Natural Language Processing

Digital Rectal Exam

Described in this document are the Stanford University algorithms for extracting both cases and controls of digital rectal examination (DRE) from electronic health records (EHR) of prostate cancer patients. DRE is a clinical procedure, part of a set of quality metrics used to determine quality care for these patients. In this regard, DRE is defined as quality care when it is performed within a time period of up to six months before first treatment for prostate cancer. For the purposes of this algorithm a case is defined as DRE documented, whereas a control is DRE not documented.

Final

Diverticulosis and Diverticulitis

An algorithm for finding patients with diverticulosis, and of those, patients who also have diverticulitis, and to also find control patients.  Control patients will have had a colonoscopy but have no evidence of diverticula.

Simple NLP (a portable program is posted here, with instructions, and support is availabe from NU as needed) of colonoscopy reports is the gold standard algorithm, but if the text of colonoscopy reports is not available, an alternate algorithm using CPT & ICD-9 codes can be used, which is also posted.

Owner Phenotyping Groups: 
View Phenotyping Groups: 
Final

Drug Induced Liver Injury

An algorithm to identify inpatients who have had an acute episode of drug induced liver injury (DILI).

Summary of drug-induced liver injury algorithm

Inclusion criteria

A. Suspect DILI? (NOTE: baseline population is institution specific.  See institution implementation details)

1.     Liver injury AND Exposure to drug (NOTE: medications are institution specific. See institution implementation details)

2.     Temporal relationship of exposure to drug and liver injury diagnosis.

Owner Phenotyping Groups: 
View Phenotyping Groups: 
Final

Electronic Health Record-based Phenotyping Algorithm for Familial Hypercholesterolemia

Familial hypercholesterolemia (FH) is a relatively common Mendelian genetic disorder that is associated with elevated plasma low-density lipoprotein cholesterol (LDL-C) levels and dramatically increased lifetime risk for premature atherosclerotic cardiovascular disease (ASCVD). FH can be diagnosed based on clinical presentation and/or genetic testing results, with a positive genetic testing considered to be the “gold standard”.

Owner Phenotyping Groups: 
Final

Hypothyroidism

Project Outline:  Selection of all Caucasian patients with hypothyroidism without a secondary cause of surgical removal or radiological ablation.  The search is designed to eliminate subclinical hypothyroidism (by requiring that patients be on a replacement medication), medication-induced hypothyroidism (e.g., PTU, lithium, or history of amiodarone), and transient causes (e.g., pregnancy or subacute thyroiditis).

Owner Phenotyping Groups: 
View Phenotyping Groups: 
Final

Identification of Fibromyalgia Patients in a Rheumatoid Arthritis Cohort

Fibromyalgia has been estimated to affect 12-17% of rheumatoid arthritis patients (1, 2). 

This algorithm was created to identify fibromyalgia patients in a population of rheumatoid arthritis patients. The gold standard used for diagnosis of fibromyalgia was that the treating rheumatologist made a clinical diagnosis of fibromyalgia. Rheumatoid arthritis patients were identified by using a previously validated algorithm (3). 

Algorithm included the following conditions: 

Owner Phenotyping Groups: 
Final

Liver cancer staging project

Hepatocellular carcinoma (HCC), the primary form of liver cancer, is one of the leading cancer-related causes of death worldwide. There are many complex treatment strategies; the populations are heterogeneous, with different genetic, lifestyle, and comorbity differences.

Here we describe the algorithm used to identify HCC liver cancer stages for AJCC, BCLC, and CLIP liver cancer staging systems.

Algorithm:

Step 1) Patient files and laboratories

Final

Pages