On Monday, August 18th, real-world clinical data company Atropos Health announced that it has partnered with innovative medicines company Novartis to help train and improve medical AI models used to detect paroxysmal nocturnal hemoglobinuria (PNH). This rare disease is a blood disorder that can present with a variety of symptoms and can remain difficult to detect by medical professionals for months or even years—often leading to damage to the organs or worse of affected patients. Atropos’ development of an AI-model used to improve early PNH detection using real-world data and machine learning will help reduce the time to diagnose and treat PNH patients, vastly improving the outcomes and quality of life for those affected.
Atropos Health CEO and co-founder Dr. Brigham Hyde expressed the importance of the company’s new PNH detection efforts, stating, “Building AI models tested and trained on high-quality real-world data is truly the next frontier in precision medicine. The accuracy of the models reduces the guesswork and patients who are able to get testing sooner provides a potentially life-changing experience. For providers and health systems, faster time to diagnosis and treatment equate to higher patient satisfaction.”
Head of Oncology at Novartis US Rodney Gillespie also expressed his excitement with the announcement, saying that “[Novartis’] collaboration with Atropos Health to develop an AI model for identifying PNH embodies [our] commitment as it advances precision health, potentially enabling earlier diagnosis and timely care, reducing delays that can greatly affect patients’ lives.”
Founded in 2020 and located in Palo Alto, California, Atropos Health is the developer of GENEVA OS™—the first-of-its-kind system used to analyze healthcare evidence across an enormous network of real-world data. Novartis was founded in 1996 and operates globally out of Basel, Switzerland as one of the largest pharmaceutical companies in the world. For more information about this announcement, read the Atropos Health press release below.
See related materials: