Bi-ECDAQ: An electrochemical dual-immuno-biosensor accompanied by a customized bi-potentiostat for clinical detection of SARS-CoV-2 Nucleocapsid proteins.

Multiplex electrochemical biosensors have been used for eliminating the matrix effect in complex bodily fluids or enabling the detection of two or more bioanalytes, overall resulting in more sensitive assays and accurate diagnostics. Many electrochemical biosensors lack reliable and low-cost multiplexing to meet the requirements of point-of-care detection due to either limited functional biosensors for multi-electrode detection or incompatible readout systems. We developed a new dual electrochemical biosensing unit accompanied by a customized potentiostat to address the unmet need for point-of-care multi-electrode electrochemical biosensing. The two-working electrode system was developed using screen-printing of a carboxyl-rich nanomaterial containing ink, with both working electrodes offering active sites for recognition of bioanalytes. The low-cost bi-potentiostat system (∼$80) was developed and customized specifically to the bi-electrode design and used for rapid, repeatable, and accurate measurement of electrochemical impedance spectroscopy signals from the dual biosensor. This binary electrochemical data acquisition (Bi-ECDAQ) system accurately and selectively detected SARS-CoV-2 Nucleocapsid protein (N-protein) in both spiked samples and clinical nasopharyngeal swab samples of COVID-19 patients within 30 min. The two working electrodes offered the limit of detection of 116 fg/mL and 150 fg/mL, respectively, with the dynamic detection range of 1-10,000 pg/mL and the sensitivity range of 2744-2936 Ω mL/pg.mm2 for the detection of N-protein. The potentiostat performed comparable or better than commercial Autolab potentiostats while it is significantly lower cost. The open-source Bi-ECDAQ presents a customizable and flexible approach towards addressing the need for rapid and accurate point-of-care electrochemical biosensors for the rapid detection of various diseases.

An ensemble learning approach to digital corona virus preliminary screening from cough sounds.

This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.