Many healthcare providers are adopting clinical decision support (CDS) systems to improve patient safety and meet Meaningful Use requirements. Computerized alerts that prompt clinicians about drug- allergy, drug-drug, and drug-disease warnings or provide dosing guidance are most commonly implemented. Alert overrides can hinder improved patient outcomes, and detailed evaluation of the appropriateness of alerts and clinician responses is necessary;however, traditional methods require manual chart reviews, which are labor intensive and difficult to replicate for all alerts across institutions. This proposal focuses on developing nove methods for evaluating and improving CDS alerts that build upon traditional informatics approaches.
Aim 1 begins by applying previously described models for predicting alert overrides then improves these models by adding covariates based on measures not previously assessed within biomedical informatics.
Aim 2 expands the use of web-based monitoring tools, developing an interactive dashboard for evaluating CDS alert and response appropriateness that incorporates the models developed in Aim 1. It is hypothesized that these methods will allow informatics personnel to identify and improve poorly performing alerts, thus reducing alert fatigue and increasing patient safety.
Effectively evaluating the appropriateness of clinical decision support alerts and responses is critical to improving patient safety through health information technology. This proposal will develop novel, semi- automated methods to facilitate such evaluations in both ambulatory and community hospital settings with commercial electronic health records.
|McCoy, Allison B; Wright, Adam; Sittig, Dean F (2015) Cross-vendor evaluation of key user-defined clinical decision support capabilities: a scenario-based assessment of certified electronic health records with guidelines for future development. J Am Med Inform Assoc 22:1081-8|
|McCoy, A B; Wright, A; Krousel-Wood, M et al. (2015) Validation of a Crowdsourcing Methodology for Developing a Knowledge Base of Related Problem-Medication Pairs. Appl Clin Inform 6:334-44|
|McCoy, Allison B; Wright, Adam; Rogith, Deevakar et al. (2014) Development of a clinician reputation metric to identify appropriate problem-medication pairs in a crowdsourced knowledge base. J Biomed Inform 48:66-72|
|McCoy, Allison B; Thomas, Eric J; Krousel-Wood, Marie et al. (2014) Clinical decision support alert appropriateness: a review and proposal for improvement. Ochsner J 14:195-202|