Artificial intelligence supporting Pharma commercial excellence within increasingly competitive markets
No surprise to anyone, the pharmaceuticals markets are becoming increasingly competitive. The recent example of the migraine market is striking. A market representing a huge unmet need for roughly 2% of the worldwide population should be an outstanding opportunity, but this blue ocean for Novartis & Amgen (who collaborated on the development of Aimovig) turns out to be a competitive face-off. While Aimovig (erenumab-aooe) was approved as a novel preventive treatment for migraine on May 17th, 2018, Ajovy (fremanezumab-vfrm) was approved on September 14th, 2018, and Emgality (galcanezumab-gnlm) from Eli Lilly was approved in September 2018. This is less than 6 months of free market for Aimovig.
This is great for patients and society but it forces companies to work and deliver revenues under increased competition. Also, recall that migraine prevention is an already crowded therapeutic area with plenty of treatments available that are genericized (e.g. beta-blockers)[1]. This blog gives a few examples on how Artificial Intelligence can create a competitive advantage in such an extremely competitive market.
More players in a single therapeutic area exacerbates the competition for physicians’ attention. Essentially, AI can help increase the relevance of the representatives for physicians and ultimately support the company commercial strategy.
There are already market offers that support what the next action is in terms of channels and message. Sadly, those technologies are currently focused on point solutions only. A representative usually knows by heart the preferred channel for a given physician to be reached. Existing technologies will therefore only incrementally support representatives if the representative’s choices are limited to those suggestions.
The identification of patterns within multiple dimensions is where human beings are more limited than the machine. Supporting the representatives in identifying the right message as well as the right supporting material is far more important than suggesting a preferred channel.
BASE life science believes that there are more dimensions to be exploited that can provide a multi-faceted and more useful view of the situation. That’s the first value proposition of machine learning. Based on data points such as prescription patterns within the area (an objective assessment of the competitive situation), the last medical evidence available for both own products and the competition, as well as other competitive factors (e.g. route of administration preferred by the physician), an AI-based system could suggest to the representatives what the talking points should be as well, and — which is of the highest importance — how the supporting documentation should be drawn up. Physicians are keen to learn and are happy to get the proper scientific information within the right environment.
Therefore, AI models need to be extended to focus much more on content and on the specific competitive situation than solely on channel and frequencies. This would enables representatives to provide physicians with the right content within the right context.
Another area where AI can support the entire commercial organization is the segmentation of both HCPs and HCOs. Clustering is a traditional machine learning technique and is essentially what segmentation means. Making the algorithm model the segmentation of physicians combined with representatives providing updates on observations and experience of the suggested segmentation could create an ever-improving segmentation environment. In addition, this would allow for encompassing additional dimensions within the model, based on competitive aspects such as the stickiness of a physicians to a certain brand. Segmentation could also encompass information flowing from the HCOs, such as the preferred supplier from the institution (as this is most of the time public data in Europe). Having the ability to run segmentation models almost constantly would also provide increasing accuracy allowing the representatives to always prioritize the right account.
If we look at the below example, it plots 2 different dimensions and the various segments of the market for trastuzumab which has multiple suppliers and faces competition from biosimilars for the IV route of administration. The first dimension depicts the number of chairs available within the HCO for IV injections. The higher the number, the less attracted the physician will be to subcutaneous injection. The second dimension is simply the sensibility (measured by a regression model of survey data on the number of prescriptions within the area) of the physician to additional evidence from the competition.
Some of the segments are easy to identify such as segment A but others would be more difficult to distinguish as the graphical representation would omit important dimensions. Of course, regression models could lead to segmentation but leveraging Artificial intelligence would render the process much more efficient and time saving.
Finally, once the segmentation and the messaging are optimized, the cycle plans delivered to representatives could be improved using the machine horsepower. The brute, computational force should enable the identification of the most impactful patterns linking segmentation messaging, HCP data and HCO data, which ultimately should provide the best model for prescriptions within the area. Of course, this requires a fair amount of data but once this is achieved, setting up a model for the machine to learn from shouldn’t be too difficult.
About BASE life science
BASE life science is a fast growing, fast paced consultancy focused on the life science industry. Established in 2007 and based in Copenhagen, Denmark, BASE targets a local as well as a global customer base.
Since inception, BASE life science focuses on helping Life Science companies create real business value from digital platforms and data within its area of expertise; Commercial Excellence, Clinical, Regulatory Affairs and Quality & Compliance. Since 2007, the company has been active globally from Denmark and employs more than 50 employees.
Want to learn more?
Read our whitepaper: Commercial Technology supports Pharma in increased Competition
About the author — Luca Morreale, Head of Operations, Switzerland
Highly motivated consultant focused on solving commercial & pricing challenges for Life Sciences companies through advisory, assessment or implementation services. Pragmatic & result driven with a strong ability to lead a team in a complex environment to achieve project goals. Ability to provide insights both at the strategy level as well as the operational level.
[1] SILBENSTEIN, Stephen D., Preventive Migraine Treatment, Continuum (Minneap Minn). 2015 Aug; 21(4 Headache): 973–989
