Blog
Identifying Healthcare's Hidden Peer-to-Peer Learning Communities
New AI-based research model maps healthcare professional (HCP) relationships across HCP networks
John Eichert, Senior Principal, Thought Leader Network Center of Excellence, IQVIA
Bruce West, Senior Principal, Thought Leader Network Center of Excellence, IQVIA
Oct 07, 2021

Thought leaders are a powerful asset in Medical Affairs and Commercial teams' strategic and tactical arsenal. They help generate initial brand awareness, establish credibility, and provide potential prescribers with a powerful rationale for treatment. In addition, selected thought leaders generate the clinical evidence that supports regulatory submission and defines clinical use of a new treatment. Despite the acknowledged importance of thought leaders, identifying and engaging the right thought leaders can be a costly and time-consuming process, and many companies often uncover only a fraction of the total leadership landscape.

To be clear, it is relatively easy to identify prominent scientific/academic thought leaders who write papers, speak at conferences and/or write expert guidelines – in other words, those top category leaders who create initial awareness and establish the treatment narrative. However, these leaders typically don’t drive treatment behavior and product adoption at the regional and local levels of the general healthcare professional (HCP) population.

Successfully promoting new treatments and broadcasting their value requires finding and engaging the local hidden thought leaders and their related HCP communities. These are the trusted colleagues and respected advisors to whom HCPs turn for clinical advice and to share knowledge, but who are typically missed by marketers because there are no ready sources to secure these leader insights.

The impact of hidden thought leaders

When thought leaders believe in a product, they are often more likely to communicate that preference to their network, which can impact treatment decisions.

IQVIA research also shows that when respected advisors in a physician network adopt a treatment protocol, the rest of their network adopts that treatment at a rate 25 percent higher than networks where thought leaders did not adopt.1

The limitations of prior methodologies

The “old art” approach to identifying thought leaders based on subject-matter expertise relies largely on desk research and analysis of peer-reviewed publications, clinical trials, conference presentations, and grants. More recently, administrative claims data has been used to identify volume leaders who are receiving referrals—what we would call “weak ties.” The problem with these approaches is that they miss identifying those local thought leaders who serve to translate new science into practical clinical practice; they help local healthcare providers understand the how, when, and where to consider use of a new treatment agent. The methods for leader identification previously open to life sciences companies included

  • Analyzing frequency of activity in scientific endeavors—publications, participation in clinical trials, presentations at medical meetings, and the number of research grants received
  • Analyzing social media activity around specific diseases or treatments
  • Analyzing the volume of referrals for a specific diagnosis, or the number of patients shared between healthcare providers
  • Analyzing early adopters to determine who initiates treatment first and then who follows

Unfortunately, these various methods are rarely, if ever, combined in an integrated fashion, and none of them adequately quantify the impact or strength of the relationship on prescribing behavior. Some relationships are stronger than others, and they all impact the learning process in different ways and in differing levels of effectiveness depending on the lifecycle stage of the product commercialization process.

A “new art” analytical technique

IQVIA has pioneered a powerful new analytics technique to transform the process of identifying and engaging individual thought leaders to a complete understanding of how local and regional thought leader communities of practice drive the adoption of new treatments. Our Thought Leader Network Science Model applies artificial intelligence and machine learning to identify the relationship ties between target HCPs and local/regional clinical leaders across disease specific markets. Our analytic approach leverages our primary peer nomination research and enhances those insights using IQVIA big data at the individual HCP level to reveal HCP peer learning networks that are a key driver for the dissemination of medical information and behavior change (product adoption).

The new approach uses a proprietary peer nomination primary research technique to capture prime learning relationships from a relatively small sample (~8-10 percent) of HCPs known to treat the targeted disease. Those responding to the survey nominate trusted colleagues whom they routinely talk to, or seek advice from, about managing a patient with a given disease. Using this sample of known strong learning relationships, we then enhance this dataset by integrating IQVIA’s Big Data Factory (which includes OneKey reference data, referrals, shared patients, affiliation, medical school, location, and prescribing). With this expanded and integrated data, we then apply patent-pending machine learning algorithms to predict links between targeted HCPs and their most likely clinical thought leader, resulting in a complete picture of network ties among an entire disease-specific target market. From these relationship links, a detailed Community of Practice (CoP) map is created that provides extensive insight into practice behaviors, product utilization, and how thought leader preferences and opinions drive HCP network learning and behavior (product adoption).

More accurate predictions of the impact of thought leaders on product adoption

This new methodology can predict strong ties with local, regional, and national thought leaders for the entire treatment landscape with a very high degree of accuracy. Our model has been shown to deliver greater than 80 percent precision in identifying the relationship ties that link clinical leaders to HCP prescribers across the disease specific network. In one study, analysts were able to expand the number of link predictions for the peer network from 364 HCPs who had been identified through a survey to 12,769 via the IQVIA model.

When commercial and medical affairs teams understand how and when a thought leader has the greatest effect on decision making within their network, they can

  • Identify the highest-value thought leaders in each community – those who have a disproportionate impact on the behaviors and preferences of their HCP peers.
  • Craft more targeted communications programs with more precise messages, improving the delivery of valuable treatment information.
  • Make informed and accurate go-to-market decisions for both medical affairs and commercial strategy based on a better understanding of HCP networks.

All of this leads to more efficient and more effective medical, marketing, and sales strategies, particularly within the critical first six months of launch. In summary, our “new art” approach leveraging link prediction analytics can help your company increase the rate of acceptance of new healthcare innovations.

 

1Dry Eye Disease Analysis – IQVIA data on file, 2020.

Identify Hidden Influencers

Is your brand optimizing thought leaders and their related HCP communities? Learn how IQVIA’s Link Prediction can have more impact on identifying and engaging the right thought leaders to drive the adoption of new treatments.
SUBSCRIBE
IQVIA Blog Digest
For all the latest industry insights, please subscribe to the IQVIA U.S. blog digest.
Contact Us