The pressure to improve a brand’s performance isn’t unique to underperforming brands. In fact, the challenge to acquire and retain more patients is renewed for all brands with each new budget cycle. It’s understandably difficult for brand teams to decide which of the performance levers at their disposal will deliver the biggest return on investment (ROI), especially given the interplay between the options. The available strategies are interrelated, and improvement in one area could have an impact (positive or negative) on the others.
Fortunately, IQVIA has developed a unique, deep learning framework (on which a patent is pending) to guide brand teams in choosing among the four functional pillars of performance:
IQVIA’s methodology, which uses embedded intelligence based on Machine Learning (ML) algorithms, reveals a brand’s potential, identifies existing performance gaps, and quantifies the ROI of various tactics. It draws upon integrated data of 300 million anonymized patients.
For more details, please download our factsheet.
Using a medical sequencing algorithm, it is possible to quantify how many “opportunity patients” – those who are not on the brand but share a similar clinical profile to patients currently on the brand – are available for capture. This entails
Having quantified the number of opportunity patients, the brand team must next understand why these patients aren’t on the brand. The team should explore the impact that the functional performance pillars 1 – 3 listed above had on performance. This is done by tapping the integrated patient database and comparing the messaging, promotional, payer access, KOLs and IDN related influences on current brand users and opportunity patients.
To expose the drivers of adherence (the 4th pillar), a ML algorithm can compare the characteristics of an adherent patient to those of a non-adherent patient and help develop strategies to improve adherence.
This exercise will identify multiple areas that can be improved, but leaves unanswered the question of which tactics should be employed. Choosing among them will require once again turning to the ML model. The cost side of the equation will still be an estimate, but the algorithm will quantify the probability of converting opportunity patients to brand users with each potential tactic.
The decision on how best to allocate limited resources and improve brand performance can now be evidence based. It requires extensive patient-level data resources, a well-structured ML framework, and IQVIA’s analytical methodology.
Every year, brand teams face the same question: how can we improve our brand’s performance? By combining subject matter expertise with vast amounts of data in an AI platform, IQVIA’s Brand Optimizer can uncover a brand’s true potential – and drive brand performance.