Identifying Potential Undiagnosed Patients at Scale
Classical approaches to market sizing, patient journey, patient finding, etc. all begin with a common assumption: that combinations of medical and Rx claims at the patient level can be deduced and combined to create a de-identified patient level cohort to anchor analysis. However, as the pharma landscape shifts from one dominated by primary care markets with high prevalence and a plethora of launch blueprints to draw upon, to one where diffuse specialty markets with low prevalence and a lack of analogs to anchor launch strategy, this assumption rarely holds true and creates significant commercialization challenges. This conundrum is particularly acute in Rare Diseases, where only about 500 of 7,000 have a diagnostic code in the International Classification of Diseases (ICD), 10th revision.
However, the combination of sponsored genetic testing, the democratization of de-identified patient level healthcare data, the rise of tokenization across entities in the healthcare eco-system, and pharma’s reluctant embrace of Machine Learning, finally enables the clinical promise of precision medicine to become an analytical reality. In this session, we provide an overview of tokenization and integration with RWE data, and share a case study anchored in patient outcomes, where the above obstacles were overcome to effectively facilitate diagnosis for 66 previously un-diagnosed patients.
- John Garcia, Alnylam Pharmaceuticals
- Jonathan Woodring, Executive Vice President and General Manager, IPM.ai