Cargando…
Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose
It is widely acknowledged that information extraction of unstructured clinical notes using natural language processing (NLP) and text mining is essential for secondary use of clinical data for clinical research and practice. Lab test results are currently structured in most of the electronic health...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Medical Informatics Association
2017
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5543347/ https://www.ncbi.nlm.nih.gov/pubmed/28815133 |
_version_ | 1783255132364865536 |
---|---|
author | Liu, Sijia Wang, Liwei Ihrke, Donna Chaudhary, Vipin Tao, Cui Weng, Chunhua Liu, Hongfang |
author_facet | Liu, Sijia Wang, Liwei Ihrke, Donna Chaudhary, Vipin Tao, Cui Weng, Chunhua Liu, Hongfang |
author_sort | Liu, Sijia |
collection | PubMed |
description | It is widely acknowledged that information extraction of unstructured clinical notes using natural language processing (NLP) and text mining is essential for secondary use of clinical data for clinical research and practice. Lab test results are currently structured in most of the electronic health record (EHR) systems. However, for referral patients or lab tests that can be done in non-clinical setting, the results can be captured in unstructured clinical notes. In this study, we proposed a rule-based information extraction system to extract the lab test results with temporal information from clinical notes. The lab test results of glucose and HbA1c from 104 randomly sampled diabetes patients selected from 1996 to 2015 are extracted and further correlated with structured lab test information in the Mayo Clinic EHRs. The system has high F1-scores of 0.964, 0.967 and 0.966 in glucose, HbA1c and overall extraction, respectively. |
format | Online Article Text |
id | pubmed-5543347 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2017 |
publisher | American Medical Informatics Association |
record_format | MEDLINE/PubMed |
spelling | pubmed-55433472017-08-16 Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose Liu, Sijia Wang, Liwei Ihrke, Donna Chaudhary, Vipin Tao, Cui Weng, Chunhua Liu, Hongfang AMIA Jt Summits Transl Sci Proc Articles It is widely acknowledged that information extraction of unstructured clinical notes using natural language processing (NLP) and text mining is essential for secondary use of clinical data for clinical research and practice. Lab test results are currently structured in most of the electronic health record (EHR) systems. However, for referral patients or lab tests that can be done in non-clinical setting, the results can be captured in unstructured clinical notes. In this study, we proposed a rule-based information extraction system to extract the lab test results with temporal information from clinical notes. The lab test results of glucose and HbA1c from 104 randomly sampled diabetes patients selected from 1996 to 2015 are extracted and further correlated with structured lab test information in the Mayo Clinic EHRs. The system has high F1-scores of 0.964, 0.967 and 0.966 in glucose, HbA1c and overall extraction, respectively. American Medical Informatics Association 2017-07-26 /pmc/articles/PMC5543347/ /pubmed/28815133 Text en ©2017 AMIA - All rights reserved. This is an Open Access article: verbatim copying and redistribution of this article are permitted in all media for any purpose |
spellingShingle | Articles Liu, Sijia Wang, Liwei Ihrke, Donna Chaudhary, Vipin Tao, Cui Weng, Chunhua Liu, Hongfang Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title | Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title_full | Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title_fullStr | Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title_full_unstemmed | Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title_short | Correlating Lab Test Results in Clinical Notes with Structured Lab Data: A Case Study in HbA1c and Glucose |
title_sort | correlating lab test results in clinical notes with structured lab data: a case study in hba1c and glucose |
topic | Articles |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5543347/ https://www.ncbi.nlm.nih.gov/pubmed/28815133 |
work_keys_str_mv | AT liusijia correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT wangliwei correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT ihrkedonna correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT chaudharyvipin correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT taocui correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT wengchunhua correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose AT liuhongfang correlatinglabtestresultsinclinicalnoteswithstructuredlabdataacasestudyinhba1candglucose |