A Smartphone-based Microplate Reader for Point-of-Care ELISA Quantification

Berg, Brandon; Cortazar, Bingen; Tseng, Derek; Özkan, Haydar; Feng, Steve; Wei, Qingshan; Chan, Raymond Y.; Burbano, Jordi; Farooqui, Qamar; Lewinski, Michael A.; Carlo, Dino Di; Garner, Omai B.; Özcan, Aydogan

doi:10.1364/cleo_at.2016.atu1o.4

Cited by 8 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…provide a much more complete and medically relevant picture of the user's health. Such sensors could be used for at-home diagnosis of infection, monitoring of treatment progression [2]- [4], hydration and fatigue tracking during exercise [5], and testing food and water safety [2], [6]- [9].…”

Section: Introductionmentioning

confidence: 99%

A Multi-Technique Reconfigurable Electrochemical Biosensor: Enabling Personal Health Monitoring in Mobile Devices

Sun

Venkatesh

Hall

2016

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

Abstract-This paper describes the design, performance, and characterization of a reconfigurable, multi-technique electrochemical biosensor designed for direct integration into smartphone and wearable technologies to enable remote and accurate personal health monitoring. By repurposing components from one mode to the next, the biosensor's potentiostat is able reconfigure itself into three different measurements modes to perform amperometric, potentiometric, and impedance spectroscopic tests all with minimal redundant devices. A 3.9×1.65 cm 2 PCB prototype of the module was developed with discrete components and tested using Google's Project Ara modular smartphone. The amperometric mode has a ±1 nA to ±200 μA measurement range. When used to detect pH, the potentiometric mode can achieve a resolution of <0.08 pH units. In impedance measurement mode, the device can measure 50 Ω -10 MΩ and has been shown to have <6° of phase error. This prototype was used to perform several point-of-care health tracking assays suitable for use with mobile devices: 1) Blood glucose tests were conducted and shown to cover the diagnostic range for Diabetes patients (~200 mg/dL). 2) Lactoferrin, a biomarker for urinary tract infections, was detected with a limit of detection of approximately 1 ng/mL. 3) pH tests of sweat were conducted to track dehydration during exercise. 4) EIS was used to determine the concentration of NeutrAvidin via a label-free assay.

show abstract

Section: Introductionmentioning

confidence: 99%

A Multi-Technique Reconfigurable Electrochemical Biosensor: Enabling Personal Health Monitoring in Mobile Devices

Sun

Venkatesh

Hall

2016

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

show abstract

“…Thus, a deep learning approach has been employed to predict positives in ELISA microplates (Nath et al, 2018) based on the training of an artificial neural network with microplate images of known sample status and the application of the trained algorithm on microplate images of unknown samples. In another report, machine learning was used as an additional step in a procedure used to evaluate transformed ELISA microplate images of a Cellphone-Based Hand-Held Microplate Reader (Berg et al, 2015). In a more recent work, an AI system was presented based on supervised deep learning that outperformed human expertise in the evaluation of mammograms for breast cancer prediction, demonstrating the great promise that such systems hold for diagnostic applications (McKinney et al, 2020).…”

Section: Discussionmentioning

confidence: 99%

Pixel-Based Machine Learning and Image Reconstitution for Dot-ELISA Pathogen Diagnosis in Biological Samples

et al. 2021

View full text Add to dashboard Cite

Serological methods serve as a direct or indirect means of pathogen infection diagnosis in plant and animal species, including humans. Dot-ELISA (DE) is an inexpensive and sensitive, solid-state version of the microplate enzyme-linked immunosorbent assay, with a broad range of applications in epidemiology. Yet, its applicability is limited by uncertainties in the qualitative output of the assay due to overlapping dot colorations of positive and negative samples, stemming mainly from the inherent color discrimination thresholds of the human eye. Here, we report a novel approach for unambiguous DE output evaluation by applying machine learning-based pattern recognition of image pixels of the blot using an impartial predictive model rather than human judgment. Supervised machine learning was used to train a classifier algorithm through a built multivariate logistic regression model based on the RGB (“Red,” “Green,” “Blue”) pixel attributes of a scanned DE output of samples of known infection status to a model pathogen (Lettuce big-vein associated virus). Based on the trained and cross-validated algorithm, pixel probabilities of unknown samples could be predicted in scanned DE output images, which would then be reconstituted by pixels having probabilities above a cutoff. The cutoff may be selected at will to yield desirable false positive and false negative rates depending on the question at hand, thus allowing for proper dot classification of positive and negative samples and, hence, accurate diagnosis. Potential improvements and diagnostic applications of the proposed versatile method that translates unique pathogen antigens to the universal basic color language are discussed.

show abstract

“…The advent of 3D printing technology for rapid prototyping enables fast, cost-effective, and easy fabrication of reliable, inexpensive accessories that connect with smartphones for highly sensitive and reliable pathogen detection. Recently, a variety of 3D printing technologies for microfluidic chips, smartphone adaptors, microscope casing, and other supportive add-ons have been described for detection of pathogens. − …”

Section: Smartphone and Its Accessoriesmentioning

confidence: 99%