Date of Award
Doctor of Nursing Practice (DNP)
Practice Problem: Heart disease stands as the leading cause of mortality in the United States. While healthcare providers strive to identify and optimize prevention strategies, particularly in high-risk patient populations, notable gaps in care persist, notably in the management of modifiable risk factors such as low-density lipoprotein cholesterol (LDL). By harnessing the power of artificial intelligence (AI) integrated software within clinical settings, we can revolutionize the landscape of this devastating chronic disease.
PICOT: The PICOT question that guided this project was: In Primary Care Advanced Practice Providers (APP) caring for high-risk and/or very high-risk patients with atherosclerotic cardiovascular disease (ASCVD) (P), how do automated electronic alerts with guideline-based recommendations (I) compare to standard notification practice (C) affect referral initiation to cardiology or prompt medication change (O) within 10 weeks (T)?
Evidence: In the realm of modern healthcare, it is crucial to recognize the impact of AI on Electronic Health Records (EHRs). This fusion of data analysis and health information technology provides an opportunity for healthcare treatments to become much more effective, resulting in better patient outcomes. Fifteen studies that matched the inclusion criteria were collected and used as substantiating evidence for this project.
Intervention: AI software integrated into the EHR system computed comprehensive data analytics, consequently discovering a substantial cohort of patients with an elevated risk profile for ASCVD, accompanied by an LDL-C level that exceeded established clinical guidelines. Subsequently, an automated communication was sent to the APP, furnishing them with pertinent notifications and offering referral recommendations.
Outcome: By integrating AI processes into the EHR, data management is streamlined and real-time disease prevention analysis is achieved. The primary goal was to identify high-risk ASCVD patient groups using AI within the EHR and assess the effectiveness of AI-generated electronic alerts with clinical guidance in encouraging behavior change. The clinical significance of this data collection and implementation was substantial. While the statistical analysis produced relevant metrics, it also exhibited applicability in the clinical context. The data exposed a patient population lacking aggressive medical management or referrals, a concern noted by APPs.
Conclusion: Introducing AI-based tools can direct the pathway of care and bridge crucial gaps in care in high-risk populations. The result of this technology utilization and integration offers timely screening strategies, education, clinical decision support, and opportunities to address vital pathways for providers and health systems to address ASCVD treatment gaps.
Wooten, E. (2023). Clinical Practice Implementation to Address ASCVD Risk: A Practice Change in Primary Care. [Doctoral project, University of St Augustine for Health Sciences]. SOAR @ USA: Student Scholarly Projects Collection. https://doi.org/10.46409/sr.CGNG4490
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.