Real World Evidence for Rare disease

Infographic courtesy RAREDISEASEDAY.ORG

Rare disease Day, recognises the 6,000+ identified, often life threatening, rare diseases*. Impacting over 300 million people worldwide, 72% of rare diseases are genetic, with 70% of those starting in childhood*. The low prevalence and often complex, chronically debilitating, degenerative nature, leads to diagnostic and treatment challenges.

Rare Diseases International, calls for universal health coverage and a call to leave no one behind. People living with rare diseases need equitable access to diagnosis, treatment and care.

“The time to integrate rare diseases, in the reflection on, and the practice of universal health coverage is now”

Rare disease international, 2019 position paper
Integrate Real World Data

A key challenge for improving diagnosis, treatment and outcomes arises from the small patient numbers. The ability to design robust research projects for evidence generation in the 6,000+ diseases is difficult. Todays environment of increasingly sophisticated data collection, along with the detailed digital health footprint left by patients, provides a wealth of evidence. Real world evidence collected through medical claims data, electronic health records and other data repositories, provide a data gold mine for science. Couple this with technology using machine learning or AI. Researchers can build a comprehensive view of a disease, the patient treatment journey and different cohorts. With an aim to improve diagnosis, treatment and outcomes.

Generate Evidence

Integrating health data to leverage what we already know, not only allows a historical analysis. It enables scenario planning, and prediction to inform future decisions. Examining patterns in data allows us to understand different cohorts of patients across geographies and patient demographics. As well as look at lifestyle, symptoms, diagnosis, treatments and outcomes. AI/ML can do this at speed, leading to rapid hypothesis generation & testing. Pooled research using health data and technology can guide clinical research studies. Leading to better disease awareness, diagnosis, treatment and care. Supporting management and advanced understanding of rare diseases.

*Nguengang Wakap, S., Lambert, D.M., Olry, A. et al. Estimating cumulative point prevalence of rare diseases: analysis of the Orphanet database. Eur J Hum Genet 28, 165–173 (2020).