How an AI-human partnership produced 50% more qualified clinical trial participants

For every medical breakthrough that comes to market, several more are tested in clinical trials to evaluate similar or related treatments.

Take, for example, the three FDA-approved Alzheimer's drugs that have come to market in the last two years. After several decades of Alzheimer's trials suffering repeated setbacks – including the suspension of investigational drugs – there is now a development pipeline of nearly 200 Alzheimer's trials. When you consider that each of these trials requires over 100 participants and that many trials are taking place simultaneously, there is suddenly a huge demand for similar patient populations. And that's just Alzheimer's trials.

There are currently over 450,000 clinical trials underway worldwide for various health conditions and treatments. About 80 percent of these are at risk of delays because trial sponsors simply cannot find the volunteers they need. Once sponsors have found participants, getting them to stay for the duration of the trial is a whole other challenge.

Participant recruitment and retention is the biggest driver of manual work, delays, and costs in clinical trials, making them ideal candidates for AI's immense potential to simplify—and even redesign—otherwise tedious processes.

As sponsors of clinical trials, recruiters and managers determine AI tools' As we improve these workflows to increase participation and retention, it is important not to deviate entirely from necessary, human-centered interactions. This can have unfortunate consequences for the quality of the patient experience.

Here's a look at the hybrid approach we developed to increase patient randomization in clinical trials by up to 50%.

Read also: Humanoid robots and their potential impact on the future of work

AI identifies and targets candidates to find new potential study participants not yet known to sites.

Since multiple studies often examine the same patient populations over similar time periods, many trial centers often have limited ability to effectively register all studies simultaneously.

This is in part because sites' databases, while comprehensive, do not capture every potential participant; in many cases, patients simply have not yet been identified.

In the USA alone, for example, over 6.5 million people live with AlzheimerMany of these people may qualify for clinical trials that could lead to life-changing treatments for themselves or others, but they either don't know what trials are being conducted or how to get involved. And the trial sites probably don't know about them either.

In response to these limitations, sites are increasingly relying on outside vendors to help them recruit through direct patient advertising and advocacy methods. As a result, social media and digital advertising have become important tools to reach these previously uninformed patient populations by reaching them where they are already searching.

With the addition of AI and machine learningCampaigns can consider thousands of historical data points from recruiting firms or pharmaceutical companies to identify potential candidates for trials – all based on highly specific trial criteria. And AI can do this at an exponentially greater scale and speed.

When AI works hand-in-hand with this historical data – and continues to learn as it goes – study sponsors can do more than just target ads to populations within 10 miles of the study site that meet the age criteria. While this is undoubtedly a good and logical starting point, the potential that can be achieved by using advanced technology is infinitely larger.

AI assists with pre-screening to speed up the enrollment process.

Once potential participants are identified, pre-screening is required to determine whether or not they meet study requirements. Screening participants before they visit the study site ensures that sites can focus their time and resources on only the best-qualified patients.

Not only can we use AI to pre-screen exponentially more candidates faster than any other method before, but it also makes more accurate patient recommendations so that the right participants are included in the right trials. This increases the chances that each trial will get what it needs and enables more efficient use of existing and new Patient pools.

This approach has enabled us to increase the number of highly qualified participants we assign to trials each month by 15%, a tremendous benefit for sponsors who need more patients than ever before.

Then humans step in to transform candidates into participants.

Once candidates are pre-screened, the technology routes them to qualified nurses who personally guide candidates through the rest of the enrollment process. These nurses conduct thorough health screenings and ensure that potential clinical study Participants meet protocol criteria. You are also responsible for understanding participants' individual lifestyle considerations and how these intersect with the requirements for participation in the study.

By combining the efficiency of technology with human-centered care, we have been able to increase the number of patients randomized to trials by up to 50%, even higher than with an online-only screening.

Also read: AI strategies to accelerate clinical trial timelines and ROI

Human care plays a critical role in the patient experience because patients want to work with providers they trust.

Healthcare is a deeply personal and intimate area, which is one of the biggest limitations of AI.

For those struggling with illnesses they may not fully understand, or who are confused and anxious about the full implications of their diagnoses and treatment plans, guidance from well-trained human nurses and doctors can make all the difference. That human touch fills in gaps that AI may never be able to detect or understand. Perceiving emotional nuances and approaching them with human compassion is often far beyond the reach of AI.

Even though technology continues to evolve and some predict that it will become more human-like and autonomous, for the foreseeable future it will still be the job of trained humans to keep clinical trial participants engaged and comfortable throughout the duration of the study—with a gentle touch, a calm voice, and a reliable demeanor.

We've doubled down on our beliefs here and hired 50 nurses to work with patients throughout the trials. By clearly explaining trial requirements, communicating expectations, and being with them every step of the way, we can increase retention beyond anything we could achieve by simply automating the process using technology.

AI is not yet ready to rely “solely” on core clinical trial functions, and may never be. The future holds many uncertainties for a technology that has changed the landscape of every industry in just a few years.

The entire healthcare industry today faces the challenge of walking a tightrope: on the one hand, it must leverage the use of AI to optimize processes, while on the other hand, protecting those areas that require the dignity that a human touch can convey.

Finding this balance is a win-win for companies, patients and our path to progress in treating life-changing diseases.

[To share your insights with us as part of editorial or sponsored content, please write to [email protected]]