2024 Fall Symposium - Agenda

This workshop offers a deep dive into transforming data management within the life sciences industry. You'll discover how a data products strategy can unify fragmented data landscapes, decentralize ownership, and harmonize data across regions, brands, and therapeutic areas. We’ll highlight how leveraging Analytical-Ready, Report-Ready, and Generative AI-Ready Data Products drives faster analytics, reduces operational costs, and fosters innovation. Through real-world case studies and actionable insights, you’ll learn how this approach accelerates time-to-insight, enables self-service analytics, and empowers AI solutions—while significantly enhancing data quality, trust, and overall operational efficiency.

In this session, we will delve into the complexities of measuring the impact of DMA-level Direct-to-Consumer (DTC) marketing campaigns within the pharmaceutical industry. We will examine various scenarios, highlighting instances where prior experimental setups are permissible and those where they are not. Additionally, we will evaluate the advantages and disadvantages of different causal inference methodologies tailored to these scenarios. Our goal is to empower business analytics professionals with actionable insights and advanced strategies in causal inference, ultimately enhancing their expertise in navigating the challenges of DTC marketing measurement.

How Gen AI can be integrated to perform data transformation and extract key insights out of it.

Retrospective Matching Analyses (RMA) are often relied upon to conduct impact assessments of promotional/educational activities when a randomized control trial is not feasible; despite the ubiquity of RMA applications in practice, many practitioners of the techniques may be unaware of their pitfalls when not properly deployed. Moreover, recent literature in the RMA space has demonstrated that even some of the most traditional of RMA methods need to be revisited and in some cases even abandoned (most notably Propensity Score Matching). In this presentation we will provide an overview of the fundamental assumptions underpinning RMA. Additionally we will provide a survey of traditional methods and highlight the shortcomings/requirements of each.

Loss of Exclusivity (LoE) is a critical event in the product life cycle, leading to sales erosion of branded products due to competition from generics. Traditionally, the ranges for sales erosion post-LoE are estimated through Analogue Analysis, which involves a collaborative cross-functional effort for data gathering and attribute selection. However, this process is often cumbersome and time-consuming, with a high probability of errors or missing crucial information.

To address this challenge, we developed a UI-driven analogue selection app that uses AI algorithms to measure product similarity. This app allows users to quickly run different simulations to select the best analogues and estimate the final erosion curve in just a few clicks, without any data processing or manual analysis. The app features a comprehensive repository of approximately 300 analogue products from different therapeutic areas, along with 50+ selection attributes developed in collaboration with medical, commercial, and access experts. It employs state-of-the-art supervised and unsupervised machine learning models for analogue selection and generates additional insights for strategic decision-making.

This session will provide an in-depth look at the development and implementation of the analogue selection app, showcasing its impact on reducing time and effort in analogue identification and improving the accuracy of sales erosion estimates post-LoE.

This session will provide an overview of an innovative in-house solution designed to enhance patient analytics, thereby achieving launch excellence in the rare disease market. The key takeaway for the audience will be to recognize the immense potential of machine learning and artificial intelligence in driving analytics across commercial functions.

This presentation will showcase how Bayer has fundamentally transformed Field Force Operations into a practical and sophisticated one using an Artificial Intelligence/Machine Learning-driven approach across 3 primary sub-functions - Design & Planning, Execution and People.

In today's rapidly evolving oncology landscape, organizations must embrace the power of predictive analytics and AI-driven capabilities to enhance customer experience. By strategically deploying AI-powered solutions, we can streamline workflows, personalize engagement, and improve outcomes for healthcare providers, patients, and their caregivers. We should aim to harness AI capabilities to anticipate customer needs, optimize touchpoints, and deliver a seamless, data-driven customer experience that sets a new standard of excellence in the oncology space.

HCP segmentation, also known as customer segmentation, is the process of dividing healthcare professionals (HCPs) into distinct groups based on certain characteristics or criteria. This segmentation helps pharmaceutical companies to better understand their customers and tailor their marketing strategies and communication efforts accordingly.

As the pharmaceutical industry increasingly embraces AI-driven business insights and analytics, the demand for skilled professionals who can lead these transformative initiatives is growing rapidly. This panel will delve into the critical aspects of recruiting, developing, and retaining top talent in this evolving landscape and discussion topics will include the essential skills and expertise required, the importance of domain-specific knowledge, and strategies for fostering collaboration between data scientists and business leaders. Additionally, the panel will touch upon industry trend and how to measure the business impact of AI initiatives.

Join us as we discuss how to build the data science and analytics teams that will shape the future of the pharmaceutical industry.

In today’s promotional environment, it is critical to arm the field force with actionable recommendations to maximize their time with the right customers focused on the right activities. Through our Action Alerts program, Astellas and Axtria partnered to deliver clear, concise recommendations to the field and create awareness in areas such as Rx Abandonment, Sample Optimization, Team Coordination, and other key areas of rep success. This program took the NBA (Next Best Action) concept, optimized it using AI, and implemented it through practical, easy to understand suggestions to the field, with the goal of increasing Rx uplift, keeping reps focused on the highest potential customers, and changing rep behavior through enhanced engagement and execution of these practical suggestions. This presentation will show how Astellas and Axtria worked together to leverage data, convert it to useful rep suggestions, and ultimately improve brand performance for through better field execution.

Enable non-technical users to access insights via natural language generation-based applications that leverage generative AI (GenAI) and have user-friendly interfaces and strict data access controls.

Over the past few decades, pharmaceutical forecasting has progressed from intuitive methods to more scientific approaches. This session offers an overview of the evolution of forecasting methodologies and their increasing reliance on data. It also provides insights into the potential future direction of the industry.

During the session we will presents a methodology leveraging multimodal LLMs to profile HCP behavior for personalized outreach. By fusing structured and unstructured data, the approach provides deeper insights into factors driving HCP decisions, enabling customized targeting for business objectives like understanding declining patient starts or drug adoption trends. The methodology also incorporates LLM-driven agents to interpret patient journeys and HCP timelines, enhancing content relevance. Overall, this framework significantly improves personalized communication strategies, offering actionable insights for marketing and clinical teams to enhance HCP engagement.

How should we select the most optimal targets for our pharmaceutical marketing efforts? This session explores one practical solution - figuring out who is likely to prescribe our products. At the core of the solution are machine learning models that find patterns in the data and get an accurate prediction for the future. But as you'll see a practical end-to-end solution requires many more components!

We always grapple with the same haunting questions when we analyze a data source to provide insights, make decisions, or recommend actions to be taken. How complete is the data? What are the holes? What are the biases? What anomalies in the data may throw off our findings? In other words, we need to calibrate what the data suggests. Indeed, we need to assess and enhance the data source and even bring in other related data sources to ensure we are not off the mark. In this talk, we’ll discuss 26 data sources from the public domain that help us do just that. We’ll provide plenty of examples and illustrate our points using real case studies. Why is it, you may wonder, that most analysts are not aware of those 26 data sources? It’s precisely because they are free. These data sources are not publicized. No one is calling you to give you a dog-and-pony show and sing the praises of the data sources. What’s more, there is no one to answer your questions. We embarked on a long exploration journey years ago and that’s how we found those hidden gems that we’ll be sharing with you.

Discover how cutting-edge AI/ML models can redefine your IC goal-setting process. Learn how to leverage these powerful tools to:

• Set data-driven, accurate goals tailored to individual territories and reps.
• Optimize resource allocation and maximize sales efficiency.
• Improve forecast accuracy and reduce the impact of market uncertainties.
• Gain a competitive edge by harnessing the power of AI-driven insights.

Join us for an insightful session on how AI/ML can transform your IC strategy.