Interview: Harnessing data for effective patient retention strategies

They say providing a seamless participant experience is crucial for tackling the long-standing challenge of high clinical trial dropout.

Understanding why patients leave trials, collecting real-time patient sentiment data and harnessing new technologies are the key to success.

OSP: Where should we start when it comes to improving trial participant retention?​

SW: The prerequisite to knowing how to retain patients is knowing what causes them to leave trials in the first place. As an industry we have done studies on some of these drivers.

But we really need to have widespread processes to collect dropout data on a trial-by-trial basis. The reasons for churn are going to vary between trials, sites, patients and even visits.

Great data can help inform great decisions. Without it, we are simply making educated guesses as to how to design a given trial to ensure minimal patient dropout.

OSP: Can you give a practical example of one way to boost retention?​

JD: One practical way to prevent early dropout is to ensure patients get to their first site visit. We can do this by allowing them to book travel without incurring any out-of-pocket expenses.

Lots of patient’s dropout between being qualified on the phone and arriving at the screening visit so removing that out-of-pocket cost can make a real difference. This is particularly important for lower socioeconomic-level participants for whom expenses from flights, hotels and taxis might be prohibitive to participating in the trial.

OSP: How can sponsors improve retention throughout the lifespan of a trial?​

SW: It is important to collect real-time patient sentiment about the trial experience. For example, was a particular visit difficult, was a treatment difficult, were interactions between the patient and some service providers a deterrent?

We can then use this patient sentiment to inform things such as trial design, site selection, or even address patient concerns head-on before they are likely to drop out.

There are now seamless technology innovations that can help to collect this data in gentle, unintrusive, and even gamified, ways.

OSP: How can we harness new technologies to improve retention?​

JD: Machine Learning can be part of the patient-sentiment data collection strategy which, as explained above, can improve patient-centric trial design, and allow early intervention to prevent dropout.

By parsing through messages between the patient and the site using natural language processing (NLP), we can start to pick up signals of when individual patients are indicating they are likely to drop out.

We can then notify site coordinators of these signals so they can intervene and, hopefully, retain the patient on the trial.