The Science Behind Drug Development 

Updated on January 13, 2023

From the discovery of ether’s function as an aesthetic in 1846 to the polio vaccine and beyond, modern medicine has enabled us to prolong life expectancy and improve quality of life dramatically. 

The advancements made in the last hundred years or so specifically can be considered genuine leaps in progress, and the last decade has seen transformative developments in the fields of genomics, stem cell research, cancer therapies, and immunotherapy.

Today, data is at the heart of these advances. And, as we continue to gather more data and develop technologies that can quickly validate, process, and analyze it, the pace of discovery will only accelerate.  

This means huge opportunities for us as a society, and for pharmaceutical companies in particular, with McKinsey estimating that effective big data strategies could generate up to $100 billion in value every year in the US healthcare system alone. 

To see where this value is coming from, this Datawatch blog is dedicated to exploring four key ways analytics is fuelling the science of drug development. 

Accelerating development and treatment with shared resources

Did you know that the average cost of developing a drug is an incredible $985 million? This is a process that requires significant time and resources, and if COVID-19 has taught us anything it’s that sometimes time is not on our side. One thing that is on our side though, is data – lots of it.

Data is the key to developing any new drug, from the initial R&D stages to public trials and beyond. Today, a number of major pharmaceutical players, academics, and government bodies have begun to share their data, making insights more readily available and reducing the costs and time required to bring drugs to market.

One notable example is Project Data Sphere®, an open-source platform that makes cancer treatment data available to all of those who need it. Using advanced analytics, this data is being used to develop new treatments, cut costs, reduce patient enrolment times, quantify the size of tumours, augment test results, expedite approval processes and much more. 

Similar projects are taking place worldwide to help fight other diseases like Alzheimer’s and dementia

Providing personalized treatments

No two patients are the same, so it stands to reason that people will respond differently to treatments. It can be difficult for clinicians to isolate the reasons for this, but thanks to the proliferation of digital medical records and wearable devices, there is now more data than ever to try and pinpoint the root causes.

In fact, scientific advances and access to big data mean we can now develop different drugs to treat people with specific forms of an illness or with rare combinations of different conditions, which is a huge step-change for the industry. Going forward, scientists believe it will be possible to tailor drugs even more precisely to individuals, giving patients the very best chances of positive outcomes. 

Again, the success of these endeavors is dependent on access to data. Of course, data sharing comes with its own security and privacy concerns, but the benefits for society at large are inarguable.

When writing about this in 2020, Forbes quoted Stephanie Reel, CIO of Johns Hopkins Health System, who said: “The next big discovery will come from the use of technology and information. I don’t want us to be too careful and too controlling, because I think there is some risk that we will not make that next big discovery.” 

Gaining new insights through social listening

Social listening, or ‘sentiment analysis’, is nothing new in the wider world of big data analytics, but it is something that is increasingly being adopted by pharmaceutical companies.

By using AI to analyze social media discourse, news reports, and a variety of other sources, it’s possible to tap into a whole world of information that wouldn’t have been available otherwise. 

This technique can be used to identify likely candidates for clinical trials, learn about patient experiences with treatments, and even geo-locate symptoms and outbreaks to help target trends in particular geographies. 

Social listening played a huge part in tracking symptoms and spread during the COVID-19 pandemic, and in the long run it can help us to develop and deploy treatments in a more tactical, controlled, and impactful way.  

A data-driven approach to choosing trial participants

Clinical trials are a vital part of the drug development process, and it’s essential that they provide accurate results – especially when they are so expensive and time consuming to run. The problem is, nine out of ten trials worldwide can’t recruit enough people within their target timeframes. 

With access to big data related to patients, demographics, and previous trial participants, pharmaceutical companies can use AI to accelerate the process of selecting the best people for a particular trial – and, vitally, they can remove human error and oversights from the process. 

Today, a company called Medidata is currently working on this very principle, compiling information from more than 23,000 trials and nearly 7 million patients over the last decade to help clinicians zero in on the best participants. The result? Better trials, faster time-to-insight, and better-quality treatments. 

The future of pharma is data-driven

The pace of change in medicine is rapid and exciting, and, just like in every other area of life, big data and analytics promise to unveil new, transformative opportunities in the coming years.

Patrick Cronin is Vice President of Business Development for The Smart Cube, and Abhishek Jain is Vice President of Analytics and Data Science for The Smart Cube.