A clinical decision support system (CDSS) is a type of healthcare technology that exists to assist professionals with clinical decision-making. CDSS is evidenced to reduce adverse medication events (AMEs), which is a very important care quality measure (Jia, Zhang, Chen, Zhao, & Zhang, 2016). The present paper will offer a consideration of an initiative that aims to reduce AMEs through the implementation of CDSS. With sufficient planning and an adequate approach to the evaluation of its outcomes, this evidence-based solution to a significant issue encountered by a particular hospital that does not currently employ a CDSS can become a successful quality improvement project.
specifically for you
for only $16.05 $11/page
Problem and Setting Overview
In a particular hospital setting, AMEs remains an acute issue. AMEs are a rather complex phenomenon affected by varied factors, but the general problem is the preventable negative events that are associated with medications (Hedna, Andersson, Gyllensten, Hägg, & Böttiger, 2019; Jia et al., 2016). Among other solutions, CDSS can be employed to improve the quality of care in this regard (Jia et al., 2016), and the described hospital does not use one yet. Therefore, the adoption of a CDSS is proposed as a quality improvement initiative in this paper.
Justification of the Proposed Initiative Using Research Data
A CDSS is expected to have multiple positive effects, and the reduction of preventable AMEs is among them. For example, Hedna et al. (2019) and Niehoff et al. (2016) devoted studies to the topic that involved the testing of a particular CDSS. Hedna et al. (2019) studied the ability of their CDSS to issue alerts about possible problems with patients’ medications (for example, allergic reactions).
The findings showed that the predictive ability of the system was acceptably high for AMEs. Niehoff et al. (2016) tested their CDSS for the capability to pull up the data that demonstrated various AMEs, for instance, inappropriate medications or possible overtreatment of different conditions (diabetes and hypertension). The system was able to generate alerts related to such issues successfully. Thus, different studies of CDSS can explain the mechanisms through which they might reduce AMEs.
Moreover, a recent meta-analysis further supports the idea that CDSS is an effective measure in reducing AMEs. Jia et al. (2016) analyzed twenty high-quality articles, some of which focused on hospital settings, and determined that a CDSS can reduce AMEs. The study also demonstrated that CDSS reducing AMEs is often associated with improvements in the care process. Thus, this meta-analysis suggests that CDSS are a viable solution to the described problem. With this level of evidence, it is reasonable to assume that CDSS is an evidence-based solution that is suited for a quality improvement project.
One of the very comprehensive and regularly updated models of change that have been used in nursing is the Iowa Model (IM) by the Iowa Model Collaborative et al. (2017). This model can guide the change process that is offered in this quality improvement initiative. The first step of IM presupposes determining the problem and its importance; during it, the proposed project should be analyzed to establish its relevance and the hospital’s interest in addressing it. The next step would involve the creation of a team that would carry out the change.
After the solution is found and evaluated, which, for the proposed change, should involve locating a CDSS that fits the needs of the hospital, a plan for its pilot implementation can be drafted by the team. A comprehensive plan, according to Iowa Model Collaborative et al. (2017), should incorporate the consideration of resources and potential barriers to implementation. A recent qualitative study that investigated the topic suggests that the integration of CDSS with electronic health records is necessary for effective work (Koskela, Sandström, Mäkinen, & Liira, 2016).
100% original paper
on any topic
done in as little as
Failure to ensure this type of integration could result in the system issuing false alarms, which might reduce the participants’ trust in it. Other than that, major potential challenges include costs, training, and resistance to change, which are relatively common for technology-related initiatives (Kruse, Kristof, Jones, Mitchell, & Martinez, 2016). These topics need to be reviewed during the planning stage of the change.
On the other hand, as reported by Koskela et al. (2016), facilitators to change can include the ease of use, the value contributed by CDSS (if it is visible), and active cooperation between the multidisciplinary team members who use the system. These data offer suggestions regarding the appropriate use of resources and opportunities, which is another important aspect of planning. Finally, as pointed out by the Iowa Model Collaborative et al. (2017), the plan should involve the consideration of evaluation plans.
They are going to be discussed in detail below, but this element must be included in the plan because the team needs to be able to collect baseline data during the implementation stage. Other activities that are involved in the implementation include the promotion of technology adoption and monitoring of the use of CDSS.
After the pilot implementation, the post-intervention data should be gathered, and the analysis of the implementation effectiveness needs to be performed. IM presupposes repeating any of the steps if necessary, which is why any changes to the specifics of implementation can be made to ensure the most CDSS integration. When the solution is shown to be effective, the piloting is to be followed by maintaining the change and fully integrating it into practice.
Initiative Evaluation: Variables, Hypothesis, and Tests
Given that the project aims to ensure the reduction in AMEs, this factor is the dependent variable for the proposed project, and its measurement is going to be used to evaluate the outcomes. The independent variable would be the CDSS; its introduction will be hypothesized to reduce AMEs, as evidenced by their smaller numbers post-implementation when compared to an equivalent pre-implementation period. The null hypothesis would consist of the idea that the CDSS does not have any impact on the dependent variable and that the pre-and post-intervention evaluations have no statistically significant differences.
To test the hypothesis, a statistical analysis would need to contrast the pre-and post-intervention data. This activity will determine if the null hypothesis can be rejected or not (Polit & Beck, 2017). The type of statistical test will be defined by the data collected, as well as the above-described design. The data gathered for the project would probably be continuous since it reflects AME numbers. Therefore, a statistical test that can be applied to continuous data gathered from the same sample before and after the introduction of the independent variable is required.
As demonstrated by Polit and Beck (2017), the paired t-test is most commonly employed with such conditions. If the difference between the two sets of data is shown to be statistically significant (significance level below or equal to 0.05), the null hypothesis can be rejected, and the project will be determined to be a success.
The proposed quality improvement project is concerned with introducing a technology (CDSS) that is new for the described settings to reduce AMEs. There exists evidence that suggests that CDSS can have such an effect, which makes the intervention evidence-based. The use of IM to structure the change and statistical methods to evaluate its outcomes should ensure the effective testing of the proposed change.
- Hedna, K., Andersson, M., Gyllensten, H., Hägg, S., & Böttiger, Y. (2019). Clinical relevance of alerts from a decision support system, PHARAO, for drug safety assessment in the older adults. BMC Geriatrics, 19(1), 1-8. Web.
- Iowa Model Collaborative, Buckwalter, K. C., Cullen, L., Hanrahan, K., Kleiber, C., McCarthy, A. M.,… Tucker, S. (2017). Iowa Model of evidence-based practice: Revisions and validation. Worldviews on Evidence-Based Nursing, 14(3), 175-182. Web.
- Jia, P., Zhang, L., Chen, J., Zhao, P., & Zhang, M. (2016). The effects of clinical decision support systems on medication safety: An overview. PLOS ONE, 11(12), e0167683. Web.
- Koskela, T., Sandström, S., Mäkinen, J., & Liira, H. (2016). User perspectives on an electronic decision-support tool performing comprehensive medication reviews – a focus group study with physicians and nurses. BMC Medical Informatics and Decision Making, 16(1), 1-9. Web.
- Kruse, C. S., Kristof, C., Jones, B., Mitchell, E., & Martinez, A. (2016). Barriers to electronic health record adoption: A systematic literature review. Journal of Medical Systems, 40(12), 1-7. Web.
- Niehoff, K., Rajeevan, N., Charpentier, P., Miller, P., Goldstein, M., & Fried, T. (2016). Development of the Tool to Reduce Inappropriate Medications (TRIM): A clinical decision support system to improve medication prescribing for older adults. Pharmacotherapy: The Journal of Human Pharmacology and Drug Therapy, 36(6), 694-701. Web.
- Polit, D.F., & Beck, C.T. (2017). Nursing research: Generating and assessing evidence for nursing practice (10th ed.). Philadelphia, PA: Lippincott, Williams & Wilkins.