In the latest blog in our Datawatch series, we look at the role analytics plays in fighting epidemics – from cholera in the 1800s to COVID-19 today.

COVID-19 has dramatically changed the world in a short time, presenting new challenges to world leaders and medical experts. To fight it, we had to use every tool at our disposal, and past experience shows us that advanced analytics is perhaps the most powerful weapon in our arsenal.

You’d be forgiven for thinking that analytics and data science are relatively new tools that give us an edge today in our fight against viral outbreaks. In a sense you would be right, the tools and techniques used by data scientists have evolved considerably in recent years. But analysis has actually been used in this way for over a century, with one of the earliest examples dating back to 1854.

At this time, residents of Victorian London were in the midst of a rampant cholera outbreak that had killed more than 600 people in a week. Little was known about these types of epidemics at the time, and many people assumed that cholera was an airborne disease. However, with some rudimentary data analysis and modeling, Dr. John Snow was able to quickly dispel this misunderstanding.

Long before GIS maps existed, Dr Snow began collecting data on cholera deaths and plotting them, by hand, on a map of London. Using this early form of data visualization, Snow was able to trace the source of the outbreak back to a water pump on Broad Street. The pump handle was replaced and the outbreak was brought to a halt.

Amazingly, these same techniques are still used today – although visualization has improved somewhat. You can see what Dr. Snow’s work would look like if done today, here.

Big data, analytics and the fight against COVID-19

Although the theory behind this technique is still widely used today, we now have tools at our disposal that Dr. Snow could only have dreamed of in 1854. Most notably, enormous computing power that allows us to process huge amounts of data in record time. .

This technology has played a huge role in our battle against the recent COVID-19 pandemic, helping medical experts and world leaders identify the right answers, develop the right solutions, and chart the best paths to recovery. Here are just three ways analytics has helped us fight the pandemic.

Monitoring the spread of the virus

Tracking the spread of COVID-19 has been essential in our fight to mitigate and overcome its impacts. Interestingly, in this case, analytics played a role in tracking COVID-19 before most of us even knew it existed.

In 2019, an AI system owned by an epidemic-prone startup called BlueDot detected some similarities between what the press called “a strain of pneumonia” in Wuhan and the 2003 Sars outbreak.

Since that initial discovery, BlueDot has continued to track the spread of COVID and monitor its movements, using AI to analyze a wealth of unstructured data, including social media posts and news reports.

Social media can actually play a huge role in situations like this. By applying sentiment analysis to unstructured social data, it is possible to track everything from regions where the virus has spread, to attitudes towards proposed legislative responses and government directives.

All of this data can then feed into action plans and help health officials respond more appropriately, fine-tuning the best social distancing and quarantine measures, for example.

Develop vaccines

As the pandemic entered its second year, it became clear that this was not going away. And that meant vaccination was our best chance for a normal life.

The problem is that developing a vaccine usually takes years. Before Pfizer and AstraZenica, the mumps vaccine held the record for the fastest development, and it took nearly half a decade.

However, thanks to advances in analytics and AI, a COVID vaccine was approved and made available for emergency use within a year of the outbreak of the virus.

Much of this was due to global cooperation and the fact that virologists have encountered coronaviruses before. But data analysis and tools like AI and machine learning were also important factors.

For example, AlphaFold, a tool in Google’s DeepMind platform, used AI algorithms to catalog the structure of potential proteins that could help the virus spread – a key part of understanding how a virus works and how it can be contained.

AlphaFold is a state-of-the-art system that can predict the structure of proteins based on their genetic sequence. This system was used to study proteins associated with COVID, before the information was made available to scientists working on the vaccine.

To the same end, AI and natural language processing have played an important role in applying analytics to the open COVID-19 research dataset – a collection of nearly 500,000 scientific papers assembled. worldwide and made available to the global research community. .

Elsewhere, in a lab in Tennessee, the world’s second fastest supercomputer has been analyzing data to try to understand the behavior of the virus, analyzing 2.5 billion genetic combinations to determine how COVID attacks the human body.

Respond at the right time in the right way

COVID-19 has been perhaps the toughest test imaginable for healthcare facilities around the world. With limited resources, difficult decisions had to be made every day. For example, what critical assets are needed at each location? And where and when will hospital beds be needed as the virus spreads through populations?

These problems cannot be solved by flipping through spreadsheets – there is simply too much data, too many variables, and a picture that changes every day. However, with advanced analytics, health officials were able to make these key decisions based on vital, actionable and timely information.

For example, epidemiological models have been useful in predicting the spread of infection across regions, helping healthcare workers predict the potential number of infected people who will require medical treatment – ​​and what that level of treatment will look like.

Predictive simulation and scenario modeling have also been used to help predict the required number of healthcare workers under given scenarios, as well as the strain that outbreaks may place on healthcare services. This data was then directly incorporated into national containment plans.

An example of this in action can be seen at Sheba Medical Center in Israel, where data-driven forecasts are used to optimize resource allocation even before epidemics strike. The center has used machine learning to analyze data related to confirmed cases, deaths, test results, contact tracing and availability of medical resources, to ensure it is ready to do to what awaits us.

The center also conducted a national competition to develop the best technology to predict the rate of deterioration of COVID patients.

A radical change for virology

The scale and speed of spread of COVID-19 is unprecedented. But the scale of our response has been equally impressive. Using the latest analytics techniques, healthcare workers have been able to prepare for unpredictable scenarios, governments have been able to better understand the best actions to keep people safe, and businesses have been able to take measured approaches to adapt. to the world around them.

Amid this pandemic, it’s hard to find many, if any, positives, but the lessons learned during COVID-19 will have a huge effect on how we approach similar events in the future.

Whether developing vaccines, ensuring the right resources are in the right place at the right time, or accelerating our understanding of the situation to keep as many people as possible safe, analysis is able to provide answers to the most complex questions of these present situations. And it’s been doing it since the 1800s.


Nitin Aggarwal is Vice President and Business Head of Analytics at The Smart Cube, a global provider of analytics and procurement intelligence solutions.