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

Seungmin Lee; Sunmok Kim; Dae Sung Yoon; Jeong Soo Park; Hyowon Woo; Dongho Lee; Sung Yeon Cho; Chulmin Park; Yong Kyoung Yoo; Ki  Baek Lee; Jeong Hoon Lee

doi:10.1038/s41467-023-38104-5

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

Seungmin Lee, Sunmok Kim, Dae Sung Yoon, Jeong Soo Park, Hyowon Woo, Dongho Lee, Sung Yeon Cho, Chulmin Park, Yong Kyoung Yoo, Ki Baek Lee, Jeong Hoon Lee

School of Biomedical Engineering

Research output: Contribution to journal › Article › peer-review

31 Citations (Scopus)

Abstract

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.

Original language	English
Article number	2361
Journal	Nature communications
Volume	14
Issue number	1
DOIs	https://doi.org/10.1038/s41467-023-38104-5
Publication status	Published - 2023 Dec

Bibliographical note

Publisher Copyright:
© 2023, The Author(s).

ASJC Scopus subject areas

General Chemistry
General Biochemistry,Genetics and Molecular Biology
General Physics and Astronomy

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1038/s41467-023-38104-5

Cite this

@article{cd41cd52babd4899a827d560c7676c2b,

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

abstract = "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 (SMARTAI-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 SMARTAI-LFA was maintained at over 99% while there was a significant decrease in human accuracy, indicating the reliable performance of SMARTAI-LFA. We envision a smartphone-based SMARTAI-LFA that allows continuously enhanced performance by adding clinical tests and satisfies the new criterion for digitalized real-time diagnostics.",

author = "Seungmin Lee and Sunmok Kim and Yoon, {Dae Sung} and Park, {Jeong Soo} and Hyowon Woo and Dongho Lee and Cho, {Sung Yeon} and Chulmin Park and Yoo, {Yong Kyoung} and Lee, {Ki Baek} and Lee, {Jeong Hoon}",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

month = dec,

doi = "10.1038/s41467-023-38104-5",

language = "English",

volume = "14",

journal = "Nature communications",

issn = "2041-1723",

publisher = "Nature Research",

number = "1",

}

TY - JOUR

T1 - Sample-to-answer platform for the clinical evaluation of COVID-19 using a deep learning-assisted smartphone-based assay

AU - Lee, Seungmin

AU - Kim, Sunmok

AU - Yoon, Dae Sung

AU - Park, Jeong Soo

AU - Woo, Hyowon

AU - Lee, Dongho

AU - Cho, Sung Yeon

AU - Park, Chulmin

AU - Yoo, Yong Kyoung

AU - Lee, Ki Baek

AU - Lee, Jeong Hoon

PY - 2023/12

Y1 - 2023/12

N2 - 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 (SMARTAI-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 SMARTAI-LFA was maintained at over 99% while there was a significant decrease in human accuracy, indicating the reliable performance of SMARTAI-LFA. We envision a smartphone-based SMARTAI-LFA that allows continuously enhanced performance by adding clinical tests and satisfies the new criterion for digitalized real-time diagnostics.

AB - 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 (SMARTAI-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 SMARTAI-LFA was maintained at over 99% while there was a significant decrease in human accuracy, indicating the reliable performance of SMARTAI-LFA. We envision a smartphone-based SMARTAI-LFA that allows continuously enhanced performance by adding clinical tests and satisfies the new criterion for digitalized real-time diagnostics.

UR - http://www.scopus.com/inward/record.url?scp=85153687273&partnerID=8YFLogxK

U2 - 10.1038/s41467-023-38104-5

DO - 10.1038/s41467-023-38104-5

M3 - Article

C2 - 37095107

AN - SCOPUS:85153687273

SN - 2041-1723

VL - 14

JO - Nature communications

JF - Nature communications

IS - 1

M1 - 2361

ER -

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

Abstract

Bibliographical note

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this