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

Rapid, portable, and sensitive detection of CaMV35S by RPA-CRISPR/Cas12a-G4 colorimetric assays with high accuracy deep learning object recognition and classification

Fast, sensitive, and portable detection of genetic modification contributes to agricultural security and food safety. Here, we developed RPA-CRISPR/Cas12a-G-quadruplex colorimetric assays that can combine with intelligent recognition by deep learning algorithms to achieve sensitive, rapid, and portable detection of the CaMV35S promoter. When the crRNA-Cas12a complex recognizes the RPA amplification product, Cas12 cleaves the G-quadruplex, causing the G4-Hemin complex to lose its peroxide mimetic enzyme function and be unable to catalyze the conversion of ABTS2- to ABTS, allowing CaMV35S concentration to be determined based on ABTS absorbance. By utilizing the RPA-CRISPR/Cas12a-G4 assay, we achieved a CaMV35S limit of detection down to 10 aM and a 0.01 % genetic modification sample in 45 min. Deep learning algorithms are designed for highly accurate classification of color results. Yolov5 objective finding and Resnet classification algorithms have been trained to identify trace (0.01 %) CaMV35S more accurately than naked eye colorimetry. We also coupled deep learning algorithms with a smartphone app to achieve portable and rapid photo identification. Overall, our findings enable low cost ($0.43), high accuracy, and intelligent detection of the CaMV35S promoter.

Paper-Based procalcitonin and Interleukin-6 test strip with Spectrum-Based optical reader for enterovirus severity differentiation in children

Infectious diseases significantly impact global health, necessitating prompt diagnosis to mitigate life-threatening sepsis risk. Identifying patients at risk of severe neurological complications from enterovirus infections is challenging due to nonspecific initial presentations. Point-of-care testing (POCT) has emerged as a transformative tool, with low-cost lateral-flow colorimetric assays showing promise in deployable POCT devices. We developed a PCT/IL-6 rapid diagnostic system integrating lateral flow assay (LFA) test strips and a portable optical spectrum reader, allowing simultaneous semi-quantitative measurement of serum PCT and IL-6 within 30 min at the point of care. The system demonstrated a strong correlation with traditional ELISA and effectively differentiated severe pediatric enterovirus cases using serum samples. IL-6 showed superior discriminatory ability over PCT in identifying patients with severe neurological complications. This novel diagnostic platform holds great potential for early sepsis recognition and infectious disease management, especially in resource-limited settings.

Digitalization of Colorimetric Sensor Technologies for Food Safety

Colorimetric sensors play a crucial role in promoting on-site testing, enabling the detection and/or quantification of various analytes based on changes in color. These sensors offer several advantages, such as simplicity, cost-effectiveness, and visual readouts, making them suitable for a wide range of applications, including food safety and monitoring. A critical component in portable colorimetric sensors involves their integration with color models for effective analysis and interpretation of output signals. The most commonly used models include CIELAB (Commission Internationale de l'Eclairage), RGB (Red, Green, Blue), and HSV (Hue, Saturation, Value). This review outlines the use of color models via digitalization in sensing applications within the food safety and monitoring field. Additionally, challenges, future directions, and considerations are discussed, highlighting a significant gap in integrating a comparative analysis toward determining the color model that results in the highest sensor performance. The aim of this review is to underline the potential of this integration in mitigating the global impact of food spoilage and contamination on health and the economy, proposing a multidisciplinary approach to harness the full capabilities of colorimetric sensors in ensuring food safety.

Loop-Mediated Isothermal Amplification and Lateral Flow Immunochromatography Technology for Rapid Diagnosis of Influenza A/B

Influenza viruses cause highly contagious respiratory diseases that cause millions of deaths worldwide. Rapid detection of influenza viruses is essential for accurate diagnosis and the initiation of appropriate treatment. We developed a loop-mediated isothermal amplification and lateral flow assay (LAMP-LFA) capable of simultaneously detecting influenza A and influenza B. Primer sets for influenza A and influenza B were designed to target conserved regions of segment 7 and the nucleoprotein gene, respectively. Optimized through various primer set ratios, the assay operated at 62 °C for 30 min. For a total of 243 (85 influenza A positive, 58 influenza B positive and 100 negative) nasopharyngeal swab samples, the performance of the influenza A/B multiplex LAMP-LFA was compared with that of the commercial AllplexTM Respiratory Panel 1 assay (Seegene, Seoul, Korea). The influenza A/B multiplex LAMP-LFA demonstrated a specificity of 98% for the non-infected clinical samples, along with sensitivities of 94.1% for the influenza A clinical samples and 96.6% for the influenza B clinical samples, respectively. The influenza A/B multiplex LAMP-LFA showed high sensitivity and specificity, indicating that it is reliable for use in a low-resource environment.

A Wash-Free Spheres-on-Sphere Strategy for On-Site and Multiplexed Biosensing

Respiratory infections and food contaminants pose severe challenges to global health and the economy. A rapid on-site platform for the simultaneous detection of multiple pathogens is crucial for accurate diagnosis, appropriate treatment, and a reduced healthcare burden. Herein, we present a spheres-on-sphere (SOS) platform for multiplexed detection using a portable Coulter counter, which employs millimeter- and micron-sized spheres coupled with antibodies as multitarget probes. The assay allows for quantitative detection of multiple analytes within 20 min by simple mixing, enabling on-site detection. The platform shows high accuracy in identifying three respiratory viruses (SARS-CoV-2, influenza A virus, and parainfluenza virus) from throat swab samples, with LOD of 50.7, 32.4, and 49.1 pg/mL. It also demonstrates excellent performance in quantifying three mycotoxins (aflatoxin B1, deoxynivalenol, and ochratoxin A) from food samples. The SOS platform offers a rapid on-site approach with high sensitivity and specificity for applications in resource-limited settings.

A portable, integrated microfluidics for rapid and sensitive diagnosis of Streptococcus agalactiae in resource-limited environments

Streptococcus agalactiae (Group B Streptococcus, GBS) has been the leading cause of infections in newborns. Rapid and accurate diagnosis of GBS in pregnant women is a deterministic strategy to prevent newborn infection. Conventional detection methods based on nucleic acid amplification assay have been applied in GBS diagnosis in central laboratories, with demonstrated high sensitivity. However, their heavy dependence on instrumentation and trained technicians forms remarkable obstacles to GBS detection in wide scenarios, including self-testing, and bedside-/community-screening. Furthermore, the structures of GBS bring about extra challenges to the nucleic acid extraction and purification. Novel GBS diagnosis platforms integrating sample processing, amplification, and read-out, are highly desired in clinical. Here, we report a portable, integrated microfluidics that enables rapid extraction of DNA from sampling swabs (<10 min), power-free DNA amplification (<30 min), and simple read-out in GBS detection. The platform works without an external pump, achieving rapid and highly efficient DNA extraction from clinical samples, with a significantly reduced time from 6 h to less than 50 min. Systematic clinical tests based on 47 patient samples validated the high performance of the platform, highlighted with a low limit of detection (LOD, 103 copies/ml), high sensitivity (100%), and specificity (100%). Head-to-head comparisons showed that the device improved the LOD by an order of magnitude than the traditional PCR method, showing a simple yet powerful POCT platform for home-/community-based testing towards GBS (and other pathogens) prevention in remote areas.

Rapid deep learning-assisted predictive diagnostics for point-of-care testing

Prominent techniques such as real-time polymerase chain reaction (RT-PCR), enzyme-linked immunosorbent assay (ELISA), and rapid kits are currently being explored to both enhance sensitivity and reduce assay time for diagnostic tests. Existing commercial molecular methods typically take several hours, while immunoassays can range from several hours to tens of minutes. Rapid diagnostics are crucial in Point-of-Care Testing (POCT). We propose an approach that integrates a time-series deep learning architecture and AI-based verification, for the enhanced result analysis of lateral flow assays. This approach is applicable to both infectious diseases and non-infectious biomarkers. In blind tests using clinical samples, our method achieved diagnostic times as short as 2 minutes, exceeding the accuracy of human analysis at 15 minutes. Furthermore, our technique significantly reduces assay time to just 1-2 minutes in the POCT setting. This advancement has the potential to greatly enhance POCT diagnostics, enabling both healthcare professionals and non-experts to make rapid, accurate decisions.

Ultrasensitive ImmunoMag-CRISPR Lateral Flow Assay for Point-of-Care Testing of Urinary Biomarkers

Rapid, accurate, and noninvasive detection of biomarkers in saliva, urine, or nasal fluid is essential for the identification, early diagnosis, and monitoring of cancer, organ failure, transplant rejection, vascular diseases, autoimmune disorders, and infectious diseases. We report the development of an Immuno-CRISPR-based lateral flow assay (LFA) using antibody-DNA barcode complexes with magnetic enrichment of the target urinary biomarkers CXCL9 and CXCL10 for naked eye detection (ImmunoMag-CRISPR LFA). An intermediate approach involving a magnetic bead-based Immuno-CRISPR assay (ImmunoMag-CRISPR) resulted in a limit of detection (LOD) of 0.6 pg/mL for CXCL9. This value surpasses the detection limits achieved by previously reported assays. The highly sensitive detection method was then re-engineered into an LFA format with an LOD of 18 pg/mL for CXCL9, thereby enabling noninvasive early detection of acute kidney transplant rejection. The ImmunoMag-CRISPR LFA was tested on 42 clinical urine samples from kidney transplant recipients, and the assay could determine 11 positive and 31 negative urinary samples through a simple visual comparison of the test line and the control line of the LFA strip. The LFA system was then expanded to quantify the CXCL9 and CXCL10 levels in clinical urine samples from images. This approach has the potential to be extended to a wide range of point-of-care tests for highly sensitive biomarker detection.

Design, implementation and evaluation of e-learning program for common diseases to smartphone-based medical students: at a developing university

OBJECTIVE

Mobile-based educational software offers a wealth of resources that can foster the growth of learners and facilitate the creation of an interactive learning environment. This environment encourages both students and instructors to engage in exploration and the examination of various medical issues. The objective of this study is to design, implement, and evaluate an electronic educational program focused on common medical conditions, specifically tailored for medical students and accessible through mobile phones.

METHOD

The study was conducted following an action research approach, which comprised four key stages: needs assessment, application design, training, and evaluation. This research took place at the Kermanshah University of Medical Sciences' Medical School. In the needs assessment phase, a formal survey was distributed to the teaching faculty members, requesting them to identify diseases and medical issues of high importance for medical interns' education that were suitable for virtual teaching. Each faculty member was asked to prioritize a minimum of three and a maximum of seven cases. Subsequently, 10 faculty members from various departments completed the survey, leading to the identification of 47 common diseases after eliminating duplicates. These 47 cases were then presented to 30 medical interns, who were asked to select the 20 most significant cases. The 20 diseases with the highest statistical frequency were selected for further development due to resource constraints. The mobile application was developed for the Android platform using the Java programming language and the Android Studio development environment. To assess the application's effectiveness from the students' perspective, a questionnaire was designed, encompassing 25 questions across five domains: satisfaction, performance, learning, usability, and educational effectiveness. The questionnaire employed a Likert scale, with response options ranging from 'completely disagree' to 'completely agree,' scored from 1 to 5. One hundred medical interns and trainees were invited to participate in the evaluation, with 92 of them completing the questionnaires.

RESULTS

The findings revealed a significant disparity in the average scores between students who underwent traditional teaching methods and those who engaged in mobile-based app-assisted education. This discrepancy was statistically significant across all three examined components.

CONCLUSION

Mobile-based learning represents a burgeoning educational approach with profound implications for healthcare education and the enhancement of patient care quality. The widespread integration of mobile phones into the educational framework offers a flexible teaching paradigm, fostering the potential for continuous lifelong learning.

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.

Machine Learning-Assisted High-Throughput Strategy for Real-Time Detection of Spermine Using a Triple-Emission Ratiometric Probe

In this study, we designed and fabricated a spermine-responsive triple-emission ratiometric fluorescent probe using dual-emissive carbon nanoparticles and quantum dots, which improve the sensor's accuracy and reduce interfering environmental effects. The probe is advantageous for the proportionate detection of spermine because it has good emission resolution, and the maximum points of the two emission peaks differ by 95 nm. As a proof of concept, cuvettes and a 96-well plate were combined with a smartphone and YOLO series algorithms to accomplish real-time, visual, and high-throughput detection of seafood and meat freshness. In addition, the reaction mechanism was verified by density functional theory and fundamental characterizations. Upon exposure to different amounts of spermine, the intensity of the fluorescent probe changed linearly, and the fluorescent color shifted from yellow-green to red, with a limit of detection of 0.33 μM. To enable visual identification of food-originated spermine, a hydrogel-based visual sensing platform was successfully developed utilizing the triple-emission fluorescent probe. Consequently, spermine could be identified and quantified without complicated equipment.

Lateral Flow Assay: A Summary of Recent Progress for Improving Assay Performance

Lateral flow tests are one of the most important types of paper-based point-of-care (POCT) diagnostic tools. It shows great potential as an implement for improving the rapid screening and management of infections in global pandemics or other potential health disorders by using minimally expert staff in locations where no sophisticated laboratory services are accessible. They can detect different types of biomarkers in various biological samples and provide the results in a little time at a low price. An important challenge regarding conventional LFAs is increasing their sensitivity and specificity. There are two main approaches to increase sensitivity and specificity, including assay improvement and target enrichment. Assay improvement comprises the assay optimization and signal amplification techniques. In this study, a summarize of various sensitivity and specificity enhancement strategies with an objective evaluation are presented, such as detection element immobilization, capillary flow rate adjusting, label evolution, sample extraction and enrichment, etc. and also the key findings in improving the LFA performance and solving their limitations are discussed along with numerous examples.