Profiling and Diagnosing Rare Disease Patients

A pharmaceutical company needed to identify patients with hereditary ATTR (hATTR) amyloidosis, a rare genetic disorder, which required connecting disparate healthcare data sources to build a model capable of recognizing undiagnosed cases. The pharma company worked with an Advanced Analytics company to build a predictive model, with Datavant supplying the data matching/linking infrastructure needed to connect the data across databases while preserving privacy. The approach identified more than 60 new hATTR amyloidosis patients who may not have previously received a diagnosis.

The customer is anonymised in Datavant’s own case study — not withheld by us.

Datavant is the tokenization and linkage infrastructure behind most of the US real-world-data ecosystem — it de-identifies and connects patient records across health-data partners without exposing PII.

This sits in the Data Providers stage of the AI use-case lifecycle: Named examples from the real-world-data, claims and competitive-intelligence providers pharma AI systems are trained on, benchmarked against, or run inside of.