Developing a Portable Natural Language Processing Based Phenotyping System

TL;DR

This paper introduces a portable NLP-based phenotyping system that integrates rule-based and machine learning methods, utilizing UMLS and OMOP CDM for standardization and adaptability across institutions.

Contribution

The system uniquely combines rule-based and statistical approaches with standard data models, enabling portability and reuse of clinical NLP components across different healthcare settings.

Findings

Achieved top 10 performance in obesity phenotyping challenge

Standardized data extraction using UMLS and OMOP CDM

Facilitated reuse and extension of rule-based NLP systems

Abstract

This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating OHDSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented with our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.