Leveraging data science to accelerate clinical trial results

Recruiting patients has been a challenge for pharmaceutical companies. 90 per cent of trials are delayed with patient enrollment as a primary cause. It makes sense to look at newer methods of recruitment. Timely enrollment of qualified patients needs to be substantially improved for clinical trials to complete on time. Each day of delay in a phase III trial costs pharma companies anywhere from $600,000 to $8,000,000 in opportunity costs.

Adding data science modeling to trials data

Data science techniques dealing with large volumes of structured and unstructured data (collectively known as ‘Big Data’) offer prescriptive clues to solve recruitment and retention issues. A data science approach generates insights by harvesting the data with sophisticated algorithms. With this approach, we can better understand why timely enrollment isn’t happening, and ultimately what needs to happen to improve success for clinical trials.

Building key attribute data models

Effective target segmentation for enrollment is a key to success. Traditional methods of enrollment rely upon campaign and segmentation based on disease lines across wider populations. Using data science, we can look at the past data to identify proper signals and help planners with more precise and predictive segmentation. Data scientists will look at the key attributes that matter for a given patient to successfully get enrolled. For each disease type, there may be several attributes that matter. For example, a clinical trial that is focused on a new diabetes medication targets populations’ A1C levels, age group, demographics, outreach methods, and site performance. Data science looks at the above attribute values for the target users past enrollment data and then builds ‘patient enrollment propensity’ and ‘dropout propensity’ models. These models can generate multi variant probabilities for predicting future success.

Social media provides previously unavailable insights

In addition to the above modeling, we can identify the target segment’s social media footprint for valuable clues. We can see which outreach methods are working, and which social media channels the ‘generation Googlers’ are using. This can be tracked on a continuous basis from the unstructured data of social media. Natural language processing (NLP) techniques to understand the target population’s sentiment on clinical trial sites, physicians, and facilities can be generated and coded into a machine understandable form. Influencer segments can be generated from this user base to finely tune campaign methods for improving effectiveness.

Combining structured prediction models such as patient enrollment propensity described above and the social media data gives us valuable signals that were previously not available to clinical trial planners. Moore’s law for clinical trials namely, ‘doubling enrollments at half the costs’ may still be far away, but leveraging big data is certainly a step in that direction.

This data science approach has been successfully leveraged by retail, telco, and media companies to gain critical insights. The pharma industry has recognised the opportunity of big data and needs a strategic plan to answer key business questions that will drive and quantify improvement. A data science-driven clinical trials management approach is an advanced strategic process to get trials back on schedule.