What question did this study set out to answer?

This study aims to develop an NLP-based method to automatically map clinical documents to coding systems and evaluate its effectiveness quantitatively.

June 8, 2004Open Access

Automated Encoding of Clinical Documents Based on Natural Language Processing

Key Points

This study aims to develop an NLP-based method to automatically map clinical documents to coding systems and evaluate its effectiveness quantitatively.
Adapted an existing NLP system, MedLEE, to generate codes from clinical documents.
Evaluated recall and precision through two test sets of 150 sentences each, processed by the adapted MedLEE system and reviewed by experts.
Compared results of the NLP system with manual coding standards established by seven experts.
The system achieved a recall of 0.77 for UMLS coding of all terms (95% CI 0.72-0.81).
For terms with corresponding UMLS codes, recall was 0.83 (95% CI 0.79-0.87).
The precision of the system was 0.89 (95% CI 0.87-0.91), outperforming expert precision which ranged from 0.61 to 0.91.

Abstract

OBJECTIVE: The aim of this study was to develop a method based on natural language processing (NLP) that automatically maps an entire clinical document to codes with modifiers and to quantitatively evaluate the method. METHODS: An existing NLP system, MedLEE, was adapted to automatically generate codes. The method involves matching of structured output generated by MedLEE consisting of findings and modifiers to obtain the most specific code. Recall and precision applied to Unified Medical Language System (UMLS) coding were evaluated in two separate studies. Recall was measured using a test set of 150 randomly selected sentences, which were processed using MedLEE. Results were compared with a reference standard determined manually by seven experts. Precision was measured using a second test set of 150 randomly selected sentences from which UMLS codes were automatically generated by the method and then validated by experts. RESULTS: Recall of the system for UMLS coding of all terms was .77 (95% CI.72-.81), and for coding terms that had corresponding UMLS codes recall was .83 (.79-.87). Recall of the system for extracting all terms was .84 (.81-.88). Recall of the experts ranged from .69 to .91 for extracting terms. The precision of the system was .89 (.87-.91), and precision of the experts ranged from .61 to .91. CONCLUSION: Extraction of relevant clinical information and UMLS coding were accomplished using a method based on NLP. The method appeared to be comparable to or better than six experts. The advantage of the method is that it maps text to codes along with other related information, rendering the coded output suitable for effective retrieval.

Read Full Paperexternally

Mark Helpful

Bookmark

Relay

View Full Paper