Automated Diabetes Case Identification Using Electronic Health Record Data at a Tertiary Care Facility

To develop and validate a phenotyping algorithm for the identification of patients with type 1 and type 2 diabetes mellitus (DM) preoperatively using routinely available clinical data from electronic health records. We used first-order logic rules (if-then-else rules) to imply the presence or absenc...

Full description

Saved in:

Bibliographic Details
Published in:	Mayo Clinic proceedings. Innovations, quality & outcomes Vol. 1; no. 1; pp. 100 - 110
Main Authors:	Upadhyaya, Sudhi G., Murphree, Dennis H., Ngufor, Che G., Knight, Alison M., Cronk, Daniel J., Cima, Robert R., Curry, Timothy B., Pathak, Jyotishman, Carter, Rickey E., Kor, Daryl J.
Format:	Journal Article
Language:	English
Published:	Netherlands Elsevier Inc 01-07-2017 Elsevier
Subjects:	Original T1DM T2DM DDC HbA1c of NYC eMERGE MICS DM EHR NLP ICD-9-CM CCW SUPREME-DM HbA1c T1DM, type 1 diabetes mellitus T2DM, type 2 diabetes mellitus DM, diabetes mellitus SUPREME-DM, Surveillance, Prevention, and Management of Diabetes Mellitus eMERGE, Electronic Medical Records and Genomics EHR, electronic health record ICD-9-CM, International Classification of Diseases, Ninth Revision, Clinical Modification HbA1c of NYC, Hemoglobin A1c of New York City MICS, Mayo Integrated Clinical Systems CCW, Chronic Condition Data Warehouse HbA1c, hemoglobin A1c DDC, Durham Diabetes Coalition NLP, natural language processing
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	To develop and validate a phenotyping algorithm for the identification of patients with type 1 and type 2 diabetes mellitus (DM) preoperatively using routinely available clinical data from electronic health records. We used first-order logic rules (if-then-else rules) to imply the presence or absence of DM types 1 and 2. The “if” clause of each rule is a conjunction of logical and, or predicates that provides evidence toward or against the presence of DM. The rule includes International Classification of Diseases, Ninth Revision, Clinical Modification diagnostic codes, outpatient prescription information, laboratory values, and positive annotation of DM in patients’ clinical notes. This study was conducted from March 2, 2015, through February 10, 2016. The performance of our rule-based approach and similar approaches proposed by other institutions was evaluated with a reference standard created by an expert reviewer and implemented for routine clinical care at an academic medical center. A total of 4208 surgical patients (mean age, 52 years; males, 48%) were analyzed to develop the phenotyping algorithm. Expert review identified 685 patients (16.28% of the full cohort) as having DM. Our proposed method identified 684 patients (16.25%) as having DM. The algorithm performed well—99.70% sensitivity, 99.97% specificity—and compared favorably with previous approaches. Among patients undergoing surgery, determination of DM can be made with high accuracy using simple, computationally efficient rules. Knowledge of patients’ DM status before surgery may alter physicians’ care plan and reduce postsurgical complications. Nevertheless, future efforts are necessary to determine the effect of first-order logic rules on clinical processes and patient outcomes.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ISSN:	2542-4548 2542-4548
DOI:	10.1016/j.mayocpiqo.2017.04.005