Atropos Enters Strategic Collaboration with Novartis to Use Real World Data to Find People with PNH

Rare Daily Staff

Atropos Health, a company that translates real-world clinical data into personalized real-world evidence and insights, said it entered into a collaboration with Novartis to build, train, and evaluate multiple models to help streamline the identification of people with a rare disease who have not yet been diagnosed.

The collaboration will specifically focus on paroxysmal nocturnal hemoglobinuria, or PNH, a rare, serious blood disorder. People with PNH have an acquired mutation in some hematopoietic stem cells that causes them to produce red blood cells susceptible to premature destruction by the complement system.

The goal of the strategic collaboration is to build and publish patient-finding models aimed at reducing time from initial symptoms to testing, diagnosis, and treatment. The models created by Atropos Health through this collaboration will be implemented across health system members of the Atropos Evidence Network and integrated at the point of care to improve the provider and patient experience.

Adults with PNH often experience lengthy diagnostic delays—many wait more than a year, and some more than five—because the disease is rare and presents varied symptoms affecting multiple organs. As part of this collaboration, Atropos Health has developed an initial AI model to identify potential PNH patients who have not yet been diagnosed. The model is now available for integration into health systems.

“Building AI models tested and trained on high-quality real-world data is truly the next frontier in precision medicine,” said Brigham Hyde, CEO and co-founder at Atropos Health. “The accuracy of the models reduces the guesswork, and patients who are able to get testing sooner experience a potentially life-changing benefit. For providers and health systems, faster time to diagnosis and treatment equates to higher patient satisfaction.”