Developing IQVIA’s positions on key trends in the pharma and life sciences industries, with a focus on EMEA.
Learn moreDeveloping IQVIA’s positions on key trends in the pharma and life sciences industries, with a focus on EMEA.
Learn moreDeveloping IQVIA’s positions on key trends in the pharma and life sciences industries, with a focus on EMEA.
Learn moreDeveloping IQVIA’s positions on key trends in the pharma and life sciences industries, with a focus on EMEA.
Learn more"We strive to help improve outcomes and create a healthier, more sustainable world for people everywhere.
LEARN MOREReimagine clinical development by intelligently connecting data, technology, and analytics to optimize your trials. The result? Faster decision making and reduced risk so you can deliver life-changing therapies faster.
Research & Development OverviewGenerate and disseminate evidence that answers crucial clinical, regulatory and commercial questions, enabling you to drive smarter decisions and meet your stakeholder needs with confidence.
REAL WORLD EVIDENCE OVERVIEWElevate commercial models with precision and speed using AI-driven analytics and technology that illuminate hidden insights in data.
COMMERCIALIZATION OVERVIEWOrchestrate your success across the complete compliance lifecycle with best-in-class services and solutions for safety, regulatory, quality and medical information.
COMPLIANCE OVERVIEWWhen your destination is a healthier world, making intelligent connections between data, technology, and services is your roadmap.
TECHNOLOGIES OVERVIEWExplore our library of insights, thought leadership, and the latest topics & trends in healthcare.
DISCOVER INSIGHTSAn in-depth exploration of the global healthcare ecosystem with timely research, insightful analysis, and scientific expertise.
SEE LATEST REPORTSBy making intelligent connections between your needs, our capabilities, and the healthcare ecosystem, we can help you be more agile, accelerate results, and improve patient outcomes.
LEARN MOREBuilding on a rich history of developing AI for healthcare, IQVIA AI connects the right data, technology, and expertise to address the unique needs of healthcare. It's what we call Healthcare-grade AI.
LEARN MOREYour new expert analyst is here. Be at the forefront of data-driven decision-making with a new generative AI tool that enables you to interact with our products and solutions like never before. Get results you can trust, faster.
LEARN MOREThe IQVIA Human Data Science Cloud is our unique capability designed to enable healthcare-grade analytics, tools, and data management solutions to deliver fit-for-purpose global data at scale.
LEARN MOREThe IQVIA Innovation Hub connects start-ups with the extensive IQVIA network of assets, resources, clients, and partners. Together, we can help lead the future of healthcare with the extensive IQVIA network of assets, resources, clients, and partners.
LEARN MOREIQVIA Decentralized Trials deliver purpose-built clinical services and technologies that engage the right patients wherever they are. Our hybrid and fully virtual solutions have been used more than any others.
LEARN MOREEmpowering patients to personalize their healthcare and connecting them to caregivers has the potential to change the care delivery paradigm.
LEARN MORE"At IQVIA your potential has no limits. We thrive on bold ideas and fearless innovation. Join us in reimagining what’s possible.
VIEW ROLESAt IQVIA, we are frequently asked by clients to help identify Key Opinion Leaders for a given therapeutic area and market. Traditionally, this work has been done using peer-nomination surveys. This is a respectable methodology with a long history but is open to various degrees of bias and can be expensive and time consuming due to the manual effort involved in the process.
I lead our Graph Analytics team in our larger AI/ML group, which applies network and topological techniques to various problems within the life sciences and healthcare domains. We model data using mathematical graphs or networks and use analytical techniques over these models. Modelling influence relationships between health care professionals (HCPs) is a natural application of these techniques, which have been used widely in social network analysis.
A simple first pass approach is to ingest data from various sources to build a multigraph showing all the different kinds of connections between HCPs (e.g. which HCPs have co-authored papers together, which HCPs have a patient-referring relationships, and many more). We can also weight these relationships based on the number or importance of the papers or the prescribing volumes depending on the dimensions we’re interested in. We can even combine this with conventional peer nomination data to get a richer picture if needed.
Once we have this network, it’s relatively straightforward to use graph centrality measures to determine who appears to have the most influence in the graph, and we can tailor this to the particular needs of a given project (e.g. are we looking for scientific influencers vs prescribing influencers). However, this on its own may not give us much beyond what could be done with conventional analysis of the various data sources.
A more advanced step is to then consider how influence or messages propagate over the HCP networks. Once we seed a single HCP with a message, what is the probability that other HCPs in the network will receive the message (e.g. about the advantages of a new product)? Do we see cliques or clusters forming? These could be e.g. geographical or related to institutional affiliation, or more intriguingly not have obvious explainable meaning but still have predictive power.
We can also run simulations over the network to determine which are the most effective HCPs to target given the network topology. This is a more nuanced approach than simply picking e.g. the top 20 highest ranked KOLs, because there’s a risk that if those top 20 KOLs are in similar influence cliques, then your limited resources may be better spent targeting HCPs lower in the overall scoring list, but more likely to have greater impact by reaching parts of the network you may not otherwise be able to reach.
As ever, we have to deal with incomplete data, and again there are graph analytical techniques such as link prediction algorithms that we can use to impute relationships that aren’t concretely available in the data (with some associated probability).
Finally, the big question after all this is to understand can we actually measure the impact of our messaging to KOLs? This can be tested using the same infrastructure used for peer nominations, by surveying samples of HCPs before and after messaging to see if messaging has diffused as expected. This can then be fed back in to the models to improve future iterations.
Interested in finding out how Graph Analytics can help you identify KOLs?