products indicative of sexual activity (e.g., condoms). Trained pharmacy providers assisted clients with HIVST (as needed), photographed the completed HIVST, and uploaded the photo to a web-based platform. In real time, each self-test was interpreted independently by the (1) client and (2) pharmacy provider, with the HIVST images subsequently interpreted by (3) an AI algorithm (trained on lab-captured images of HIVST results) and (4) an expert panel of three HIVST readers. Using the expert panel's determination as the ground truth, we calculated the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for HIVST result interpretation for the AI algorithm as well as for pharmacy clients and providers, for comparison.

Results

From March to June 2022, we screened 1,691 pharmacy clients and enrolled 1,500 in the study. All clients completed HIVST. Among 854 clients whose HIVST images were of sufficient quality to be interpretable by the AI algorithm, 63% (540/854) were female, median age was 26 years (interquartile range: 22-31), and 39% (335/855) reported casual sexual partners. The expert panel identified 94.9% (808/854) of HIVST images as HIV-negative, 5.1% (44/854) as HIV-positive, and 0.2% (2/854) as indeterminant. The AI algorithm demonstrated perfect sensitivity (100%), perfect NPV (100%), and 98.8% specificity, and 81.5% PPV (81.5%) due to seven false-positive results. By comparison, pharmacy clients and providers demonstrated lower sensitivity (93.2% and 97.7% respectively) and NPV (99.6% and 99.9% respectively) but perfect specificity (100%) and perfect PPV (100%).

Conclusions

AI computer vision technology shows promise as a tool for providing additional quality assurance of HIV testing, particularly for catching Type II error (false-negative test interpretations) committed by human end-users. We discuss possible use cases for this technology to support differentiated HIV service delivery and identify areas for future research that is needed to assess the potential impacts-both positive and negative-of deploying this technology in real-world HIV service delivery settings.

Computer vision meets microfluidics: a label-free method for high-throughput cell analysis

In this paper, we review the integration of microfluidic chips and computer vision, which has great potential to advance research in the life sciences and biology, particularly in the analysis of cell imaging data. Microfluidic chips enable the generation of large amounts of visual data at the single-cell level, while computer vision techniques can rapidly process and analyze these data to extract valuable information about cellular health and function. One of the key advantages of this integrative approach is that it allows for noninvasive and low-damage cellular characterization, which is important for studying delicate or fragile microbial cells. The use of microfluidic chips provides a highly controlled environment for cell growth and manipulation, minimizes experimental variability and improves the accuracy of data analysis. Computer vision can be used to recognize and analyze target species within heterogeneous microbial populations, which is important for understanding the physiological status of cells in complex biological systems. As hardware and artificial intelligence algorithms continue to improve, computer vision is expected to become an increasingly powerful tool for in situ cell analysis. The use of microelectromechanical devices in combination with microfluidic chips and computer vision could enable the development of label-free, automatic, low-cost, and fast cellular information recognition and the high-throughput analysis of cellular responses to different compounds, for broad applications in fields such as drug discovery, diagnostics, and personalized medicine.

Computational methods applied to syphilis: where are we, and where are we going?

Syphilis is an infectious disease that can be diagnosed and treated cheaply. Despite being a curable condition, the syphilis rate is increasing worldwide. In this sense, computational methods can analyze data and assist managers in formulating new public policies for preventing and controlling sexually transmitted infections (STIs). Computational techniques can integrate knowledge from experiences and, through an inference mechanism, apply conditions to a database that seeks to explain data behavior. This systematic review analyzed studies that use computational methods to establish or improve syphilis-related aspects. Our review shows the usefulness of computational tools to promote the overall understanding of syphilis, a global problem, to guide public policy and practice, to target better public health interventions such as surveillance and prevention, health service delivery, and the optimal use of diagnostic tools. The review was conducted according to PRISMA 2020 Statement and used several quality criteria to include studies. The publications chosen to compose this review were gathered from Science Direct, Web of Science, Springer, Scopus, ACM Digital Library, and PubMed databases. Then, studies published between 2015 and 2022 were selected. The review identified 1,991 studies. After applying inclusion, exclusion, and study quality assessment criteria, 26 primary studies were included in the final analysis. The results show different computational approaches, including countless Machine Learning algorithmic models, and three sub-areas of application in the context of syphilis: surveillance (61.54%), diagnosis (34.62%), and health policy evaluation (3.85%). These computational approaches are promising and capable of being tools to support syphilis control and surveillance actions.

A comprehensive review for machine learning based human papillomavirus detection in forensic identification with multiple medical samples

Human papillomavirus (HPV) is a sexually transmitted virus. Cervical cancer is one of the highest incidences of cancer, almost all patients are accompanied by HPV infection. In addition, the occurrence of a variety of cancers is also associated with HPV infection. HPV vaccination has gained widespread popularity in recent years with the increase in public health awareness. In this context, HPV testing not only needs to be sensitive and specific but also needs to trace the source of HPV infection. Through machine learning and deep learning, information from medical examinations can be used more effectively. In this review, we discuss recent advances in HPV testing in combination with machine learning and deep learning.

A Quantitative Detection Algorithm for Multi-Test Line Lateral Flow Immunoassay Applied in Smartphones

The traditional lateral flow immunoassay (LFIA) detection method suffers from issues such as unstable detection results and low quantitative accuracy. In this study, we propose a novel multi-test line lateral flow immunoassay quantitative detection method using smartphone-based SAA immunoassay strips. Following the utilization of image processing techniques to extract and analyze the pigments on the immunoassay strips, quantitative analysis of the detection results was conducted. Experimental setups with controlled lighting conditions in a dark box were designed to capture samples using smartphones with different specifications for analysis. The algorithm's sensitivity and robustness were validated by introducing noise to the samples, and the detection performance on immunoassay strips using different algorithms was determined. The experimental results demonstrate that the proposed lateral flow immunoassay quantitative detection method based on image processing techniques achieves an accuracy rate of 94.23% on 260 samples, which is comparable to the traditional methods but with higher stability and lower algorithm complexity.

Leveraging artificial intelligence in the fight against infectious diseases

Despite advances in molecular biology, genetics, computation, and medicinal chemistry, infectious disease remains an ominous threat to public health. Addressing the challenges posed by pathogen outbreaks, pandemics, and antimicrobial resistance will require concerted interdisciplinary efforts. In conjunction with systems and synthetic biology, artificial intelligence (AI) is now leading to rapid progress, expanding anti-infective drug discovery, enhancing our understanding of infection biology, and accelerating the development of diagnostics. In this Review, we discuss approaches for detecting, treating, and understanding infectious diseases, underscoring the progress supported by AI in each case. We suggest future applications of AI and how it might be harnessed to help control infectious disease outbreaks and pandemics.

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.

REASSURED diagnostics at point-of-care in sub-Saharan Africa: A scoping review

Point-of-care (POC) diagnostics that meet the REASSURED criteria are essential in combating the rapid increase and severity of global health emergencies caused by infectious diseases. However, little is known about whether the REASSURED criteria are implemented in regions known to have a high burden of infectious diseases such as sub-Saharan Africa (SSA). This scoping review maps evidence of the use of REASSURED POC diagnostic tests in SSA. The scoping review was guided by the advanced methodological framework of Arksey and O'Malley, and Levac et al. We searched the following electronic databases for relevant literature: Scopus, Dimensions, ProQuest Central, Google Scholar, and EBSCOhost (MEDLINE, CINAHL, as well as AFRICA-WIDE). Two reviewers independently screened abstracts and full-text articles using the inclusion criteria as reference. We appraised the quality of the included studies using the mixed-method appraisal tool (MMAT) version 2018. We retrieved 138 publications, comprising 134 articles and four grey literature articles. Of these, only five articles were included following abstract and full-text screening. The five included studies were all conducted in SSA. The following themes emerged from the eligible articles: quality assurance on accuracy of REASSURED POC diagnostic tests, sustainability of REASSURED POC diagnostic tests, and local infrastructure capability for delivering REASSURED POC diagnostic tests to end users. All five articles had MMAT scores between 90% and 100%. In conclusion, our scoping review revealed limited published research on REASSURED diagnostics at POC in SSA. We recommend primary studies aimed at investigating the implementation of REASSURED POC diagnostic tests in SSA.

Sample-to-answer platform for the clinical evaluation of COVID-19 using a deep learning-assisted smartphone-based assay

Since many lateral flow assays (LFA) are tested daily, the improvement in accuracy can greatly impact individual patient care and public health. However, current self-testing for COVID-19 detection suffers from low accuracy, mainly due to the LFA sensitivity and reading ambiguities. Here, we present deep learning-assisted smartphone-based LFA (SMART^AI-LFA) diagnostics to provide accurate decisions with higher sensitivity. Combining clinical data learning and two-step algorithms enables a cradle-free on-site assay with higher accuracy than the untrained individuals and human experts via blind tests of clinical data (n = 1500). We acquired 98% accuracy across 135 smartphone application-based clinical tests with different users/smartphones. Furthermore, with more low-titer tests, we observed that the accuracy of SMART^AI-LFA was maintained at over 99% while there was a significant decrease in human accuracy, indicating the reliable performance of SMART^AI-LFA. We envision a smartphone-based SMART^AI-LFA that allows continuously enhanced performance by adding clinical tests and satisfies the new criterion for digitalized real-time diagnostics.

Machine Learning Approaches to Understand Cognitive Phenotypes in People With HIV

Cognitive disorders are prevalent in people with HIV (PWH) despite antiretroviral therapy. Given the heterogeneity of cognitive disorders in PWH in the current era and evidence that these disorders have different etiologies and risk factors, scientific rationale is growing for using data-driven models to identify biologically defined subtypes (biotypes) of these disorders. Here, we discuss the state of science using machine learning to understand cognitive phenotypes in PWH and their associated comorbidities, biological mechanisms, and risk factors. We also discuss methods, example applications, challenges, and what will be required from the field to successfully incorporate machine learning in research on cognitive disorders in PWH. These topics were discussed at the National Institute of Mental Health meeting on "Biotypes of CNS Complications in People Living with HIV" held in October 2021. These ongoing research initiatives seek to explain the heterogeneity of cognitive phenotypes in PWH and their associated biological mechanisms to facilitate clinical management and tailored interventions.

Smartphone-based platforms implementing microfluidic detection with image-based artificial intelligence

The frequent outbreak of global infectious diseases has prompted the development of rapid and effective diagnostic tools for the early screening of potential patients in point-of-care testing scenarios. With advances in mobile computing power and microfluidic technology, the smartphone-based mobile health platform has drawn significant attention from researchers developing point-of-care testing devices that integrate microfluidic optical detection with artificial intelligence analysis. In this article, we summarize recent progress in these mobile health platforms, including the aspects of microfluidic chips, imaging modalities, supporting components, and the development of software algorithms. We document the application of mobile health platforms in terms of the detection objects, including molecules, viruses, cells, and parasites. Finally, we discuss the prospects for future development of mobile health platforms.

Lessons from COVID-19 for improving diagnostic access in future pandemics

Throughout the COVID-19 pandemic, we have witnessed the critical and expanding roles of testing. Despite the development of over a thousand brand of tests - with some close to fulfilling the 4As (accuracy, access, affordability, and actionability via quick time to result) of an ideal diagnostic test - gaps persisted in developing tests to fit public health needs, and in providing equitable access. Here, we review how the use cases for testing evolved over the course of the COVID-19 pandemic, with associated engineering challenges (and potential lessons) at each phase for test developers. We summarise lessons learnt from the recent epidemic and propose four areas for future cooperative effort among test developers, government regulators and policy makers, public health experts, and the public: 1) develop new models for public sector funding and research and development; 2) increase testing capacity by investing in adaptable open-platform technologies at every level of the healthcare system; 3) build data connectivity infrastructures to support a connected diagnostic system as a backbone for surveillance; and 4) facilitate the rapid translation of innovation into use through a coordinated framework for regulatory approval and policy development.

Review of HIV Self Testing Technologies and Promising Approaches for the Next Generation

The ability to self-test for HIV is vital to preventing transmission, particularly when used in concert with HIV biomedical prevention modalities, such as pre-exposure prophylaxis (PrEP). In this paper, we review recent developments in HIV self-testing and self-sampling methods, and the potential future impact of novel materials and methods that emerged through efforts to develop more effective point-of-care (POC) SARS-CoV-2 diagnostics. We address the gaps in existing HIV self-testing technologies, where improvements in test sensitivity, sample-to-answer time, simplicity, and cost are needed to enhance diagnostic accuracy and widespread accessibility. We discuss potential paths toward the next generation of HIV self-testing through sample collection materials, biosensing assay techniques, and miniaturized instrumentation. We discuss the implications for other applications, such as self-monitoring of HIV viral load and other infectious diseases.

Real-time, smartphone-based processing of lateral flow assays for early failure detection and rapid testing workflows

Despite their simplicity, lateral flow immunoassays (LFIAs) remain a crucial weapon in the diagnostic arsenal, particularly at the point-of-need. However, methods for analysing LFIAs still rely heavily on sub-optimal human readout and rudimentary end-point analysis. This negatively impacts both testing accuracy and testing times, ultimately lowering diagnostic throughput. Herein, we present an automated computational imaging method for processing and analysing multiple LFIAs in real-time and in parallel. This method relies on the automated detection of signal intensity at the test line, control line, and background, and employs statistical comparison of these values to predictively categorise tests as "positive", "negative", or "failed". We show that such a computational methodology can be transferred to a smartphone and detail how real-time analysis of LFIAs can be leveraged to decrease the time-to-result and increase testing throughput. We compare our method to naked-eye readout and demonstrate a shorter time-to-result across a range of target antigen concentrations and fewer false negatives compared to human subjects at low antigen concentrations.

Rapid, label-free histopathological diagnosis of liver cancer based on Raman spectroscopy and deep learning

Biopsy is the recommended standard for pathological diagnosis of liver carcinoma. However, this method usually requires sectioning and staining, and well-trained pathologists to interpret tissue images. Here, we utilize Raman spectroscopy to study human hepatic tissue samples, developing and validating a workflow for in vitro and intraoperative pathological diagnosis of liver cancer. We distinguish carcinoma tissues from adjacent non-tumour tissues in a rapid, non-disruptive, and label-free manner by using Raman spectroscopy combined with deep learning, which is validated by tissue metabolomics. This technique allows for detailed pathological identification of the cancer tissues, including subtype, differentiation grade, and tumour stage. 2D/3D Raman images of unprocessed human tissue slices with submicrometric resolution are also acquired based on visualization of molecular composition, which could assist in tumour boundary recognition and clinicopathologic diagnosis. Lastly, the potential for a portable handheld Raman system is illustrated during surgery for real-time intraoperative human liver cancer diagnosis.

A Smartphone-Based Platform Assisted by Artificial Intelligence for Reading and Reporting Rapid Diagnostic Tests: Evaluation Study in SARS-CoV-2 Lateral Flow Immunoassays

BACKGROUND

Rapid diagnostic tests (RDTs) are being widely used to manage COVID-19 pandemic. However, many results remain unreported or unconfirmed, altering a correct epidemiological surveillance.

OBJECTIVE

Our aim was to evaluate an artificial intelligence-based smartphone app, connected to a cloud web platform, to automatically and objectively read RDT results and assess its impact on COVID-19 pandemic management.

METHODS

Overall, 252 human sera were used to inoculate a total of 1165 RDTs for training and validation purposes. We then conducted two field studies to assess the performance on real-world scenarios by testing 172 antibody RDTs at two nursing homes and 96 antigen RDTs at one hospital emergency department.

RESULTS

Field studies demonstrated high levels of sensitivity (100%) and specificity (94.4%, CI 92.8%-96.1%) for reading IgG band of COVID-19 antibody RDTs compared to visual readings from health workers. Sensitivity of detecting IgM test bands was 100%, and specificity was 95.8% (CI 94.3%-97.3%). All COVID-19 antigen RDTs were correctly read by the app.

CONCLUSIONS

The proposed reading system is automatic, reducing variability and uncertainty associated with RDTs interpretation and can be used to read different RDT brands. The web platform serves as a real-time epidemiological tracking tool and facilitates reporting of positive RDTs to relevant health authorities.

Evaluation of the Nigeria national HIV rapid testing algorithm

Human Immunodeficiency Virus (HIV) diagnosis remains the gateway to HIV care and treatment. However, due to changes in HIV prevalence and testing coverage across different geopolitical zones, it is crucial to evaluate the national HIV testing algorithm as false positivity due to low prevalence could be detrimental to both the client and the service delivery. Therefore, we evaluated the performance of the national HIV rapid testing algorithm using specimens collected from multiple HIV testing services (HTS) sites and compared the results from different HIV prevalence levels across the six geopolitical zones of Nigeria. The evaluation employed a dual approach, retrospective, and prospective. The retrospective evaluation focused on a desktop review of program data (n = 492,880) collated from patients attending routine HTS from six geopolitical zones of Nigeria between January 2017 and December 2019. The prospective component utilized samples (n = 2,895) collected from the field at the HTS and tested using the current national serial HIV rapid testing algorithm. These samples were transported to the National Reference Laboratory (NRL), Abuja, and were re-tested using the national HIV rapid testing algorithm and HIV-1/2 supplementary assays (Geenius to confirm positives and resolve discordance and multiplex assay). The retrospective component of the study revealed that the overall proportion of HIV positives, based on the selected areas, was 5.7% (28,319/492,880) within the study period, and the discordant rate between tests 1 and 2 was 1.1%. The prospective component of the study indicated no significant differences between the test performed at the field using the national HIV rapid testing algorithm and the re-testing performed at the NRL. The comparison between the test performed at the field using the national HIV rapid testing algorithm and Geenius HIV-1/2 supplementary assay showed an agreement rate of 95.2%, while that of the NRL was 99.3%. In addition, the comparison of the field results with HIV multiplex assay indicated a sensitivity of 96.6%, the specificity of 98.2%, PPV of 97.0%, and Kappa Statistic of 0.95, and that of the NRL with HIV multiplex assay was 99.2%, 99.4%, 99.0%, and 0.99, respectively. Results show that the Nigeria national serial HIV rapid testing algorithm performed very well across the target settings. However, the algorithm's performance in the field was lower than the performance outcomes under a controlled environment in the NRL. There is a need to target testers in the field for routine continuous quality improvement implementation, including refresher trainings as necessary.

Simplifying the complex: accessible microfluidic solutions for contemporary processes within in vitro diagnostics

In vitro diagnostics (IVDs) form the cornerstone of modern medicine. They are routinely employed throughout the entire treatment pathway, from initial diagnosis through to prognosis, treatment planning, and post-treatment surveillance. Given the proven links between high quality diagnostic testing and overall health, ensuring broad access to IVDs has long been a focus of both researchers and medical professionals. Unfortunately, the current diagnostic paradigm relies heavily on centralized laboratories, complex and expensive equipment, and highly trained personnel. It is commonly assumed that this level of complexity is required to achieve the performance necessary for sensitive and specific disease diagnosis, and that making something affordable and accessible entails significant compromises in test performance. However, recent work in the field of microfluidics is challenging this notion. By exploiting the unique features of microfluidic systems, researchers have been able to create progressively simple devices that can perform increasingly complex diagnostic assays. This review details how microfluidic technologies are disrupting the status quo, and facilitating the development of simple, affordable, and accessible integrated IVDs. Importantly, we discuss the advantages and limitations of various approaches, and highlight the remaining challenges within the field.

Web-Based Risk Prediction Tool for an Individual's Risk of HIV and Sexually Transmitted Infections Using Machine Learning Algorithms: Development and External Validation Study

Background

HIV and sexually transmitted infections (STIs) are major global public health concerns. Over 1 million curable STIs occur every day among people aged 15 years to 49 years worldwide. Insufficient testing or screening substantially impedes the elimination of HIV and STI transmission.

Objective

The aim of our study was to develop an HIV and STI risk prediction tool using machine learning algorithms.

Methods

We used clinic consultations that tested for HIV and STIs at the Melbourne Sexual Health Centre between March 2, 2015, and December 31, 2018, as the development data set (training and testing data set). We also used 2 external validation data sets, including data from 2019 as external “validation data 1” and data from January 2020 and January 2021 as external “validation data 2.” We developed 34 machine learning models to assess the risk of acquiring HIV, syphilis, gonorrhea, and chlamydia. We created an online tool to generate an individual’s risk of HIV or an STI.

Results

The important predictors for HIV and STI risk were gender, age, men who reported having sex with men, number of casual sexual partners, and condom use. Our machine learning–based risk prediction tool, named MySTIRisk, performed at an acceptable or excellent level on testing data sets (area under the curve [AUC] for HIV=0.78; AUC for syphilis=0.84; AUC for gonorrhea=0.78; AUC for chlamydia=0.70) and had stable performance on both external validation data from 2019 (AUC for HIV=0.79; AUC for syphilis=0.85; AUC for gonorrhea=0.81; AUC for chlamydia=0.69) and data from 2020-2021 (AUC for HIV=0.71; AUC for syphilis=0.84; AUC for gonorrhea=0.79; AUC for chlamydia=0.69).

Conclusions

Our web-based risk prediction tool could accurately predict the risk of HIV and STIs for clinic attendees using simple self-reported questions. MySTIRisk could serve as an HIV and STI screening tool on clinic websites or digital health platforms to encourage individuals at risk of HIV or an STI to be tested or start HIV pre-exposure prophylaxis. The public can use this tool to assess their risk and then decide if they would attend a clinic for testing. Clinicians or public health workers can use this tool to identify high-risk individuals for further interventions.

Machine learning to support visual auditing of home-based lateral flow immunoassay self-test results for SARS-CoV-2 antibodies

Background

Lateral flow immunoassays (LFIAs) are being used worldwide for COVID-19 mass testing and antibody prevalence studies. Relatively simple to use and low cost, these tests can be self-administered at home, but rely on subjective interpretation of a test line by eye, risking false positives and false negatives. Here, we report on the development of ALFA (Automated Lateral Flow Analysis) to improve reported sensitivity and specificity.

Methods

Our computational pipeline uses machine learning, computer vision techniques and signal processing algorithms to analyse images of the Fortress LFIA SARS-CoV-2 antibody self-test, and subsequently classify results as invalid, IgG negative and IgG positive. A large image library of 595,339 participant-submitted test photographs was created as part of the REACT-2 community SARS-CoV-2 antibody prevalence study in England, UK. Alongside ALFA, we developed an analysis toolkit which could also detect device blood leakage issues.

Results

Automated analysis showed substantial agreement with human experts (Cohen's kappa 0.90-0.97) and performed consistently better than study participants, particularly for weak positive IgG results. Specificity (98.7-99.4%) and sensitivity (90.1-97.1%) were high compared with visual interpretation by human experts (ranges due to the varying prevalence of weak positive IgG tests in datasets).

Conclusions

Given the potential for LFIAs to be used at scale in the COVID-19 response (for both antibody and antigen testing), even a small improvement in the accuracy of the algorithms could impact the lives of millions of people by reducing the risk of false-positive and false-negative result read-outs by members of the public. Our findings support the use of machine learning-enabled automated reading of at-home antibody lateral flow tests as a tool for improved accuracy for population-level community surveillance.

Introduction to supervised machine learning in clinical epidemiology

Machine learning refers to a series of processes in which a computer finds rules from a vast amount of data. With recent advances in computer technology and the availability of a wide variety of health data, machine learning has rapidly developed and been applied in medical research. Currently, there are three types of machine learning: supervised, unsupervised, and reinforcement learning. In medical research, supervised learning is commonly used for diagnoses and prognoses, while unsupervised learning is used for phenotyping a disease, and reinforcement learning for maximizing favorable results, such as optimization of total patients' waiting time in the emergency department. The present article focuses on the concept and application of supervised learning in medicine, the most commonly used machine learning approach in medicine, and provides a brief explanation of four algorithms widely used for prediction (random forests, gradient-boosted decision tree, support vector machine, and neural network). Among these algorithms, the neural network has further developed into deep learning algorithms to solve more complex tasks. Along with simple classification problems, deep learning is commonly used to process medical imaging, such as retinal fundus photographs for diabetic retinopathy diagnosis. Although machine learning can bring new insights into medicine by processing a vast amount of data that are often beyond human capacity, algorithms can also fail when domain knowledge is neglected. The combination of algorithms and human cognitive ability is a key to the successful application of machine learning in medicine.

Clinical decisions using AI must consider patient values

Built-in decision thresholds for AI diagnostics are ethically problematic, as patients may differ in their attitudes about the risk of false-positive and false-negative results, which will require that clinicians assess patient values.

A Universal Boronate-Affinity Crosslinking-Amplified Dynamic Light Scattering Immunoassay for Point-of-Care Glycoprotein Detection

Herein, we report a universal boronate-affinity crosslinking-amplified dynamic light scattering (DLS) immunoassay for point-of-care (POC) glycoprotein detection in complex samples. This enhanced DLS immunoassay consists of two elements, i.e., antibody-coated magnetic nanoparticles (MNP@mAb) for target capture and DLS signal transduction, and phenylboronic acid-based boronate-affinity materials as crosslinking amplifiers. Upon the addition of targets, glycoproteins are first captured by MNP@mAb and amplified by target-induced crosslinking stemming from the selective binding between the boronic acid ligand and cis-diol-containing glycoprotein, thereby resulting in a remarkably increased DLS signal in the average nanoparticle size. Benefiting from the multivalent binding and fast boronate-affinity reaction between glycoproteins and crosslinkers, the proposed immunosensing strategy has achieved the ultrasensitive and rapid quantitative assay of glycoproteins at the fM level within 15 min. Overall, this work provides a promising and versatile design strategy for extending the DLS technique to detect glycoproteins even in the field or at POC.

Dual Photoredox Catalysis Strategy for Enhanced Photopolymerization-Based Colorimetric Biodetection

Catalytic redox reactions have been employed to enhance colorimetric biodetection signals in point-of-care diagnostic tests, while their time-sensitive visual readouts may increase the risk of false results. To address this issue, we developed a dual photocatalyst signal amplification strategy that can be controlled by a fixed light dose, achieving time-independent colorimetric biodetection in paper-based tests. In this method, target-associated methylene blue (MB⁺) photocatalytically amplifies the concentration of eosin Y by oxidizing deactivated eosin Y (EYH^3-) under red light, followed by photopolymerization with eosin Y autocatalysis under green light to generate visible hydrogels. Using the insights from mechanistic studies on MB⁺-sensitized photo-oxidation of EYH^3-, we improved the photocatalytic efficiency of MB⁺ by suppressing its degradation. Lastly, we characterized 100- to 500-fold enhancement in sensitivity obtained from MB⁺-specific eosin Y amplification, highlighting the advantages of using dual photocatalyst signal amplification.