Amy Joseph1, Charles Mullett1,2, Christa Lilly3, Matthew Armistead2, Harold J Cox2, Michael Denney2, Misha Varma1, David Rich4, Donald A Adjeroh5, Gianfranco Doretto5, William Neal1, Lee A Pyles1. 1. Department of Pediatrics, School of Medicine, West Virginia University, Morgantown, West Virginia, United States. 2. West Virginia Clinical and Translational Science Institute, West Virginia University, Morgantown, West Virginia, United States. 3. Department of Biostatistics, School of Public Health, West Virginia University, Morgantown, West Virginia, United States. 4. West Virginia University Hospital System, Morgantown, West Virginia, United States. 5. Lane Department of Computer Science and Electrical Engineering, Benjamin M. Statler College of Engineering and Mineral Resources, West Virginia University, Morgantown, West Virginia, United States.
Abstract
BACKGROUND: The United States, and especially West Virginia, have a tremendous burden of coronary artery disease (CAD). Undiagnosed familial hypercholesterolemia (FH) is an important factor for CAD in the U.S. Identification of a CAD phenotype is an initial step to find families with FH. OBJECTIVE: We hypothesized that a CAD phenotype detection algorithm that uses discrete data elements from electronic health records (EHRs) can be validated from EHR information housed in a data repository. METHODS: We developed an algorithm to detect a CAD phenotype which searched through discrete data elements, such as diagnosis, problem lists, medical history, billing, and procedure (International Classification of Diseases [ICD]-9/10 and Current Procedural Terminology [CPT]) codes. The algorithm was applied to two cohorts of 500 patients, each with varying characteristics. The second (younger) cohort consisted of parents from a school child screening program. We then determined which patients had CAD by systematic, blinded review of EHRs. Following this, we revised the algorithm by refining the acceptable diagnoses and procedures. We ran the second algorithm on the same cohorts and determined the accuracy of the modification. RESULTS: CAD phenotype Algorithm I was 89.6% accurate, 94.6% sensitive, and 85.6% specific for group 1. After revising the algorithm (denoted CAD Algorithm II) and applying it to the same groups 1 and 2, sensitivity 98.2%, specificity 87.8%, and accuracy 92.4; accuracy 93% for group 2. Group 1 F1 score was 92.4%. Specific ICD-10 and CPT codes such as "coronary angiography through a vein graft" were more useful than generic terms. CONCLUSION: We have created an algorithm, CAD Algorithm II, that detects CAD on a large scale with high accuracy and sensitivity (recall). It has proven useful among varied patient populations. Use of this algorithm can extend to monitor a registry of patients in an EHR and/or to identify a group such as those with likely FH. Thieme. All rights reserved.
BACKGROUND: The United States, and especially West Virginia, have a tremendous burden of coronary artery disease (CAD). Undiagnosed familial hypercholesterolemia (FH) is an important factor for CAD in the U.S. Identification of a CAD phenotype is an initial step to find families with FH. OBJECTIVE: We hypothesized that a CAD phenotype detection algorithm that uses discrete data elements from electronic health records (EHRs) can be validated from EHR information housed in a data repository. METHODS: We developed an algorithm to detect a CAD phenotype which searched through discrete data elements, such as diagnosis, problem lists, medical history, billing, and procedure (International Classification of Diseases [ICD]-9/10 and Current Procedural Terminology [CPT]) codes. The algorithm was applied to two cohorts of 500 patients, each with varying characteristics. The second (younger) cohort consisted of parents from a school child screening program. We then determined which patients had CAD by systematic, blinded review of EHRs. Following this, we revised the algorithm by refining the acceptable diagnoses and procedures. We ran the second algorithm on the same cohorts and determined the accuracy of the modification. RESULTS: CAD phenotype Algorithm I was 89.6% accurate, 94.6% sensitive, and 85.6% specific for group 1. After revising the algorithm (denoted CAD Algorithm II) and applying it to the same groups 1 and 2, sensitivity 98.2%, specificity 87.8%, and accuracy 92.4; accuracy 93% for group 2. Group 1 F1 score was 92.4%. Specific ICD-10 and CPT codes such as "coronary angiography through a vein graft" were more useful than generic terms. CONCLUSION: We have created an algorithm, CAD Algorithm II, that detects CAD on a large scale with high accuracy and sensitivity (recall). It has proven useful among varied patient populations. Use of this algorithm can extend to monitor a registry of patients in an EHR and/or to identify a group such as those with likely FH. Thieme. All rights reserved.
Authors: Ilse K Luirink; Albert Wiegman; D Meeike Kusters; Michel H Hof; Jaap W Groothoff; Eric de Groot; John J P Kastelein; Barbara A Hutten Journal: N Engl J Med Date: 2019-10-17 Impact factor: 91.245
Authors: Lori L Popejoy; Mohammed A Khalilia; Mihail Popescu; Colleen Galambos; Vanessa Lyons; Marilyn Rantz; Lanis Hicks; Frank Stetzer Journal: J Am Med Inform Assoc Date: 2014-10-16 Impact factor: 4.497
Authors: Pedro L Teixeira; Wei-Qi Wei; Robert M Cronin; Huan Mo; Jacob P VanHouten; Robert J Carroll; Eric LaRose; Lisa A Bastarache; S Trent Rosenbloom; Todd L Edwards; Dan M Roden; Thomas A Lasko; Richard A Dart; Anne M Nikolai; Peggy L Peissig; Joshua C Denny Journal: J Am Med Inform Assoc Date: 2016-08-07 Impact factor: 4.497
Authors: Børge G Nordestgaard; M John Chapman; Steve E Humphries; Henry N Ginsberg; Luis Masana; Olivier S Descamps; Olov Wiklund; Robert A Hegele; Frederick J Raal; Joep C Defesche; Albert Wiegman; Raul D Santos; Gerald F Watts; Klaus G Parhofer; G Kees Hovingh; Petri T Kovanen; Catherine Boileau; Maurizio Averna; Jan Borén; Eric Bruckert; Alberico L Catapano; Jan Albert Kuivenhoven; Päivi Pajukanta; Kausik Ray; Anton F H Stalenhoef; Erik Stroes; Marja-Riitta Taskinen; Anne Tybjærg-Hansen Journal: Eur Heart J Date: 2013-08-15 Impact factor: 29.983
Authors: Rahul Kashyap; Kumar Sarvottam; Gregory A Wilson; Jacob C Jentzer; Mohamed O Seisa; Kianoush B Kashani Journal: BMC Med Inform Decis Mak Date: 2020-05-07 Impact factor: 2.796
Authors: Katherine P Liao; Ashwin N Ananthakrishnan; Vishesh Kumar; Zongqi Xia; Andrew Cagan; Vivian S Gainer; Sergey Goryachev; Pei Chen; Guergana K Savova; Denis Agniel; Susanne Churchill; Jaeyoung Lee; Shawn N Murphy; Robert M Plenge; Peter Szolovits; Isaac Kohane; Stanley Y Shaw; Elizabeth W Karlson; Tianxi Cai Journal: PLoS One Date: 2015-08-24 Impact factor: 3.240