Retrospective Study of Propionic Acidemia Using Natural Language Processing in Mayo Clinic Electronic Health Record Data

Open full publication

Conclusions: • This retrospective, descriptive study of diagnostically confirmed patients with PA in the Mayo Clinic EHR demonstrates the range and frequency of clinical outcomes of such patients and highlights the disease burden experienced by individuals with PA who have a history of MDEs • This analysis shows a clear and detailed view of complications, comorbidities, and treatments for patients with PA in the real-world setting, and subsetting patients by those who do and do not experience MDEs offers a unique perspective into PA outcomes and severity • Overall, augmented curation, supplemented by structured EHR data and manual review, allowed for a robust and thorough understanding of PA outcomes by enabling extraction of MDEs, salient PA-related HCRU, treatments, symptomatology, and comorbidities not detected by structured diagnosis, procedure, or medication code

nference, Cambridge, Massachusetts, USA Moderna, Inc., Cambridge, Massachusetts, USA Department of Clinical Genomics, Mayo Clinic, Rochester, Minnesota, USA