@article{ba9a5b5f549a4d669d93aaa55ac87f67,
title = "Under-specification as the source of ambiguity and vagueness in narrative phenotype algorithm definitions",
abstract = "Introduction: Currently, one of the commonly used methods for disseminating electronic health record (EHR)-based phenotype algorithms is providing a narrative description of the algorithm logic, often accompanied by flowcharts. A challenge with this mode of dissemination is the potential for under-specification in the algorithm definition, which leads to ambiguity and vagueness. Methods: This study examines incidents of under-specification that occurred during the implementation of 34 narrative phenotyping algorithms in the electronic Medical Record and Genomics (eMERGE) network. We reviewed the online communication history between algorithm developers and implementers within the Phenotype Knowledge Base (PheKB) platform, where questions could be raised and answered regarding the intended implementation of a phenotype algorithm. Results: We developed a taxonomy of under-specification categories via an iterative review process between two groups of annotators. Under-specifications that lead to ambiguity and vagueness were consistently found across narrative phenotype algorithms developed by all involved eMERGE sites. Discussion and conclusion: Our findings highlight that under-specification is an impediment to the accuracy and efficiency of the implementation of current narrative phenotyping algorithms, and we propose approaches for mitigating these issues and improved methods for disseminating EHR phenotyping algorithms.",
keywords = "Algorithm: Natural Language, Ambiguity, Electronic Health Records (EHR), Phenotyping, Under-Specification, Vagueness",
author = "Jingzhi Yu and Pacheco, {Jennifer A.} and Ghosh, {Anika S.} and Yuan Luo and Chunhua Weng and Ning Shang and Barbara Benoit and Carrell, {David S.} and Carroll, {Robert J.} and Ozan Dikilitas and Freimuth, {Robert R.} and Gainer, {Vivian S.} and Hakon Hakonarson and George Hripcsak and Kullo, {Iftikhar J.} and Frank Mentch and Murphy, {Shawn N.} and Peissig, {Peggy L.} and Ramirez, {Andrea H.} and Nephi Walton and Wei, {Wei Qi} and Rasmussen, {Luke V.}",
note = "Funding Information: This work was primarily conducted under Phase III of the eMERGE Network, which was initiated and funded by the NHGRI through the following grants: U01HG008657 (Kaiser Permanente Washington/University of Washington); U01HG008685 (Brigham and Women{\textquoteright}s Hospital); U01HG008672 (Vanderbilt University Medical Center); U01HG008666 (Cincinnati Children{\textquoteright}s Hospital Medical Center); U01HG006379 (Mayo Clinic); U01HG008679 (Geisinger Clinic); U01HG008680 (Columbia University Health Sciences); U01HG008684 (Children{\textquoteright}s Hospital of Philadelphia); U01HG008673 (Northwestern University); U01HG008701 (Vanderbilt University Medical Center serving as the Coordinating Center); U01HG008676 (Partners Healthcare/Broad Institute); U01HG008664 (Baylor College of Medicine); and U54MD007593 (Meharry Medical College). Additional work was completed in Phase IV of the eMERGE Network, which was initiated and funded by the NHGRI through the following grants: U01HG011172 (Cincinnati Children{\textquoteright}s Hospital Medical Center); U01HG011175 (Children{\textquoteright}s Hospital of Philadelphia); U01HG008680 (Columbia University); U01HG008685 (Mass General Brigham); U01HG006379 (Mayo Clinic); U01HG011169 (Northwestern University); U01HG008657 (University of Washington); U01HG011181 (Vanderbilt University Medical Center); U01HG011166 (Vanderbilt University Medical Center serving as the Coordinating Center). Publisher Copyright: {\textcopyright} 2022, The Author(s).",
year = "2022",
month = dec,
doi = "10.1186/s12911-022-01759-z",
language = "English (US)",
volume = "22",
journal = "BMC Medical Informatics and Decision Making",
issn = "1472-6947",
publisher = "BioMed Central",
number = "1",
}