View source for A framework for evaluating the appropriateness of clinical decision support alerts and responses

This is a review of McCoy, Waitman, Lewis, Wright, Choma, Miller and Peterson’s 2012 article, A framework for evaluating the appropriateness of clinical decision support alerts and responses.<ref name="McCoy et al 2012"> McCoy, A. B., Waitman, L. R., Lewis, J. B., Wright, J. A., Choma, D. P., Miller, R. A., & Peterson, J. F. (2012). A framework for evaluating the appropriateness of clinical decision support alerts and responses. Journal of the American Medical Informatics Association : JAMIA, 19(3), 346–352. doi:10.1136/amiajnl-2011-000185 </ref>

== Introduction ==

With healthcare transitioning into the 21st century, more and more hospitals and clinics are making the switch from paper-based records to Electronic Medical Records ([[EMR]]). Included in the EMRs are Computerized Provider Order Entries ([[CPOE]]) and Clinical Decision Support ([[CDS]]). These two features are aimed to specifically improve patient safety. Clinical Decision Support is a process for enhancing health-related decisions and actions with pertinent, organized clinical knowledge and patient information to improve health and healthcare delivery.<ref name="Clinical Decision Support"> http://www.himss.org/library/clinical-decision-support</ref>

The authors present a comprehensive framework for evaluating the clinical appropriateness of synchronous, interruptive medication safety [[alerts]].<ref name="McCoy et al 2012"></ref>

== Methods ==

Through literature review and iterative testing, metrics were developed that describe successes, justifiable overrides, provider non-adherence, and unintended adverse consequences of clinical decision support [[alerts]].<ref name="McCoy et al 2012"></ref>

The framework was validated by applying it to a medication alerting system for patients with acute kidney injury ([https://www.kidney.org/atoz/content/AcuteKidneyInjury AKI]).<ref name="McCoy et al 2012"></ref> The site location for this validation was at Vanderbilt University Hospital. The author’s evaluated the AKI alerts by comparing it to their framework retrospectively. 

== Results ==

A total of 487 alerts were evaluated by the reviewers. After a group consensus was made, the authors decided to select 391 alerts as appropriate to display. 
A fascinating result obtained was that providers initially overrode 400 (82%) of the alerts, while 82 (17%) out of the 487 were labeled as inappropriate alert responses. 

Contributing factors to alert display inappropriateness included:<ref name="McCoy et al 2012"></ref>
* No AKI actually present because of laboratory error
* Medications or conditions interfering with creatinine assays
* Insufficient change in glomerular filtration rate for 54% of inappropriate alerts

Additional contributing factors to alert display inappropriateness included:<ref name="McCoy et al 2012"></ref>
* The pre-alert medication dose was acceptable because of a previous adjustment
* Drug doses not subject to adjustment because of short-duration prophylaxis
* Presence of clinician monitoring of therapeutic drug levels for 33% of inappropriate alerts.

== Discussion ==

The proposed framework of the authors shows the effectiveness of implementing clinical alerts. A key attribute of the framework is that it determines appropriateness by capturing relevant clinical context information at the time of a triggered alert and by applying expert knowledge. The framework determines appropriateness of alerts and responses independently. 

According to the authors, it is anticipated that the framework, once verified and evolved for other settings, can serve as a means to evaluate, post facto, underperforming existing systems. It can also serve to evaluate a CDS system in preparation for a comparative trial that measures its patient-level clinical impact.<ref name="McCoy et al 2012"></ref>

== Conclusion ==

High rates of alert overrides and low rates of alert adherence can hinder the success of otherwise well-designed CDS alerting systems. The authors developed and tested a framework that utilizes expert review for evaluating the clinical appropriateness of CDS alerts and providers’ responses to the alerts that extends previous work by others. <ref name="McCoy et al 2012"></ref>

== Comments ==

With greater advancement in healthcare technology, the use of the CDS tool will bring added value to patient safety. The results obtained in this article showed the alert override rate (Provider non-adherence + Justifiable overrides)/(Total alerts) was equal to 33%. This means that one third of all alerts were overridden by the providers and leaves much room for improvement in the alert system.  

Related article review:
* [[Clinical decision support alert appropriateness: A review and proposal for improvement]]

== References==
<references/>

[[Category:CDS]]
[[Category:Reviews]]