Background Paroxysmal nocturnal hemoglobinuria (PNH) is a life-threatening disease of dysregulated complement activation characterized by hemolysis and thrombosis and is associated with bone marrow failure. PNH can also impair patient quality of life and negatively impact the ability to work. PNH is a rare disease with an estimated incidence of 1 to 1.5 cases per million people globally. Inhibition of complement component 5 (C5) has been shown to reduce intravascular hemolysis, stabilize hemoglobin, reduce the need for blood transfusion, and improve quality of life for patients with PNH. C5 inhibitors eculizumab and ravulizumab are approved in the United States and other countries for treatment of PNH, yet there are limited data on the real-world use of these agents, especially in populations not eligible to participate in registrational clinical trials. Here we describe the COMMODORE Cohort study, which will use a novel patient-centered study design to collect both retrospective and prospective patient data on the real-world use, safety, and effectiveness of eculizumab and ravulizumab, as well as disease burden and outcomes, in patients with PNH in the United States. Study Design and Methods This noninterventional cohort study will collect data using the PicnicHealth digital personal health record platform. This platform uses a novel human-in-the-loop machine learning system to integrate, harmonize, and structure patient data, including clinical notes, medications, laboratory results, and diagnostic reports contained in medical records collected from any healthcare facility in the United States. This study was designed in collaboration with patient advocacy groups to ensure that data generated will answer questions important to the patient community. In contrast to many studies, patients will be directly recruited to participate through multiple avenues, including working with patient advocacy groups and societies as well as outreach through social media and other communication tools. All patients must complete an informed consent form to participate. Patient data is anonymized, and the study complies with the Health Insurance Portability and Accountability Act data security standards. The study will be submitted to IntegReview for institutional review board approval. Patients who report a diagnosis of PNH within the past 5 years and have subsequently been treated with eculizumab or ravulizumab can be included in this study (Figure). Data extracted by the platform will confirm that the patient meets study criteria. The study has 3 arms: arm A is comprised of patients who initiated therapy with eculizumab, arm B is patients who initiated therapy with ravulizumab, and arm C is patients who initiated therapy with eculizumab and later switched to ravulizumab. Exclusion criteria for patients in arms A and B includes treatment with a complement inhibitor prior to PNH diagnosis and treatment with eculizumab or ravulizumab for > 25 weeks. Exclusion criteria for all patients include platelet count < 30,000/μL, absolute neutrophil count < 500/μL, and history of bone marrow transplant. The primary objective is to describe the proportion of patients who do not receive packed red blood cell transfusion. Secondary objectives are to determine the proportions of patients with breakthrough hemolysis, stabilized hemoglobin, and a thromboembolic event and the change in normalized lactate dehydrogenase. Safety objectives are to determine the rates and proportions of selected adverse events. Primary, secondary, and safety objectives will be evaluated from week 5 to 25 of treatment. The effectiveness and safety analyses will be conducted in all patients who fulfill entry criteria and have a minimum of 25 weeks of accrued person-time from treatment initiation. Exploratory analyses assessing long-term experiences and outcomes and will be conducted in all patients who fulfill entry criteria with no minimum treatment duration requirement. Descriptive statistics will be provided. Summary The COMMODORE Cohort study will use a novel, patient-centered approach to data generation including collaborating with patient groups to ensure that the study answers questions important to the PNH community. This approach may serve as a model for future studies evaluating other rare diseases with limited real-world data. Disclosures Shang: F. Hoffmann-La Roche Ltd: Current Employment, Current equity holder in publicly-traded company, Other: All authors received support for third party writing assistance, furnished by Scott Battle, PhD, provided by F. Hoffmann-La Roche, Basel, Switzerland.. Faghmous:Kite Pharma: Current Employment; F. Hoffmann-La Roche Ltd: Ended employment in the past 24 months, Other: All authors received medical writing support for this abstract, furnished by Scott Battle, funded by F. Hoffmann-La Roche Ltd, Basel, Switzerland. . Drozd:PicnicHealth: Current Employment, Current equity holder in private company; F. Hoffmann-La Roche Ltd: Other: All authors received support for third party writing assistance, furnished by Scott Battle, PhD, provided by F. Hoffmann-La Roche, Basel, Switzerland.. Katz:F. Hoffmann-La Roche Ltd: Current Employment, Other: All authors received support for third party writing assistance, furnished by Scott Battle, PhD, provided by F. Hoffmann-La Roche, Basel, Switzerland..