COVID-19 Open AI Consortium – Interview with Dr. Stephen Weng, Principal Investigator
The Covid-19 Open AI Consortium (COAI) intends to bring breakthrough medical discoveries and actionable findings to the fight against the Covid-19 pandemic.
COAI aims to increase collaborative research, to accelerate clinical development of effective treatments for Covid-19, and to share all of its findings with the global medical and scientific community. COAI will unite collaborators: academic institutions, researchers, data scientists and industrial partners, to fight the Covid-19 pandemic.
This is the second of three interviews with principal leaders behind COAI. The first interview was with Owkin’s Sanjay Budhdeo, MD, Business Development.
Stephen Weng is an Assistant Professor of Integrated Epidemiology and Data Science who leads the data science research within the Primary Care Stratified Medicine Research Group.
He integrate traditional epidemiological methods and study design with new informatics-based approaches, harnessing and interrogating “big health care data” from electronic medical records for the purpose of risk prediction modeling, phenotyping chronic diseases, data science methods research, and translation of stratified medicine into primary care.
You recently joined the COVID-19 Open AI Consortium (COAI) as a lead principal investigator. Can you discuss what moved you to join this project?
I have been collaborating with Owkin and European partners in projects aimed at improving secondary prevention for acute coronary syndrome for the past year. When Owkin launched the COVID-19 Open AI Consortium leverage their technology, expertise and our infrastructure to contribute to the global fight against COVID-19, this was an obvious choice and a natural fit to join the consortia. We have excellent partners who are leading cardiologists across Europe among our investigator group from our previous consortia. Using these resources and expertise, we could move very quickly and at a pace to launch this consortia within a matter of weeks and ultimately improve our understanding of disease progression, the underlying aetiology and risk factors in our populations.
A percentage of the population that is afflicted with COVID-19 show signs of cardiovascular damage. What type of heart related problems are being seen?
There is evidence emerging that cardiovascular risk factors and cardiovascular disease is a major contributor to the severity of the disease. A recent analysis of 17000 COVID-19 cases which required hospitalisations in the UK identified that heart disease was present in 29% of all hospitalised cases. Underlying cardiovascular risk factors including increasing age, high blood pressure, obesity, hypertension and type 2 diabetes contributes significantly to disease severity.
Do you believe that we currently have any type of understanding as to why COVID-19 causes this type of heart damage?
There are still many questions which need to be answered around epidemiology around the progression and severity of COVID-19, in particular regarding patients with heart disease. Patients with heart disease are at increased risk of experience severe illness which may require cardiorespiratory support in an intensive care unit. The severity of COVID-19 and progression towards severe outcomes is likely driven by some direct injury to the cardiovascular system, which may be acute. The exact type of cardiac injury in COVID-19 patients requires further investigation.
What will be your role with COAI?
I am an epidemiologist and data scientist with a research focus on prognosis of cardiovascular outcomes. Much of my work is a deep-dive in very large datasets to answer these clinical questions. In my role, as well as directly trying to answer some of these important research questions by leveraging my ability to access large population datasets, I am also trying to facilitate other academics and colleagues to contribute to our consortia.
What type of people do we need to join the COAI project in order to maximize its efficacy?
Not only is it important to obtain larger numbers from more scientists and clinical colleagues contributing data but also we need to increase the diversity of our data resources. We know COVID-19 has a wide spectrum of severity from asymptomatic individuals to very severe disease that results in death. Different types of data across the spectrum of the health care settings from primary to secondary care are needed to answer these questions about disease progression and severity.
You are currently an Assistant Professor of Integrated Epidemiology and Data Science who leads the data science research within the University of Nottingham’s Primary Care Stratified Medicine Research Group. Can you discuss possible ways big data can be used to target COVID-19 with the current information that we have?
We have some major big datasets we can leverage. The major wins have been recent investments into data linkage has really been put in action and we are starting to see these initiatives bearing major fruit. In fact, we are embarking on obtaining access to large population cohorts which have now been linked to primary care, hospital records, death registries, and COVID-19 testing data. Moreover, these data have opportunities to investigate genetic influences on COVID-19 outcomes. These linkages are only made possible with the rise of big data linkages and large population biobanks. Due to the amount of data and variables collates, the AI models that Owkin has developed and perfected are indeed very useful to efficiency analyse data at speed to derive meaningful insight.
What information do we need to gather to make precision medicine an effective tool in treating COVID-19 patients?
More diverse array of data types, including imaging, genetic, biomarkers alongside clinical features and patient demographics.
In a perfect world, what type of data should be collected from COVID-19 patients?
In such a novel disease like COVID-19, I don’t think there is and should be a maximum ceiling of data needed. There is a term “we don’t know what we don’t know yet”, so the more types of data and information we can collate now will be may be useful in the future. For instance, how many genomic advances knowledge have we experienced because we were able to sequence data and keep it accessible for researchers in bio banks? I see this occurring COVID-19. If we create a diverse and large data resource now, I have no doubt there will be new findings emerging to help our understanding in the future.
Should we also be collecting data from the segment of the population that is immune to COVID-19, in order to better understand what makes them immune?
In epidemiology, the choice of the comparator group is extremely important. Risk in many senses is relative. If our baseline starts with admitted to hospital, then we are also only understanding disease aetiology in those who present with more severe symptoms. I think a better understanding of asymptomatic individuals and what makes them asymptomatic towards COVID-19 is absolutely necessary. How many therapeutics are developed due to investigating gain of function mutations or loss of function mutations that naturally occur in populations.
Thank you for the fantastic interview. Readers who wish to learn more, may read our article describing the COAI project.
The first interview in this series was with Owkin’s Sanjay Budhdeo, MD, Business Development.
The third interview in this series was with Folkert W. Asselbergs, Principal Investigator
You may also visit the Covid-19 Open AI Consortium website.