Abstract
Current approaches to understanding medication ordering errors rely on relatively small manually captured error samples. These approaches are resource-intensive, do not scale for computerized provider order entry (CPOE) systems, and are likely to miss important risk factors associated with medication ordering errors. Previously, we described a dataset of CPOE-based medication voiding accompanied by univariable and multivariable regression analyses. However, these traditional techniques require expert guidance and may perform poorly compared to newer approaches. In this paper, we update that analysis using machine learning (ML) models to predict erroneous medication orders and identify its contributing factors. We retrieved patient demographics (race/ethnicity, sex, age), clinician characteristics, type of medication order (inpatient, prescription, home medication by history), and order content. We compared logistic regression, random forest, boosted decision trees, and artificial neural network models. Model performance was evaluated using area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC). The dataset included 5,804,192 medication orders, of which 28,695 (0.5%) were voided. ML correctly classified voids at reasonable accuracy; with a positive predictive value of 10%, ~20% of errors were included. Gradient boosted decision trees achieved the highest AUROC (0.7968) and AUPRC (0.0647) among all models. Logistic regression had the poorest performance. Models identified predictive factors with high face validity (e.g., student orders), and a decision tree revealed interacting contexts with high rates of errors not identified by previous regression models. Prediction models using order-entry information offers promise for error surveillance, patient safety improvements, and targeted clinical review. The improved performance of models with complex interactions points to the importance of contextual medication ordering information for understanding contributors to medication errors.
Highlights
Computerized provider order entry (CPOE) systems streamline medication ordering process by creating standardized templates for the entry of legible, accurate, and complete medication orders, thereby mitigating the potential for medication errors [1,2,3,4,5,6]
We propose the use of machine learning (ML) approaches for characterizing the risk factors associated with medication ordering errors
We found that gradient boosted decision tree (GBDT) was the top performing model (AUROC = 0.797) and was able to predict errors with a 10% PPV at a sensitivity of 20%
Summary
Computerized provider order entry (CPOE) systems streamline medication ordering process by creating standardized templates for the entry of legible, accurate, and complete medication orders, thereby mitigating the potential for medication errors [1,2,3,4,5,6]. Clinician interactions with CPOE systems are a source of medication errors [14,15,16,17]; errors during CPOE use account for 6–25% of detected medication errors in hospitalized patients [15]. One of the larger analysis of CPOE-based errors used manual reviews to categorize over 10,000 reported errors drawn from a national database [20], classifying the causes of such errors. Such analyses are useful in understanding the sources of CPOE-based medication errors, these databases include limited details regarding the context of a reported error with considerable variability regarding the content of reported errors. Because of the lack of matched control (non-error) orders, they cannot be used for developing prediction models
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
