Retrospective study of propionic acidemia using natural language processing in Mayo Clinic electronic health record

Hannah Barman1, Vanja Sikirica2, Katherine Carlson1

  • 1nference, One Main Street, Suite 400, East Arcade, 4th Floor, Cambridge, MA 02142, USA.

PubMed

Insights

Propionic acidemia (PA) is a rare metabolic disorder. This study details PA patient outcomes, revealing high complication rates and the significant burden of metabolic decompensation events (MDEs).

Area of Science:

  • Biochemistry
  • Genetics
  • Pediatrics

Background:

  • Propionic acidemia (PA) is a rare, autosomal recessive organic acidemia.
  • Limited data exist on the natural history, presentation, treatments, and outcomes of PA patients.

Purpose of the Study:

  • To retrospectively describe the natural history of PA patients.
  • Utilize real-world electronic health record (EHR) data, including structured and unstructured information, to detail PA patient care.

Main Methods:

  • Retrospective analysis of EHR data from 13 PA patients at the Mayo Clinic (1998-2022).
  • Employed natural language processing (NLP) on unstructured clinical notes and manual review for data accuracy.
  • Described complications, interventions, and encounters relative to the PA diagnosis index date.

Main Results:

  • 85% of PA patients experienced complications, including nutritional difficulties (46%), metabolic decompensation events (MDEs; 38%), and neurologic abnormalities (38%).
  • Patients with a history of MDEs presented with developmental delays and had higher complication rates.
  • Common presenting symptoms included hyperammonemia (78%) and decreased nutritional intake (67%).

Conclusions:

  • This study characterizes the spectrum and frequency of clinical outcomes in PA.
  • Highlights the significant clinical burden imposed by metabolic decompensation events in PA patients.
Abstract

Related Concept Videos