CPM Blog

The Nashville Scene recently did an article about Innovators in middle Tennessee.  They featured PheWAS as one of 11 "groundbreaking" innovations.  See section "Model Behavior" in the Nashville Scene article. 

The system was developed and tested using a perioperative management system using a training set of 24,599 entries and a test set of 24,857 entries from Vanderbilt University.  Our goal was to develop a high performance, easily-maintained algorithm to identify medication and food allergies and sensitivities from unstructured allergy entries in electronic medical record (EHR) systems.

PheWAS using ICD9 codes Our EMR-based PheWAS uses a custom-developed grouping of International Classification of Disease, 9th edition (ICD9) codes.  These grouping loosely follow the 3-digit (category) and section groupings defined with the ICD9 code system itself, but vary to include, for example, all hypertension codes (401-405) as one grouping.  Each custom PheWAS code group also has an associated control group that excludes other related conditions (e.g., a patient with Graves disease cannot be a control for thyroiditis).    

Methods to identify gene-disease associations primarily rely on clinical trials or observational cohorts and, more recently, Electronic Medical Record-linked DNA Biobanks.  At Vanderbilt, we have used an EMR-linked DNA biobank called BioVU to derive case and controls populations using data within the EMR to define clinical phenotypes.  Genetic data for these EMR-linked association studies are redeposited into BioVU for future EMR-linked studies.  This has opened the possibility of "reverse GWAS" or "Phenome-wide association studies" (PheWAS). 

Methods to identify gene-disease associations primarily rely on clinical trials or observational cohorts and, more recently, Electronic Medical Record-linked DNA Biobanks.  At Vanderbilt, we have used an EMR-linked DNA biobank called BioVU to derive case and controls populations using data within the EMR to define clinical phenotypes.  Genetic data for these EMR-linked association studies are redeposited into BioVU for future EMR-linked studies.  This has opened the possibility of "reverse GWAS" or "Phenome-wide association studies" (PheWAS). 

MEDI (MEDication Indication) is an ensemble medication indication resource for primary and secondary uses of electronic medical record (EMR) data.  MEDI was created based on multiple commonly used medication resources (RxNorm, MedlinePlus, SIDER 2, and Wikipedia ) and by leveraging both ontology and natural language processing (NLP) techniques.   

Nature Biotech featured PheWAS paper as one of the top computational biology innovations in 2010.http://www.nature.com/nbt/journal/v29/n1/full/nbt0111-46.html

We replicated known genetic associations for five diseases. We genotyped the first 10,000 samples accrued into BioVU (the Vanderbilt EMR-associated DNA biobank) for twenty-one loci were associated with five common diseases (reported odds ratios 1.14-2.36) in at least two previous studies. We developed automated phenotype identification algorithms that used NLP techniques (to identify key findings, medication names, and family history), billing code queries, and structured data elements (such as laboratory results) to identify cases (n=70-698) and controls (n=808-3818).