April 2020 | Point of View

How AI meets medical affairs teams’ evolving need for KPIs

Deploying real-time analytics can help pharmaceutical companies define targeted engagement plans and develop insights from field interactions

This is the second in a three-part perspective on the modernization of medical affairs through applications of artificial intelligence and machine learning to drive decisions and outcomes. Part one, “AI to Align Field Engagements With Strategy in Medical Affairs,” can be found here.

Medical affairs teams have never been more important to the success of pharmaceutical companies. The rising importance of medical science liaisons (MSLs) in the industry is reflected in their 12% industry-wide growth from 2014 to 2016 and 31% growth in specialty areas such as oncology. In many cases, MSLs are a physician’s top resource for information on game-changing interventions and play an integral role in improving patient outcomes.

The next generation of therapies (e.g., CAR-T, cell and gene therapies, etc.) are increasingly complex. The medical affairs function is not only being impacted by the demands associated with bringing these new therapies to market, but also the increasing demands for meaningful engagement from the key opinion leader (KOL) and healthcare provider (HCP) communities. Forward-thinking pharmaceutical companies are rethinking the role of Medical Affairs and are positioning the function to create competitive advantage in the evolving therapeutic landscape. 

Field personnel are the backbone of medical affairs teams. They are the ones on the front lines who use their advanced medical expertise to navigate the real-world needs and implications as drugs go from novel compounds to marketed products. They sit at a critical point in the map of the human resources involved throughout the life cycle of the drug: interacting and facilitating between groups of stakeholders, including researchers, patients, doctors, and executives.

It’s a complex job that involves many decentralized channels, one-off conversations, disparate data sources, and incomplete feedback loops. Collection, analysis, and utilization of this real-world data to impact outcomes has been difficult. Until now.

This is where data analytics, machine learning, and natural language processing play a considerable role. No longer the stuff of hypothetical doctoral theses, the advances in artificial intelligence are real and on the ground today, unlocking new efficiencies and capabilities in the life sciences.

AI-enabled software can be used to identify and engage stakeholders more effectively, measure qualitative and quantitative metrics, and most importantly for MA teams, align the overall strategy in a more real time way to the activities, insights, and observations bubbling up from the field.

Improved identification and engagement with KOLs

The linkages between stakeholders of a medical field team can look like a complex spider web. But unlike a spider that weaves its web with perfect balance and precision, the threads of communication that MSLs must manage are often tangled and unruly. 

When it comes to KOLs, who talks to whom and in what intervals they do so can be difficult to track. Equally challenging to track are more granular details like newly published research, social media chatter, and conference talks. Depending on the life cycle of a drug in development, each MSL will manage between 20 and 40 KOLs. The makeup of that portfolio of experts is critically important depending on the strategic objectives of the team. 

MSLs must be able to easily see which fields are represented within their portfolio, areas of expertise, and level of activity around certain topics. If a specific area of research is trending within a drug’s purview, an MSL could determine if there is someone within their group who can speak to the issue, or use the social analytics tool to seek out new experts who may be needed.
A distinct AI advantage comes with the ability to use social network analytics to drive influence mapping to help identify HCPs that are connected through research, patients, behavior, and interest. 

Bringing disparate data streams together in one place for analysis and strategic objective optimization

By centralizing all of this activity in one place —  giving MSLs the ability to track frequency of engagement, set up meetings, monitor topics of interest, and use real-time feedback from other channel inputs to address priority areas — it turns localized, disjointed communications into smooth efficient data streams to harvest insights and inform decisions. 

But metrics of KOL management are just a few of the inputs in the overall data picture for MSLs; there is myriad data from multiple sources that are necessary for MSLs to stay on top of, including CRMs, Veeva/Salesforce, prescription data, conference talks, social media, and clinical trials. There is an ever-expanding world of information that needs to be filtered, reviewed, analyzed, and processed for relevance and strategic importance.

One of the key factors that makes AI tools a necessity for medical affairs teams is integrating relevant yet disparate data sources so that it is accessible for platform users and can be leveraged to generate insights.

Natural language processing, a discipline of AI, is based on machine neural networks that can ingest and analyze enormous volumes of information from many different sources and formats. For medical affairs teams, this means deploying this capability to evaluate large volumes of publications, clinical trials, social media feeds and text insights to help quickly discern the key topics and concepts.

Gather insights from field activity — “bring the field into the home office in real time”

There’s plenty be learned from the field in real time and much of that important data that can easily slip through the fingers of even the most well-intentioned, diligent employees. They are awash in managing relationships, disparate data sources, and real-time events. AI technology can simplify and streamline, turning a barrage of noisy information into clear, sharp signals of actionable insights.

AI can be used to enable more real-time response capability to respond to real-world events like adaptable HCP scoring and prediction of future scores based on understanding of market behavior, scientific impact, and stakeholder beliefs. MSLs are on the front lines answering questions from the field and serve as critical conductors of information between important stakeholders. They are well positioned to add value with the ability to bubble up what they are hearing from HCPs: Is there an issue with new drug?  Do we need new data? Is there a more recent study we need to be looking at? AI allows you to use data to forge more accurate predictive models to better tie actions to goals.  

Conclusion: Aligning interactions to product lifecycle and preferred channels 

Pharmaceutical companies are under pressure to operate as efficiently as possible in both how they communicate (increasingly digital) and the ability to generate insights and automate function from those communications. 

New technology can make MSLs even more of a strategic asset for the company, not only improving MSLs’ own work experience, but also improving medical affairs’ value proposition and, ultimately, patient outcomes. Advanced AI capabilities can make your field team more effective by centralizing activity in one place: manage relationships, track important research, identify priorities, and provide transparency throughout the changing lifecycle and needs of pharmaceutical development.

AI capabilities help untangle complex stakeholder communication threads in two important ways: clarifying and amplifying strategic objectives across team members so that everyone is optimizing for the same goals and tracking one-off meetings, calls, exchanges, and disparate data sources so that all KOL and HCP activities are in the service of the identified strategic objectives.

 

Explore our latest perspectives