ABSTRACT
An IoT-WiFi smart and portable electrochemical immunosensor for the quantification of SARS-CoV-2 spike protein was developed with integrated machine learning features. The immunoenzymatic sensor is based on the immobilization of monoclonal antibodies directed at the SARS-CoV-2 S1 subunit on Screen-Printed Electrodes functionalized with gold nanoparticles. The analytical protocol involves a single-step sample incubation. Immunosensor performance was validated in a viral transfer medium which is commonly used for the desorption of nasopharyngeal swabs. Remarkable specificity of the response was demonstrated by testing H1N1 Hemagglutinin from swine-origin influenza A virus and Spike Protein S1 from Middle East respiratory syndrome coronavirus. Machine learning was successfully used for data processing and analysis. Different support vector machine classifiers were evaluated, proving that algorithms affect the classifier accuracy. The test accuracy of the best classification model in terms of true positive/true negative sample classification was 97.3%. In addition, the ML algorithm can be easily integrated into cloud-based portable Wi-Fi devices. Finally, the immunosensor was successfully tested using a third generation replicating incompetent lentiviral vector pseudotyped with SARS-CoV-2 spike glycoprotein, thus proving the applicability of the immunosensor to whole virus detection.
Subject(s)
Biosensing Techniques , COVID-19 , Influenza A Virus, H1N1 Subtype , Metal Nanoparticles , COVID-19/diagnosis , Gold , Humans , Immunoassay/methods , Machine Learning , SARS-CoV-2 , Spike Glycoprotein, Coronavirus/analysisABSTRACT
Innovative and highly performing smart voltammetric immunosensors for rapid and effective serological tests aimed at the determination of SARS-CoV-2 antibodies were developed and validated in human serum matrix. Two immunosensors were developed for the determination of immunoglobulins directed against either the nucleocapsid or the spike viral antigen proteins. The immunosensors were realized using disposable screen-printed electrodes modified with nanostructured materials for the immobilization of the antigens. Fast quantitative detection was achieved, with analysis duration being around 1 h. Signal readout was carried out through a smart, compact and battery-powered potentiostat, based on a Wi-Fi protocol and devised for the Internet of Things (IoT) paradigm. This device is used for the acquisition, storage and sharing of clinical data. Outstanding immunosensors' sensitivity, specificity and accuracy (100%) were assessed, according to the diagnostic guidelines for epidemiological data. The overall performance of the sensing devices, combined with the portability of the IoT-based device, enables their suitability as a high-throughput diagnostic tool. Both of the immunosensors were validated using clinical human serum specimens from SARS-CoV-2 infected patients, provided by IRCCS Ospedale San Raffaele.
Subject(s)
Biosensing Techniques , COVID-19 , Vaccines , Antibodies, Viral , Biosensing Techniques/methods , COVID-19/diagnosis , Humans , Immunoassay , Point-of-Care Systems , SARS-CoV-2 , Sensitivity and Specificity , Serologic TestsABSTRACT
An IoT-WiFi smart and portable electrochemical immunosensor for the quantification of SARS-CoV-2 spike protein was developed with integrated machine learning features. The immunoenzymatic sensor is based on the immobilization of monoclonal antibodies directed at the SARS-CoV-2 S1 subunit on Screen-Printed Electrodes functionalized with gold nanoparticles. The analytical protocol involves a single-step sample incubation. Immunosensor performance was validated in a viral transfer medium which is commonly used for the desorption of nasopharyngeal swabs. Remarkable specificity of the response was demonstrated by testing H1N1 Hemagglutinin from swine-origin influenza A virus and Spike Protein S1 from Middle East respiratory syndrome coronavirus. Machine learning was successfully used for data processing and analysis. Different support vector machine classifiers were evaluated, proving that algorithms affect the classifier accuracy. The test accuracy of the best classification model in terms of true positive/true negative sample classification was 97.3%. In addition, the ML algorithm can be easily integrated into cloud-based portable Wi-Fi devices. Finally, the immunosensor was successfully tested using a third generation replicating incompetent lentiviral vector pseudotyped with SARS-CoV-2 spike glycoprotein, thus proving the applicability of the immunosensor to whole virus detection.