Data-driven life science: understanding the pandemic through data

Our Insights
Data-driven life science: understanding the pandemic through data
Posted on

SARS-COV-2 is a biological enemy, but the COVID-19 pandemic can be — and actually has been — fought with digital measures. Advanced analytics and data management made it possible to track the way coronavirus is spreading, know its tactics, its structure, and the way its features make it so efficient and dangerous.

There is a curse. They say: May you live in interesting times.
Terry Pratchett, Interesting Times

Currently, leading companies and institutions in the pharmaceutical sector are working on vaccines and effective treatments for the COVID-19 disease. They would not be able to work at such a high pace without the use of digital technologies and data.

Because it concerns business, health, and people’s lives at global scale now, never before has fast and reliable access to data been so important both globally and locally. And thus, never before has the need to digest data, process it and produce meaningful insights been so pressing for so many. Suddenly, everyone is trying to understand how such a disruption is impacting their nation, society, neighborhood, business.

DataSphere nowadays

Just to remind you and keep it in the backgroundin 2020, humanity will create and consume nearly twice as much data as in 2018. As IDC indicates in their updated Global DataSphere forecast released in May, “the next three years of data creation and consumption will eclipse that of the previous 30 years”.

The gain is huge and impressive, even if we bear in mind that almost 40% of the data will be generated by entertainment (video streaming). But at a time when we binge-watch more or less interesting series during the lockdown, or when (working from home) we hold endless teleconferences back-to-back, data engineers, developers and data scientists are working with life science experts to find a way to stop the pandemic.

Data-driven tracking

It was Google that paved the way for the use of big data to track epidemics. The idea was to collect millions of users’ behaviors and use Google search queries to determine if there was a flu-like illness present in a population. Although Google Flu Trends actually failed, the way it worked was inspirational for infectious-disease researchers: Twitter was used in Brazil to get high-resolution data on the spread of the dengue fever in the country. Similarly, data from Google and Twitter helped to predict the spread of the Zika virus in Latin America.

Now, Google and Apple are working together to help with contact tracing and governments in the US, UK, and even the European Union, are relying on these technologies to fight COVID-19.

Vaccine Development

With the help of big data, scientists are working on new ways to develop vaccines, with the so-called reverse vaccinology being one of the trends. This method of vaccine development is fast, but it requires screening the entire pathogen genome. The “Vaccinology 3.0” approach, as it is also called,
is a world of huge volumes of data; it’s definitely worth reading about it in this truly fascinating article by Deepak Karunakaran.

Also: testing, production, and even delivering vaccines (it is fundamental to maintain a cold chain from the manufacturer to the point of use, and to keep temperatures within a precise range of values) require a data-driven approach. Special digital apps are designed and released to manufacturing sites to optimize their operation and limit the number of staff needed physically on site. Special software modules are being designed exclusively for the optimization of the Covid-19 vaccine production to achieve an unprecedented parallelism and satisfy global demand when the vaccine is finally ready.

There are a myriad more good examples and practices illustrating the power of data analytics to fight a pandemic. Governments, health and science organizations, communities and health professionals are conducting analyses to track the virus and simulate future spread scenarios. Likewise, companies are gathering data and using analytical tools to assess the extent of financial difficulties and delinquency risk, perform process planning, adjust the scale of production, gather insights, implement employee protection, make employment decisions or re-create customer support plans. All that data and effort is needed to make informed decisions and be able to manage business disruptions that have arisen in this crisis.

Data quality and sharing as a secret weapon

Data-sharing during the pandemic has become crucial, as “The Lancet” stressed as early as May this year.
Data is constantly being gathered in electronic health records and in laboratories, and we shouldn’t let it become dark data — considering SARS-CoV-2, the insight we could gain from a pooled, publicly available dataset analyzed by researchers in academic institutes and the industry is invaluable.

But sharing the kind of data that has been so important in the response to Covid-19 is not as simple as popping it into an email and hitting “Send”. It requires an advanced system and strategy. First of all, health data contains numerous personal and sensitive details. This makes it especially difficult to share, even though, or perhaps because, a lot of this data is collected by local hospitals or health authorities. Trying to find a solution, way back in April, the European Commission established the Covid-19 Data Platform to allow research data to be rapidly collected and widely shared, as part of their ERAvsCorona Action Plan. Check Horizon Magazine to read more about European Union’s fight against Coronavirus.

Crucially, data sharing is important not only for public health institutions, authorities or research centers. According to the 2019 Good Pharma Scorecard, big pharma data-sharing around clinical research appears to be on the increase. The biennial study, last released in June 2019, finds that 95 percent of patient trial results are now publicly available within six months of US FDA approval.
At 12 months, 100 percent public results for new drugs have been approved since 2015.

As the world is becoming increasingly digital, so is data. Data sharing from the perspective of life science companies is not only a business issue. As we can see, it is often clearly responsible for the welfare of humanity at large. The coronavirus pandemic is not the first one to have hit us, and so the sooner we establish data and data-sharing standards, and put quality over quantity, the better for all of us.

Today’s fast-changing social, business and regulatory landscape forces companies to be always on their toes to continuously meet the shifting criteria of compliance and integrity with all stakeholders and decision makers. To our aid we call advanced analytics and true data-driven decision making.

"At a time when we binge-watch more or less interesting series during the lockdown, or we hold endless teleconferences back-to-back, data engineers, developers and data scientists are working with life science experts to find a way to stop the pandemic. Data is constantly being gathered in electronic health records and in laboratories, and we shouldn’t let it become dark data — considering SARS-CoV-2, the insight we could gain from a pooled, publicly available dataset analyzed by researchers in academic institutes and the industry is invaluable. "

Piotr Carlos Pielasa Chief Solutions Officer,
Vice President of the Management Board
Go to Expert Spotlight