Skip to main content
KBS_Icon_questionmark link-ico

Go to…

Rapid implementation of mobile apps for real-time epidemiology of COVID-19

A new paper in Science shows how researchers used a prediction model and have demonstrated the potential utility of the COVID Symptom Tracker to collect data not only for long-term studies, but also for immediate public health planning.

gigi-MEwhzMxZJac-unsplash

Since its release, the COVID-19 Symptom Study app by Zoe, has collected self-reported health data of almost 2.5 million unique users and can potentially predict COVID geographical hotspots up to a week in advance of traditional measures such as positive tests, hospitalisation or mortality.  

The School of Biomedical Engineering & Imaging Sciences has been collaborating with Zoe and the KCL Twins Department of Twin Research & Genetic Epidemiology to analyse the data generated by the COVID Symptom Study app. Their process was published in leading journal Science this week.  

The rapid pace of the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic (COVID19) has presented challenges to the collection of population-scale data to address this global health crisis.  

Although many COVID symptom tracking apps have been developed and released and offer critical public health insights, they are often not tailored for the type of scalable longitudinal data capture that epidemiologists need to perform comprehensive, well-powered investigations. 

To meet this challenge, this group of researchers established a multinational collaboration, the COronavirus Pandemic Epidemiology (COPE) Consortium, comprised of leading investigators from several large clinical and epidemiological cohort studies.  

COPE brings together a multidisciplinary team of scientists with expertise in big data research and translational epidemiology to interrogate the COVID-19 pandemic in the largest and most diverse patient population assembled to-date. 

As a result, the researchers say that their app initiative offers critical proof-of-concept for the repurposing of existing approaches to enable rapidly scalable epidemiologic data collection and analysis which is critical for a data-driven response to this public health challenge. 

Researchers from the School of Biomedical Engineering & Imaging Sciences assisted with the prediction modelling for the application. Head of School Professor Seb Ourselin, said this application is reflective of successful collaboration during times of adversity. 

Working across continents with leading researchers, we have developed an application which provides some of the most critical rapidly actionable insights about this disease to help not only health workers or public health experts, but the everyday person as well. The team will also continue to engage with underrepresented populations to gather more data and produce even more of these critical insights of an even larger participant cohort.– Professor Sebastien Ourselin

While the researchers acknowledge that smartphone app users do not provide a random sample of the population, an inherent limitation of any epidemiological study that relies on voluntary participation, they are currently planning additional studies using a broader sample of individuals who will undergo uniform COVID-19 testing to further validate their approach to symptom-based modelling of incidence.  

“These data demonstrate compelling evidence for the potential predictive power of our approach, which will improve as more data are collected to inform the model and they highlight the potential utility of real-time symptom tracking to help guide allocation of resources for testing and treatment as well as recommendations for lockdown or easement in specific areas,” the researchers wrote. 

With additional data collection, they will also apply machine learning to identify novel patterns that emerge in dynamic settings of exposure, onset of symptoms, disease trajectory, and clinical outcomes. 

In the future they will also be uniquely positioned to investigate long-term outcomes of COVID-19, including mental health, disability, mortality, and financial outcomes.