Skip to main content


The COVID-19 pandemic has upended the life science industry and has catalyzed the use of approaches that will, in due course, allow us to build a more responsive and therefore resilient healthcare ecosystem. For example, in response to the urgent need for fast insights and global collaboration, we have seen a significant increase in demand for preprints, or publicly accessible scientific manuscripts that have not yet been certified by peer review. Preprints are valuable for offering a rapid, albeit unvetted, view of new research potentially coming down the pipeline, helping organizations inform their own research approaches in response to recent, relevant activity.

The beauty of preprints is in their ability to openly communicate new research with virtually no lag time. That’s a stark contrast to work published via peer review, a process with a median lapse time of 166 days. After a brief quality-control inspection, a preprint manuscript is posted without peer review and can be viewed without charge by anyone in the world. Of course, peer review remains an essential process to ensuring quality research, which is why many manuscripts are submitted for peer review and preprint publication in tandem.

"The greatest glory in living lies not in never falling, but in rising every time we fall." - Nelson Mandela

Difficult observations

It is never easy to observe someone hit “rock bottom”, especially when it is more of a routine than a one-time fall. Yet - so many of us have experienced those we love repeatedly falling into the familiar pattern of addiction. There are many forms of substance abuse. Some are more socially accepted, like alcohol consumption and tobacco use. Others like opioids, and other narcotic substances, are more taboo.

Whatever the flavor, substance abuse rarely appears in one day. There are patterns when abuse is forming and common clues once the addiction is established. The current pandemic has pushed many into a state of ill-health and substance abuse. Many nations are experiencing booming alcohol sales. And according to a recently published article in the Journal of the American Medical Association (JAMA),since March 2020 US hospitals are reporting an increase in substances found in urine samples nationwide: 67% fentanyl, 23 % methamphetamines, and 19% in cocaine.

Early identification is key. More so than we ever realized. For example, as a physician, I was taught that opioids are safe for short-term use. But the meaning of the term ‘short-term’ is shrinking drastically – some studies show that dependency starts within just a handful of days. As a former research scientist, I have reviewed thousands of patient charts - and the majority of opioids I have seen prescribed are for a minimum of five to seven days.

Drug safety is, understandably, a prime concern for pharma organizations, regulators, health authorities and patients alike. While there is always risk associated with any medication or treatment, the aim is always to understand any risk so that it can be handled or mitigated appropriately.

The holy grail is, then, how can we predict risk effectively? This is a huge focus of many research initiatives and is being address at many levels – drug target, molecule, patient, population. With the recent flourishing of AI/ML, we’ve seen a blossoming of models to enable risk prediction.

Pilot paper demonstrates use of NLP for adverse events to feed machine learning

There is ongoing work at the FDA to develop models that can predict adverse events (AEs) using post-market safety data, for new drugs coming on the market. Two papers published this year use a combination of AI/ML tools, including NLP, ensemble models and classification algorithms. Both papers build upon pilot work. The pilot study of six drugs demonstrated that pharmacological target AE profiles, based on marketed drugs, can be used to predict unlabelled adverse events for a new drug at the time of approval.

Finding the missing pieces of the puzzle

I think one of the most-used phrases of 2020 is “these are unprecedented times.”

I did hear another phrase recently that I liked: it is a “dark privilege” to be living through this global pandemic. No doubt, we live in an interesting time! In decades to come, people will talk about 2020 and the impact of coronavirus on so many global factors – economy, climate, travel, and of course population and individual health. As well as the dark clouds, there is of course light – and much light comes from the collaborative efforts of institutions, healthcare organizations and governments to find the best responses to this challenge, particularly in the areas of drug repurposing and vaccine development.

And this, to me, is where natural language processing-based text mining comes in. Whenever scientists, researchers and clinicians are faced with a challenge, one critical asset is identifying as much information about the problem as possible. Whatever information there is, locally and globally, that can be found, gathered and understood, will enable the right decisions to be taken. Relevant information on the biology of SARS-CoV2, from COVID-19 as a disease, patient demographics and co-morbidities, global or regional spread, and possible drugs that might treat the symptoms and impacts of this disease is all just the tip of a data iceberg. Much of this data exists in unstructured text: scientific papers, preprints, clinical trial records, adverse event reports, electronic healthcare records, even news feeds and social media can all provide information on epidemiological factors, for example.

Pharmaceutical leaders, from therapeutic experts to medical affairs directors, face challenges staying abreast of the latest development and research – leading them to spend significant time searching for information, rather than driving strategy and direction across the organization. As a result, they sometimes end up making decisions without having the full picture – potentially compromising innovation opportunities or delaying a response to competitive forces.

In an ideal world, leaders should be able to focus on key initiatives for their teams and organizations, rather than spend valuable time gathering and sorting through information. They need access to information that delivers the full view of their product or therapy area landscape.

The NLP Insights Hub is the latest evolution in our NLP technology offerings, designed to help pharma professionals solve their data deluge challenges. The NLP Insights Hub provides an end-to-end offering for business users, combining core NLP to extract critical information from text, with the power of dashboards to bring the data to life and enable understanding. Bringing together the key pieces of information from a wide range of structured and unstructured data sources in one hub, with visual analytics on top, enables efficient insights development, sparks innovation and optimizes decision-making.

Ready to get started?

Request a demo

Questions? Ask our experts