@Article{info:doi/10.2196/58130,
author="Penev, Yordan P
and Buchanan, Timothy R
and Ruppert, Matthew M
and Liu, Michelle
and Shekouhi, Ramin
and Guan, Ziyuan
and Balch, Jeremy
and Ozrazgat-Baslanti, Tezcan
and Shickel, Benjamin
and Loftus, Tyler J
and Bihorac, Azra",
title="Electronic Health Record Data Quality and Performance Assessments: Scoping Review",
journal="JMIR Med Inform",
year="2024",
month="Nov",
day="6",
volume="12",
pages="e58130",
keywords="electronic health record; EHR; record; data quality; data performance; clinical informatics; performance; data science; synthesis; review methods; review methodology; search; scoping",
abstract="Background: Electronic health records (EHRs) have an enormous potential to advance medical research and practice through easily accessible and interpretable EHR-derived databases. Attainability of this potential is limited by issues with data quality (DQ) and performance assessment. Objective: This review aims to streamline the current best practices on EHR DQ and performance assessments as a replicable standard for researchers in the field. Methods: PubMed was systematically searched for original research articles assessing EHR DQ and performance from inception until May 7, 2023. Results: Our search yielded 26 original research articles. Most articles had 1 or more significant limitations, including incomplete or inconsistent reporting (n=6, 30{\%}), poor replicability (n=5, 25{\%}), and limited generalizability of results (n=5, 25{\%}). Completeness (n=21, 81{\%}), conformance (n=18, 69{\%}), and plausibility (n=16, 62{\%}) were the most cited indicators of DQ, while correctness or accuracy (n=14, 54{\%}) was most cited for data performance, with context-specific supplementation by recency (n=7, 27{\%}), fairness (n=6, 23{\%}), stability (n=4, 15{\%}), and shareability (n=2, 8{\%}) assessments. Artificial intelligence--based techniques, including natural language data extraction, data imputation, and fairness algorithms, were demonstrated to play a rising role in improving both dataset quality and performance. Conclusions: This review highlights the need for incentivizing DQ and performance assessments and their standardization. The results suggest the usefulness of artificial intelligence--based techniques for enhancing DQ and performance to unlock the full potential of EHRs to improve medical research and practice. ",
issn="2291-9694",
doi="10.2196/58130",
url="https://medinform.jmir.org/2024/1/e58130",
url="https://doi.org/10.2196/58130"
}