Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Accuracy of Electronic Health Record Derived Maternal and Perinatal Condition Codes in an Integrated Health Care Delivery System: Development and Validation Study
ABSTRACT
Background:
Medical and obstetrical conditions during pregnancy can present serious risks to both the mother and the developing fetus. An accurate electronic health record (EHR) registry database of maternal and fetal conditions is necessary to understand these conditions and find causative factors.
Objective:
To evaluate the accuracy of maternal and fetal diagnoses and procedural codes in the EHR database compared to manual chart reviews.
Methods:
A random sample of 800 charts was selected from eligible records from January 1, 2021, through June 30, 2021. Perinatal outcome data were extracted from Kaiser Permanente Southern California (KPSC) EHRs. A team of trained research associates conducted manual chart review of the same perinatal outcomes, and the abstracted codes were compared with corresponding EHR records. Accuracy differences were then evaluated through sensitivity, specificity, and weighted positive and negative predictive value.
Results:
The accuracy of chart reviews and codes varied by condition. Conditions such as placenta previa, cesarean delivery, chronic hypertension, and gestational diabetes demonstrated high sensitivity (>95%), while others, including chorioamnionitis and gestational fever, showed lower sensitivity, 22% and 27%, respectively. Specificity, weighted PPV, and weighted NPV were acceptable (>85%) for most conditions.
Conclusions:
The accuracy of EHR coding for maternal and perinatal conditions is variable depending on the condition, with high reliability for certain diagnoses but notable deficiencies for others. These findings highlight the need for targeted efforts to improve coding or diagnostic accuracy, particularly for conditions with low sensitivity, to support more reliable data for clinical decision-making, quality improvement initiatives, and research.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.