Testing the Accuracy of a Digital Test to Diagnose Covid-19

• ClinicalTrials.gov Identifier: NCT04407585
• Recruitment Status: Recruiting
• First Posted: May 29, 2020
• Last Update Posted: March 31, 2022
• Sponsor: King's College London
• Collaborators: Zoe Global Limited; Department of Health, United Kingdom
• Information provided by (Responsible Party): King's College London

Study Description

Brief Summary:

The Covid-19 viral pandemic has caused significant global losses and disruption to all aspects of society. One of the major difficulties in controlling the spread of this coronavirus has been the delayed and mild (or lack of) presentation of symptoms in infected individuals, and the insufficient Covid-19 testing capacity in the UK. This warrants the development of alternative diagnostic tools that reliably assess Covid-19 infection in the early stages of infection, while also being low- cost, low-burden, and easily administered to a wide proportion of the population.

This study aims to validate machine learning models as a diagnostic tool that predicts infection with SARS-CoV-2 based on app-reported symptoms and phenotypic data, against the 'gold-standard' swab PCR-test. This study will take place within the Covid Symptom Study app, the free symptom tracking mobile application launched in March 2020.

Condition or disease	Intervention/treatment
Covid-19	Diagnostic Test: Covid-19 swab PCR test

Detailed Description:

The Covid-19 viral pandemic has caused significant global losses and disruption to all aspects of society (including health, education, and business and economic security). One of the major difficulties in controlling the spread of this coronavirus has been the delayed and mild (or lack of) presentation of symptoms in infected individuals. Moreover, there is insufficient Covid-19 testing capacity in the UK, and only moderate accuracy of such tests at confirming coronavirus infection. Together, these obstacles have led to countless unknown coronavirus cases going unobserved and fuelling the viral spread in the population, by compromising the stringency of self- isolation measures undertaken by infected individuals who may have otherwise curbed or prevented their transmission of the virus. The profound and widespread cost of the continuing Covid-19 progression, coinciding with the lack of testing capacity, warrants the development of alternative diagnostic tools that reliably assess Covid-19 infection in the early stages of infection, while also being low- cost, low-burden, and easily administered to a wide proportion of the population.

The free symptom-monitoring app 'Covid Symptom Study' was launched in mid-March by health technology start-up Zoe Global Ltd, and is currently being used in the UK, US and Sweden, with more than 2.7 million users in the UK alone who use the app to self-report their Covid-19 symptoms. Upon registering to use the app, users are asked to report demographic and phenotypic data such as age, sex, BMI, ethnicity, contact with infected individuals (through a healthcare professional capacity), smoking behaviour, existing health conditions, among other information. From then on, users are asked to report, on a daily basis, their presentation of symptoms attributable to Covid-19 (or lack thereof) through the use of app-administered questionnaires, thus enabling real-time tracking of disease progression across the UK. The app also allows users to report their Covid-19 test results, thus enabling the development of prediction algorithms based solely on self-reported user data to predict the presence of infection in untested users.

On behalf of Zoe Global Ltd, the UK Department of Health and Social Care with support from the UK's Chief Scientific Advisor has committed to test up to 10,000 app-users per week for infection with SARS-CoV-2 across England and Northern Ireland, for the purpose of rapidly improving the accuracy of symptom-based predictions. Similar testing allowance may follow in Scotland and Wales.

Symptomatic app-users will be asked to get tested for SARS-CoV-2 infection, using the popular swab and qRT-PCR technique, and asked to report their test results in the app, while continuing to log their symptoms.

This validation study, conducted at King's College London, aims to validate the sensitivity and specificity of machine learning models as a diagnostic tool that predicts infection with SARS-CoV-2 based on app-reported symptoms and phenotypic data, against the 'gold-standard' swab PCR-test, by utilising the Covid Symptom Study app as a research platform.

It is hypothesised that by training the symptom-based models using swab test results and through multiple model iterations following continuous data input from reporting and tested app users, predictions of infection will be made with considerable accuracy, thus enabling the Covid Symptom Study app to be used as a diagnostic tool that alleviates the strain of testing capacity in the UK while being easily accessible and posing low user burden.

Study Design:

Due to the rapidly developing and uncertain duration and intensity of the Covid-19 pandemic, the present study design is prospective and one that enables regular iteration on prediction models and continuous accumulation of validation data. The study consists of a series of phases, each lasting 14 days. Before the start of each phase (day 0), a set of machine learning models will be frozen and submitted for validation on data collected during this and subsequent phases.

Machine learning algorithms improve with increasing data. Therefore, validation phases will continue as long as tests are available and app users consent to joining the study. Due to the uncertainty around the progression of UK infection rates, the validation study will be continue whilst it is of value to public health.

A detailed statistical analysis plan is described in the document attached to this record. A record of all machine learning models used for validation will be regularly updated on GitHub (https://github.com/zoe/covid-validation-study).

Study Design

• Study Type: Observational
• Estimated Enrollment: 1000000 participants
• Observational Model: Cohort
• Time Perspective: Prospective
• Official Title: Validation of Machine Learning (ML) Models as Diagnostic Tools to Predict Infection With SARS-CoV-2
• Actual Study Start Date: June 1, 2020
• Estimated Primary Completion Date: May 10, 2023
• Estimated Study Completion Date: May 10, 2023

Groups and Cohorts

Group/Cohort	Intervention/treatment
Covid-19 Symptom Study app-user; UK-based Covid-19 Symptom Study primary app-user completing self-reports in the app	Diagnostic Test: Covid-19 swab PCR test; Participants satisfying machine learning test criteria will be asked to take a swab test for Covid-19.

Outcome Measures

Primary Outcome Measures :

1. SARS-CoV-2 infection [ Time Frame: 3 days ]
   Likelihood of infection with Covid-19, based on app-reported symptoms
2. SARS-CoV-2 infection [ Time Frame: 1 day ]
   Active infection with Covid-19 as assessed by PCR swab test

Eligibility Criteria

• Ages Eligible for Study: 18 Years and older (Adult, Older Adult)
• Sexes Eligible for Study: All
• Sampling Method: Non-Probability Sample

Study Population

The study population includes individuals are UK-based primary users of the Covid Symptom Study app, who provide informed consent to participate.

Criteria

Study Inclusion Criteria - app users will be eligible to join the study if they:

• Are based in the UK (are using the UK version of the Covid-19 Symptom Study app, and have listed a UK postcode)
• Are the primary app user (are reporting directly for themselves)
• Are at least 18 years of age
• Have not tested positive for a Covid-19 test before (but may have been tested)

Study Exclusion Criteria - participants are ineligible for the study if they:

• Do not meet inclusion criteria
• Do not provide informed consent to participate

Participants will be subject to further screening to identify them as eligible for swab testing during the course of the study.

Swab inclusion criteria - participants will be eligible for swab testing if they:

• Have reported in the app at least once in the previous 3 days (days -2 to 0), and at least two times in the previous 9 days (days -8 to 0). All reports must be healthy (i.e. not experiencing any symptoms).
• On the previous day (day 1), have reported that they are experiencing at least one symptom described in the app. Symptoms in the app are updated when deemed appropriate by study investigators using evidence based reports in the scientific and medical field.
• Have answered the phenotype fields required for the prediction model with physiologically plausible values.

Swab exclusion criteria - participants are ineligible for swab testing if they:

• Are asymptomatic
• Do not satisfy the inclusion criteria for testing.

Insufficient testing capacity:

If insufficient testing capacity is available for the study population as described, then recruitment will be prioritised according to:

• Firstly, most recent final healthy report before reporting symptoms
• Secondly, highest number of healthy reports during the previous 9 days before reporting symptoms
• Thirdly, randomised selection to stratify between participants of equal priority according to the first two rules above.

Excess testing capacity:

If excess testing capacity is available beyond the study population as described, then inclusion criteria will be expanded in order to adequately sample across under-represented population groups.

Specifically, on day 7 of each validation phase, investigators will assess:

• What excess testing capacity is available, if any

• Which subgroups are under-represented compared to their proportion in the UK population (as best as can be established given that some participants may not have completed some phenotype fields):

  (i) Age decade (ii) Sex (iii) Ethnicity (iv) BMI category

For underrepresented groups, investigators may additionally recruit participants with only one report during the previous 3 days (days -2 to 0) and no other report during the previous 9 days (days -8 to 0).

Contacts and Locations

Contacts

Contact: Inbar Linenberg, MSc; +447791871699; inbar.linenberg@kcl.ac.uk

Locations

United Kingdom

King's College London; Recruiting

London, United Kingdom, SE1 9NH

Contact: Inbar Linenberg, MSc +447791871699 inbar.linenberg@kcl.ac.uk

Principal Investigator: Tim Spector

Sub-Investigator: Sarah Berry

Sub-Investigator: Claire Steves

Sub-Investigator: Sebastien Ourselin

Sub-Investigator: Peter Sasieni

Sub-Investigator: Andrew Chan

Sponsors and Collaborators

King's College London

Zoe Global Limited

Department of Health, United Kingdom

  Study Documents (Full-Text)

Documents provided by King's College London:

Statistical Analysis Plan  [PDF] May 26, 2020

More Information

• Responsible Party: King's College London
• ClinicalTrials.gov Identifier: NCT04407585
• Other Study ID Numbers: Covid-19 Validation Study
• First Posted: May 29, 2020
• Last Update Posted: March 31, 2022
• Last Verified: March 2022

Individual Participant Data (IPD) Sharing Statement:

• Plan to Share IPD: No

• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No

Keywords provided by King's College London:

Covid-19; Machine learning; Covid-19 diagnostic

Additional relevant MeSH terms:

COVID-19; Respiratory Tract Infections; Infections; Pneumonia, Viral; Pneumonia; Virus Diseases; Coronavirus Infections; Coronaviridae Infections; Nidovirales Infections; RNA Virus Infections; Lung Diseases; Respiratory Tract Diseases