Market Access Today
October 5, 2024
Key Questions Answered
- What are the primary areas of specialization for an insights-driven technology and data company?
- How does such a company (an insights-driven technology and data company) utilize AI in its operations?
- In what ways does this impact patient outcomes and research advancement?
- How does this reimagine the use of real-world evidence by industry stakeholders?
AI in Market Access: Transforming Pharmaceutical Research with Real-World Evidence and Predictive Modeling
The global pharmaceutical industry is undergoing a significant transformation, with an expected compound annual growth rate (CAGR) of 5.9% between 2023 and 2028. This growth follows a 2023 slowdown driven by reduced demand for COVID-19 vaccines and therapeutics. Key factors driving this resurgence include the integration of real-world evidence (RWE) and real-world data (RWD) into drug development, and the accelerated adoption of generative artificial intelligence (Gen-AI). These technologies are revolutionizing how the industry approaches market access and clinical research, helping pharmaceutical companies navigate a rapidly changing landscape.
Since 2021, Gen-AI has dramatically advanced drug discovery by enhancing data analysis, predictive modeling, and real-time insights. This trend continues, especially as AI-powered tools enable more efficient research outcomes. Simultaneously, the increasing use of RWE provides deeper insights into therapeutic effectiveness, patient journeys, and product validation, all critical for regulatory approval and market access.
Traditionally, market access strategies have focused on areas such as oncology and rare diseases. However, there is now significant potential for growth in fields like psychiatry, immunology, and infectious diseases. By developing AI and data-driven tools for these therapeutic areas, companies can tap into new markets while improving personalized treatment approaches. Yet, one of the biggest challenges in the healthcare industry remains the fragmentation of data sources and the knowledge gaps this creates, from research and development (R&D) to clinical decision-making.
A compelling example of how AI is addressing these challenges comes from OM1, a technology and data company specializing in RWE and personalized medicine. Founded in 2015, OM1 is pioneering the use of next-generation AI platforms to improve patient outcomes by leveraging real-world data. One particularly noteworthy case study involves the development of a machine learning model to estimate Systemic Lupus Erythematosus Disease Activity Index (SLEDAI) scores using unstructured clinical notes.
Case Study: Estimating SLEDAI Scores with AI
In clinical practice, the use of the SLEDAI—a tool for measuring disease activity in patients with systemic lupus erythematosus (SLE)—is inconsistent, and clinician-recorded SLEDAI scores are often missing from real-world datasets. OM1’s machine learning model aims to address this gap by estimating SLEDAI score categories based on unstructured clinical notes.
The model was developed and validated using a large, real-world dataset and performed well in estimating SLEDAI score categories. This AI-driven approach not only provides more accurate insights into disease activity but also makes these data more valuable for research. By generating reliable SLEDAI estimates from real-world data, this model could play a crucial role in future studies of SLE and potentially be adapted to other rheumatological conditions, improving disease activity measures across the board. (Validation of a machine learning approach to estimate Systemic Lupus Erythematosus
Disease Activity Index score categories and application in a real-world dataset:
https://www.om1.com/wp-content/uploads/2021/05/OM1_Alves_SLEDAI_AI_May2021.pdf)
The potential impact on clinical practice and future developments is significant. With access to reliable, AI-generated SLEDAI scores, clinicians can better track disease activity, even when explicit SLEDAI scores are not recorded. Moreover, researchers can use this enhanced dataset to drive deeper insights into SLE treatment efficacy, patient responses, and overall disease management.