lancet-header

Preprints with The Lancet is a collaboration between The Lancet Group of journals and SSRN to facilitate the open sharing of preprints for early engagement, community comment, and collaboration. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early-stage research papers that have not been peer-reviewed. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. The findings should not be used for clinical or public health decision-making or presented without highlighting these facts. For more information, please see the FAQs.

Machine Learning for Determining Lateral Flow Device Results in Asymptomatic Population: A Diagnostic Accuracy Study

29 Pages Posted: 21 Jun 2021

See all articles by AI LFD Consortium

AI LFD Consortium

Independent

Robert Banathy

Government of the United Kingdom - NHS Test and Trace

Mark Branigan

Government of the United Kingdom - NHS Test and Trace

Paul Lewis-Borman

Government of the United Kingdom - NHS Test and Trace

Nishali Patel

Government of the United Kingdom - NHS Test and Trace

Lennard Lee

Government of the United Kingdom - NHS Test and Trace

Tom Alan Fowler

Government of the United Kingdom - NHS Test and Trace; Government of the United Kingdom - Department of Health and Social Care (DHSC); Genomics England

Camila C. S. Caiado

Durham University

Anna Dijkstra

Sensyne Health

Piotr Chudzik

Sensyne Health

Paria Yousefi

Sensyne Health

Avelino Javer

Sensyne Health

Bram Van Meurs

Sensyne Health

Lionel Tarassenko

Sensyne Health

Benjamin Irving

Sensyne Health

Celina Whalley

University of Birmingham

Neeraj Lal

University of Birmingham

Helen Robbins

University of Birmingham

Elaine Leung

University of Birmingham

Andrew D. Beggs

University of Birmingham - Institute of Biomedical Research

More...

Abstract

Introduction: Rapid antigen tests, in the form of lateral flow devices (LFD) allow testing of a large population for SARS-CoV-2 rapidly either on an asymptomatic or symptomatic basis and have been demonstrated to reduce transmission when used correctly. Compared to real time quantitative PCR (RT-qPCR), LFD have a different sensitivity range to viral load, and can be used to self-test, which can present challenges for lay users to interpret especially at low viral loads. In order to reduce the variability seen in device interpretation, we designed and tested an AI algorithm based on machine learning.

Methods: A machine learning (ML) algorithm was trained on a combination of artificially hybridised LFDs from a range of test conditions and viral dilutions and real-world LFD data linked to RT-qPCR results. Two sub-studies were carried out. In the first, participants were recruited from asymptomatic test sites (ATS) in the community and in the second from health care workers undertaking self-testing using LFDs at home. A panel of trained clinicians were used to resolve discrepancies between the algorithm and the ATS/self-report result. Standard estimates of diagnostic precision were applied, comparing ATS and self-report results to the diagnostic algorithm, with and without resolution of discrepancies.

Results: In total, 115,316 images were returned by the ATS and self-test users (59,450 ATS, 50,999 self-test). In the ATS sub study, use of the AI algorithm increased sensitivity compared to a human reader from 92.08% to 97.6% (95% CI 93.20-99.51%) and specificity from 99.85% to 99.99% (95% CI -99.90%), correctly identifying another 30 positive images compared to the submitted result. In the self-read sub study, sensitivity increased from 16.00% to 100% (95% CI 90.2-100%), predominantly due to detection of faint bands representing low viral loads, and specificity from 99.15% to 99.40% (95% CI 99.33-99.47%), with an additional 32 positive images correctly identified compared to the submitted result.

Conclusion: An ML-based classifier of LFD results outperforms human reads in asymptomatic testing sites and self-reading.

Clinical Trial Registration Details: This study is registered with the ISRCTN registry (reference number 39894, https://www.isrctn.com/ISRCTN30075312.

Funding Information: The study was funded by NHS Track and Trace. ADB is funded by an CRUK Advanced Clinician Scientist Award (ref C31641/A23923).

Declaration of Interests: There are no competing interests.

Ethics Approval Statement: Ethical approval was sought from the Public Health England Research Ethics committee, who confirmed that the study was exempt from ethical approval, as the study was purely observational with the AI result not being returned to the user.

Suggested Citation

Consortium, AI LFD and Banathy, Robert and Branigan, Mark and Lewis-Borman, Paul and Patel, Nishali and Lee, Lennard and Fowler, Tom Alan and Caiado, Camila C. S. and Dijkstra, Anna and Chudzik, Piotr and Yousefi, Paria and Javer, Avelino and Van Meurs, Bram and Tarassenko, Lionel and Irving, Benjamin and Whalley, Celina and Lal, Neeraj and Robbins, Helen and Leung, Elaine and Beggs, Andrew D., Machine Learning for Determining Lateral Flow Device Results in Asymptomatic Population: A Diagnostic Accuracy Study. Available at SSRN: https://ssrn.com/abstract=3861638 or http://dx.doi.org/10.2139/ssrn.3861638

AI LFD Consortium

Independent

Robert Banathy

Government of the United Kingdom - NHS Test and Trace

England
United Kingdom

Mark Branigan

Government of the United Kingdom - NHS Test and Trace

England
United Kingdom

Paul Lewis-Borman

Government of the United Kingdom - NHS Test and Trace

England
United Kingdom

Nishali Patel

Government of the United Kingdom - NHS Test and Trace

England
United Kingdom

Lennard Lee

Government of the United Kingdom - NHS Test and Trace

England
United Kingdom

Tom Alan Fowler

Government of the United Kingdom - NHS Test and Trace ( email )

England
United Kingdom

Government of the United Kingdom - Department of Health and Social Care (DHSC) ( email )

United Kingdom

Genomics England ( email )

United Kingdom

Camila C. S. Caiado

Durham University

Old Elvet
Mill Hill Lane
Durham, Durham DH1 3HP
United Kingdom

Anna Dijkstra

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Piotr Chudzik

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Paria Yousefi

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Avelino Javer

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Bram Van Meurs

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Lionel Tarassenko

Sensyne Health ( email )

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Benjamin Irving

Sensyne Health

Science Park, Schrödinger Building
Oxford, OX44GE
United Kingdom

Celina Whalley

University of Birmingham

Neeraj Lal

University of Birmingham

Helen Robbins

University of Birmingham

Elaine Leung

University of Birmingham

Andrew D. Beggs (Contact Author)

University of Birmingham - Institute of Biomedical Research ( email )

United Kingdom

Click here to go to TheLancet.com

Paper statistics

Downloads
746
Abstract Views
4,734
PlumX Metrics