It seems weve done all too many columns on the unintended consequences of healthcare IT. So were happy to highlight this month some success stories for clinical decision support systems (CDS).
Cedars-Sinai Medical Center integrated select recommendations from the Choosing Wisely campaign as CDS alerts into their EHR. This included many alert-based CDS interventions, both inpatient and ambulatory. Providers, when presented with an alert, had the option to cancel, change, or justify the order, They analyzed the impact of these CDS alerts on inpatient encounters (Heekin 2018). The researchers found that encounters in which providers adhered to all alerts had significantly lower total costs, shorter lengths of stay, a lower probability of 30-day readmissions, and a lower probability of complications compared with nonadherent encounters. Full adherence to Choosing Wisely alerts was associated with savings of $944 from a median encounter cost of $12,940.
Another recent study (Wachsberg 2018) demonstrated that an educational intervention, combined with real-time clinical decision support (CDS), reduced blood utilization among hospitalized solid tumor cancer patients without adversely affecting outcomes. The odds of receiving a transfusion were cut by almost half in the postintervention cohort. There were no significant differences in readmission, outpatient transfusion within seven days of discharge, or inpatient mortality. Patients in the postintervention cohort also had lower odds of ICU transfer (OR = 0.29).
And another study in a large academic medical center () showed a mixed impact of nonintrusive clinical decision support systems on laboratory test utilization, reminding us to focus on areas where a positive impact is seen and avoid unnecessary alerts that dont change outcomes. The study focused on CDS for red blood cell folate, hepatitis C virus viral loads and genotypes, and (blood) type and screens. Appropriate indications for these labs were incorporated into text that accompanied the laboratory orders in the hospital's EHR. There was a 43% decrease in the rate of hepatitis C virus tests per monthly admissions after the CDS was implemented. But there was no significant change in type and screen orders or folate orders. The authors stress that nonintrusive CDS should be evaluated for individual laboratory tests to ensure only effective alerts continue to be used so as to avoid increasing EHR fatigue.
The last point is very important. Avoiding alert fatigue is critical in any clinical decision support program. We stress to hospitals that they need to have an interdisciplinary group that works with their IT staff to evaluate the impact of every new CDS rule implemented. That means looking to see what the adherence/override rate is for each alert and whether the alert results in the desired change in ordering.
These three studies, however, clearly show that careful planning, implementation, and evaluation of clinical decision support tools can be beneficial to patient care and can be done in a manner that is nonintrusive.
See some of our other Patient Safety Tip of the Week columns dealing with unintended consequences of technology and other healthcare IT issues:
Heekin AM, Kontor J, Sax HC, et al. Choosing Wisely Clinical Decision Support Adherence and Associated Inpatient Outcomes. Am J Manag Care 2018; 24(8): 361-366
Wachsberg KN, O'Leary KJ, Buck R, et al. Impact of Real-Time Clinical Decision Support on Blood Utilization and Outcomes in Hospitalized Patients with Solid Tumor Cancer. The Joint Commission Journal on Quality and Patient Safety 2018; Published online: August 17, 2018
Eaton KP, Chida N, Apfel A, et al. Impact of nonintrusive clinical decision support systems on laboratory test utilization in a large academic centre. Journal of Evaluation in Clinical Practice 2018; 24(3): 474-479 First Published: 15 February 2018