Objectives: The disease burden of wAIHA is not well known due to the difficulty of identifying patients in the absence of a diagnostic code for wAIHA. Our goals were to 1) identify a wAIHA cohort, 2) bisect severe versus non-severe patients, 3) compare comorbidities, anemia symptoms, treatments, diagnostic tests, and healthcare provider visits in these two groups, and 4) use a predictive model to validate clinical variables and prevalence estimates.

Methods: A de-identified, longitudinal, patient-level claims database of >300 million US patients was used to identify patients with wAIHA. Classification as severe required transfusion, frequent blood testing, frequent interactions with a hematologist, and/or >2 ER visits/year. Codes for anemia symptoms, comorbidities, treatments, and diagnostic tests were grouped and analyzed. Prevalence was estimated using Artificial Intelligence/Machine Learning (AI/ML) lookalike modeling.

Results: We identified 1,548 patients with wAIHA (n= 631 severe; n= 917 non-severe). The rate of disease-relevant claims was higher in severe patients; specifically, anemia symptomatology codes were 61% higher and wAIHA specific testing and monitoring codes were 570% higher over 12 months. Primary hypertension, hyperlipidemia, gastro-esophageal reflux, and evidence of chemotherapy use were more common in severe patients, while lupus was more common in non-severe patients. Severe patients also had a higher rate of claims related to Hospital/Emergency care. AI/ML modeling predicted patients using relevant claims variables and provided prevalence estimates comparable to reported US estimates of 30,000-49,000 patients.

Conclusions: We developed and validated a method for defining wAIHA patients using de-identified claims data. While disease manifestations were similar in severe and non-severe patients, the rate of occurrence was higher in severe patients, who also had higher healthcare resource utilization. Comorbidity with lupus was more common with non-severe wAIHA. This may indicate that a known diagnosis that requires monitoring could prevent the development of severe wAIHA.