EHR algorithm can be used to detect, classify diabetes

December 10, 2012
EHR algorithm can be used to detect, classify diabetes
Data from electronic health records can be used to detect more cases of diabetes than claim codes alone and can be used to accurately distinguish between type 1 and type 2 diabetes, according to a study published online Nov. 27 in Diabetes Care.

(HealthDay)—Data from electronic health records (EHRs) can be used to detect more cases of diabetes than claim codes alone and can be used to accurately distinguish between type 1 and type 2 diabetes, according to a study published online Nov. 27 in Diabetes Care.

To classify type 1 versus type 2 disease, Michael Klompas, M.D., M.P.H., of Harvard Medical School and the Harvard Pilgrim Health Care Institute in Boston, and colleagues used four years of structured EHR data, such as laboratory test results, diagnosis codes, and suggestive prescriptions, from a large, multispecialty ambulatory practice serving approximately 700,000 patients. The optimized algorithm was tested in a cohort of 210 patients and validated in an additional cohort.

The researchers found that the algorithm flagged 43,177 patients. For type 1 diabetes, the sensitivity and of the International Classification of Diseases version 9 codes were 26 and 94 percent, respectively, for type 1 codes alone, and 90 and 57 percent, respectively, for two or more type 1 codes and any number of type 2 codes. Using an optimized algorithm incorporating the ratio of these codes plus additional information on plasma C-peptide and autoantibody levels and suggestive prescriptions, 100 percent of patients with type 1 diabetes were flagged. On validation, the optimized algorithm correctly identified 35 of 36 patients with .

"In sum, we demonstrate the utility of EHR-based algorithms to detect and classify patients with diabetes," the authors write.

One author is an employee of Heliotropic Inc.

Explore further: 'Jack Spratt' diabetes gene identified

More information: Abstract
Full Text (subscription or payment may be required)

Related Stories

'Jack Spratt' diabetes gene identified

June 1, 2012

Type 2 diabetes is popularly associated with obesity and a sedentary lifestyle. However, just as there are obese people without type 2 diabetes, there are lean people with the disease.

Cataract risk up for statin users with type 2 diabetes

August 13, 2012

(HealthDay) -- Statin use, which is substantially higher in patients with type 2 diabetes, correlates with an increased risk of age-related (AR) cataracts, according to a study published in the August issue of Optometry and ...

Lung cancer risk unaffected by metformin use in diabetes

August 30, 2012

(HealthDay)—Patients with type 2 diabetes who take metformin do not have a reduced risk of lung cancer, in contrast to previous observational studies, according to a study published online Aug. 24 in Diabetes Care.

Study assesses bidirectional link for diabetes, depression

November 19, 2012

(HealthDay)—There is a bidirectional relationship between type 2 diabetes and depression, with a stronger correlation for depression predicting diabetes onset, according to research published online Nov. 12 in Diabetes ...

Recommended for you

Diets avoiding dry-cooked foods can protect against diabetes

August 24, 2016

Simple changes in how we cook could go a long way towards preventing diabetes, say researchers at the Icahn School of Medicine at Mount Sinai. A new randomized controlled trial, published online July 29 in the journal Diabetologia, ...

New study reveals a novel protein linked to type 2 diabetes

August 16, 2016

Findings from Boston University School of Medicine (BUSM), which appear in eLife, provide a possible explanation as to why most people who are obese develop insulin resistance and type 2 diabetes. A minority of obese individuals, ...

Gene variant explains differences in diabetes drug response

August 9, 2016

The first results from a large international study of patients taking metformin, the world's most commonly used type 2 diabetes drug, reveal genetic differences among patients that may explain why some respond much better ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.