Taking Clinical Trials to the Next Level with NLP
Natural language processing technology is a promising gamechanger
Clinical trials are crucial to examine the safety and efficacy of new treatments, yet research shows 20 percent of U.S. oncology trials fail to meet enrollment targets due to lack of patient participation. Studies also show trial costs can increase by 20 percent due to poor site selection. Denise Juliano, Group Vice President of Life Sciences at healthcare improvement company Premier, shares how natural language processing (NLP) is revolutionizing the clinical trials landscape.
What is NLP and how can it help solve the costly issues associated with clinical trials?
DJ: Simply put, NLP enables computers to understand, interpret and manipulate human language. When used in healthcare, NLP algorithms can search clinicians’ free-flowing and unstructured notes, pathology reports and other documents in the electronic medical record (EMR), decipher the data, and identify eligible patients and sites for participation in a clinical trial.
NLP can make sense out of important EMR data that would otherwise be inaccessible to trial sponsors and investigators.
How does this look in a real-life clinical trial scenario?
DJ: In a typical clinical trial situation, there’s a heavy burden on staff to manually find patients who meet complex inclusion/ exclusion (I/E) criteria. Many struggle to enroll patients outside of the investigator’s own patient panel. This makes for a long, complicated and costly study startup process. As a result, most investigators enroll one or no patients into complex trials and many investigators don’t participate in a second trial at all.
NLP technology has the power to automate and simplify the candidate identification process. By applying the I/E criteria to EMR data, the technology can read and understand the incredibly rich clinical narrative to rapidly identify the right types of patients to enroll into a clinical trial. In fact, with NLP, up to 2 million documents per hour can be processed! That means many more eligible patients can be identified to the trial investigator in much less time.
NLP can also be used to estimate eligible patient volumes with a new level of granularity and accuracy previously unattainable when screening sites to match trial protocols. The technology allows trial developers to assess the suitability of a site based on investigator availability, experience in therapy area and historical performance metrics. Based on the assessment, the sites that have the best chance to outperform against expected site metrics for each trial can be selected.
How is Premier taking advantage of the power of NLP?
DJ: Premier Applied Sciences® (PAS), the research and analytics division of Premier, has partnered with Clinithink, a healthcare technology company, to put NLP technology into the hands of trial sponsors, investigators, life sciences companies and other research organizations that could reap its benefits.
PAS partners with industry leaders to develop, teach, test and research care delivery practices and real-world interventions for healthcare improvement. This includes prospective research and clinical trials to help improve patient outcomes.
Clinithink’s NLP technology helps PAS to quickly and efficiently:
• Build a more productive site research network driven by analytics, offering trial sponsors a new level of insights.
• Choose participating sites with advanced knowledge of qualified patients.
• Find the best clinical trial candidates.
• Hand off analysis to the sites for local patient identification.
• Increase the diversity of recruited patients, a key goal of the Food and Drug Administration (FDA) given that Black and Latinx Americans are under-represented in U.S. trials as compared to White and Asian Americans.
• Expand investigator pools by building a national investigator network.
• Expand the reach of new treatments to underserved communities.
What does the future look like for clinical trials that utilize NLP technology?
DJ: The idea of using NLP more and more to identify eligible patients and sites for clinical trials is extremely exciting, and it can be vital to trial success. All parties involved benefit. Trial sponsors and investigators gain significant time and cost savings. Health systems gain greater efficiencies and the potential for data sharing and internal data analyses. Patients gain the promise of new and successful therapies.
It’s time to cast aside manual candidate and site identification processes and start leveraging the patient details that doctors have input into the EMR for years.