Natural Language Processing

ACE Inhibitor (ACE-I) induced cough

ACE-I induced cough is a common side effect of use of ACE inhibitors, one of the most common class of antihypertensives.  The frequency of ACEI-induced cough varies based on ancestry.  A GWAS of ACEI cough using this algorithm in the eMERGE Network identified KCNIP4 as associated with this phenotype, which was validated in two replication cohorts. 

Cases are those with ACEI cough.  Controls are those exposed to ACEI without adverse events noted and not switched to angiotensin receptor blockers (ARBs).  

Algorithm validated - December 12, 2012.

Owner Phenotyping Groups: 
eMERGE Vanderbilt Group
View Phenotyping Groups: 
eMERGE Phenotype WG
Final

Appendicitis

Appendicitis is one of the most common acquired surgical conditions of childhood.  Diagnosis of appendicitis remains difficult.  Much work has been done on validation of clinical scores to reduce the number of unnecessary surgeries and radiographic tests while maintaining a high sensitivity for disease.  However, no score performs well enough in practice to reduce these risks (Kulik et al., 2013).  It is also known that appendicitis has a familial predominance, but little is known about the genetic factors that may increase a certain child's risk for the condition (Oldmeadow et al., 2009). 

Owner Phenotyping Groups: 
eMERGE CCHMC/BCH Group
View Phenotyping Groups: 
eMERGE Phenotype WG
Final

Atrial Fibrillation - Demonstration Project

Atrial Fibrillation phenotype algorithm for the DNA Demonstration project.  The algorithm selects cases based on atrial fibrillation but no presence of a heart transplant.  Controls select for records with no evidence of atrial flutter, atrial fibrillation, or atrial tachycardia but with at least one ECG.

 

 

Diagnostic Codes?

Text Keywords?

Owner Phenotyping Groups: 
Vanderbilt - SD/RD Group
View Phenotyping Groups: 
Vanderbilt - SD/RD Group
Final

bone scan utilization

Objective
Clinical care guidelines recommend that newly diagnosed prostate cancer patients at high risk for metastatic spread receive a bone scan prior to treatment and that low risk patients not receive it. The objective was to develop an automated pipeline to interrogate heterogeneous data to evaluate the use of bone scans using a two different Natural Language Processing (NLP) approaches.

Final

Breast Cancer

Breast cancer is the most common cancer and the second leading cause of cancer-related death among women in the U.S. Known breast cancer risk factors include age, race/ethnicity, reproductive factors, and benign breast disease. Family history of breast cancer and hereditary cancer syndromes, such as BRCA1/BRCA2 mutations, confer the strongest risk for this disease.

Owner Phenotyping Groups: 
eMERGE Columbia Group
View Phenotyping Groups: 
001
American-Swiss Allergy Phenotyping Group
BioVU Phenotyping
Clostridium Difficile Colitis Phenotype Group
Data Science to Patient Value Initiative (D2V) - Colorado
Denny’s Group at Vandy
eMERGE CCHMC Group
eMERGE CCHMC/BCH Group
eMERGE CHOP Group
eMERGE Columbia Group
eMERGE Geisinger Group
eMERGE GHC/University of Washington Group
eMERGE Harvard Group
eMERGE Marshfield Group
eMERGE Mayo Group
eMERGE Meharry Group
eMERGE Mount Sinai Group
eMERGE Northwestern Group
eMERGE Phenotype WG
eMERGE Vanderbilt Group
Farr Institute Kidney Working Group
GPC
NIH Collaboratory Group
PCORI CDRN/PPRN
PCORI MidSouth CDRN
PCORI MidSouth CDRN/Duke Group
PCORI MidSouth CDRN/Greenway Group
PCORI MidSouth CDRN/HSSC Group
PCORI MidSouth CDRN/Meharry Group
PCORI MidSouth CDRN/UNC Group
PCORI MidSouth CDRN/VUMC Group
PGPop WG
PGx model group
PGx Workgroup
PheMA Test Group
Precision Medicine and Health Disparities Collaborative
Resistant hypertension WG
Vanderbilt - Music Cognition Lab
Vanderbilt - SD/RD Group
VESPA - Vanderbilt Electronic Systems for Pharmacogenomic Assessment
VICTR Phenotyping
Final

CAAD (Carotid Artery Atherosclerosis Disease)

Carotid artert atherosclerosis disease (CAAD) is measured in cases and controls by both structured data, including ICD diagnosis codes, and quantitative measurements of carotid stenosis based on doppler and other imaging technologies.

The phenotype algorithm includes typical eMERGE pseudo code for implementing the structured data components of the algorithm, as well as a portable natural language processing (NLP) system used to extract percent stenosis measurements from imaging reports.

Owner Phenotyping Groups: 
eMERGE GHC/University of Washington Group
View Phenotyping Groups: 
eMERGE Phenotype WG
Final

Pages