Atropos Health and Novartis Partner to Deploy AI for Faster Rare Disease Diagnosis in PNH Patients
核心洞察
Atropos Health (搜索) has partnered with Novartis to develop AI models that identify undiagnosed patients with paroxysmal nocturnal hemoglobinuria (搜索) (PNH (搜索)), a rare blood disorder affecting 10-20 people per million worldwide.
The collaboration addresses critical diagnostic delays in PNH (搜索), where many patients wait over a year for diagnosis and some wait more than five years due to the disease's rarity and varied symptoms.
The AI model, trained on real-world data from the Atropos Evidence Network, is now available for integration into health systems to accelerate appropriate diagnosis at the point of care.
Atropos Health (搜索) announced a strategic collaboration with Novartis to develop artificial intelligence models that identify undiagnosed patients with paroxysmal nocturnal hemoglobinuria (搜索) (PNH (搜索)), addressing critical diagnostic delays that can extend beyond five years for some patients with this rare blood disorder.
The collaboration specifically targets PNH (搜索), a rare, chronic and serious complement-mediated blood disorder that affects approximately 10-20 people per million worldwide. Adults with PNH often experience lengthy diagnostic delays—many wait over a year, and some more than five years—because the disease is rare and presents varied symptoms affecting multiple organs.
AI Model Development and Implementation
Atropos Health (搜索) has developed an initial AI model for finding potential patients with PNH (搜索) who have not yet been diagnosed, aimed at saving critical time for both patients and providers by helping health systems accelerate appropriate diagnosis. The AI model is now available for integration into health systems and will be implemented across health system members of the Atropos Evidence Network.
"Building AI models tested and trained on high-quality real-world data is truly the next frontier in precision medicine," said Dr. Brigham Hyde, CEO and co-founder at Atropos Health (搜索). "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."
The models will be trained on real-world data from the Atropos Evidence Network, which includes GENEVA OS. The collaboration aims to build and publish patient-finding models designed to reduce time from initial symptoms to testing, diagnosis and treatment, with seamless integration at the point of care to improve both provider and patient experience.
Clinical Significance and Disease Background
PNH (搜索) patients have an acquired mutation in some of their hematopoietic stem cells located in the bone marrow, which causes them to produce red blood cells that are susceptible to premature destruction by the complement system (搜索). Although PNH can develop at any age, it is often diagnosed in people between 30-40 years old.
"At Novartis, we are committed to delivering meaningful impact for patients. Accelerating diagnosis and treatment through AI and machine learning has the power to significantly improve patient outcomes by enabling faster access to appropriate care," said Rodney Gillespie, Head of Oncology, Novartis US. "Our collaboration with Atropos Health (搜索) to develop an AI model for identifying PNH (搜索) embodies this commitment as it advances precision health, potentially enabling earlier diagnosis and timely care, reducing delays that can greatly affect patients' lives."
Technology Platform and Network Integration
The announcement follows Atropos Health (搜索)'s AI model training capabilities released earlier this year. The company is also collaborating with Arcadia to help leading healthcare organizations deliver advanced precision medicine at scale, enabling healthcare providers to accelerate clinical decision-making with actionable, AI-powered insights at the point of care using real-world evidence and longitudinal patient records.
Healthcare organizations are engaged with Atropos Health (搜索) on leveraging AI for precision medicine and building MOTOR, CLMBR and Foundation models on the Atropos Evidence Network. The partnership enables the combination of real-world evidence and longitudinal patient records to improve outcomes and drive high-value, low-cost care.