Related Experiment Video
Updated: May 6, 2026
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
Published on: September 20, 2018
Deriving comorbidities from medical records using natural language processing
Hojjat Salmasian1, Daniel E Freedberg, Carol Friedman
1Department of Biomedical Informatics, Columbia University, New York, USA.
Insights
This study introduces an automated method for extracting comorbidity data from electronic medical records, achieving high accuracy. This approach can aid in predicting patient outcomes like mortality and readmission.
Area of Science:
- Medical Informatics
- Clinical Research
- Natural Language Processing
Background:
- Comorbidity information is vital for phenotypic studies due to its confounding effects.
- Accurate comorbidity extraction from electronic medical records (EMRs) is challenging but essential.
Purpose of the Study:
- To develop and validate an automated method for extracting comorbidity information from EMRs.
- To compare the performance of automated extraction against traditional claims data.
Main Methods:
- A modified Charlson Comorbidity Index (CCI) was used, with a reference standard created by two physicians from 100 admission notes.
- The MedLEE natural language processing system processed notes, and queries were written for automated comorbidity extraction.
- Interrater agreement for the reference set was 97.7%.
Main Results:
- The automated method achieved an F1 score of 0.761, with no significant difference in summed CCI scores compared to the reference standard.
- Automated extraction outperformed claims data (F1 score 0.741) due to higher sensitivity (66.1%).
Conclusions:
- The developed automated method accurately determines comorbidities from EMRs.
- This technique enables automated prediction of mortality and readmission, leveraging the validated predictive power of the CCI.
Abstract:
Extracting comorbidity information is crucial for phenotypic studies because of the confounding effect of comorbidities. We developed an automated method that accurately determines comorbidities from electronic medical records. Using a modified version of the Charlson comorbidity index (CCI), two physicians created a reference standard of comorbidities by manual review of 100 admission notes. We processed the notes using the MedLEE natural language processing system, and wrote queries to extract comorbidities automatically from its structured output. Interrater agreement for the reference set was very high (97.7%). Our method yielded an F1 score of 0.761 and the summed CCI score was not different from the reference standard (p=0.329, power 80.4%). In comparison, obtaining comorbidities from claims data yielded an F1 score of 0.741, due to lower sensitivity (66.1%). Because CCI has previously been validated as a predictor of mortality and readmission, our method could allow automated prediction of these outcomes.
More Related Videos
Related Concept Videos
01:17Classification of Illness
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
01:26Methods of Documentation II: POMR
02:02Genomics
01:17Introduction to Language of Pathophysiology ll
01:11Purpose of Health Records I
Here's a breakdown of how health records serve these purposes:
01:10Documentation of Nursing Diagnosis
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...