Accelerating Vaccine Approval with Prescriptive Modeling

Situation

One of the world’s leading pharmaceutical companies partnered with Mu Sigma to accelerate pre-market approval of a Respiratory syncytial virus (RSV) vaccine for adults over 60. In the U.S., the Centers for Disease Control and Prevention (CDC) reports that RSV contributes to over 150,000 hospitalizations and up to 10,000 deaths annually among adults aged 65 and older.
Despite initial discoveries related to RSV in the early 1980s, the complex biological, safety, and logistical challenges of RSV clinical trials had long delayed vaccine availability.

Challenge

Key challenges included differentiating RSV symptoms from similar respiratory illnesses (like influenza and COVID-19), understanding the RSV disease burden in older adults, and identifying specific risk factors in vulnerable populations. Technical hurdles also arose from immunogenicity complexities related to vaccine design.

Approach

Mu Sigma applied its Art of Problem-Solving System (AoPSS) and tools like muPDNA to build a comprehensive roadmap that addressed these complexities and expedited the vaccine approval process:

• Defining and Expanding Patient Cohorts: By leveraging muPDNA and analyzing over 20 research publications, we refined patient definitions, excluding misdiagnosed flu and COVID-19 cases and incorporating specific lab test data. Our approach increased the RSV target patient cohort by 12%.
• Patient Journey Analysis and Risk Identification: Through patient journey analysis and predictive modeling, we identified four previously unrecognized risk factors linked to RSV-related hospitalization, further validating the disease severity and impact on quality of life.
• Enhanced Trial Site Selection: Using demographic data, we identified over 300 high-density RSV patient counties within the U.S. These insights enabled a more efficient trial site selection and faster patient recruitment for Phase III clinical trials.
• Accelerating Data-Driven Decisions: Our Enablers of Confidence (EoC) platform provided reusable classification and survival components, which reduced the project’s execution time by 50%. Our Innovation and Development Labs introduced Bayesian Causal Network modeling, enhancing data interpretation and decision-making accuracy.

Impact

• 12% Expansion in Patient Cohort with refined patient targeting
• 50% faster execution time, accelerating insights for trial readiness
• Optimized Trial Site Selection
• Compelling Real-World Evidence