Harmonizing Multi-Institutional Clinical Documentation Using Natural Language Processing in Neurofibromatosis Type 1.

Stephanie M Morris^1,2, Levi Kaster³, Saki Amagai⁴, Carolyn Raski^5,6, Kelly Regan-Fendt^5,6, Yuan Luo⁴, Marc Rosenman^5,6, Carlos E Prada^5,6, Robert Listernick^5,6, Philip R O Payne³, David H Gutmann⁷, Aditi Gupta³

¹Department of Neurology, Kennedy Krieger Institute, Baltimore, MD.

²Department of Neurology, Johns Hopkins University, Baltimore, MD.

³Institute for Informatics, Data Science and Biostatistics, Washington University School of Medicine, St. Louis, MO.

⁴Department of Preventive Medicine, Northwestern University Feinberg School of Medicine, Chicago, IL.

⁵Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL.

⁶Ann & Robert H. Lurie Children's Hospital of Chicago, IL; and.

⁷Department of Neurology, Washington University School of Medicine, St. Louis, MO.

PubMed DOI

Abstract

BACKGROUND AND OBJECTIVES: Machine learning (ML) and natural language processing (NLP) approaches are increasingly used to support nuanced phenotyping, surveillance, and trial readiness using electronic health records (EHRs) in neurologic disease. However, inconsistent clinical documentation limits data harmonization and model performance, particularly in complex heterogeneous disorders such as ne…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.