Assigment .Apa seven . All instructions attached.

profilebutterflyl
  • 19 days ago
  • 35
files (2)

LeadershipinQI-Week2Outline.docx

2

Leadership in Quality Improvement: IT Projects to Improve Daily Weight Compliance in Heart Failure Patients

Vianka Concepcion

Florida National University

Nursing Leadership and Management

Dr. Nora Hernandez-Pupo

September 12, 2026

1

Leadership in Quality Improvement: IT Projects to Improve Daily Weight Compliance in Heart Failure Patients

Scenario & Project Instructions

My unit of practice is Heart Failure/Cardiac Step-Down, and I am the new nurse manager and my goal is to improve adherence to daily weight checks among our HF population, which is one of the earliest, lowest cost markers of fluid overload and/or impending decompensation (De Lathauwer et al., 2025). This outline aims to tackle issues uncovered by a root cause analysis of current compliance gaps, including inconsistent technology adoption and low data literacy among staff, with three IT projects, as well as a discussion of appropriate approaches to data and AI and a plan for the implementation and sustainability of the team.

IT Projects (3 Total)

IT Project 1: Remote Patient Monitoring (RPM) Platform for Daily Weights. A scalable system that automatically syncs patient weight info to the EHR, mitigating manual recording and enhancing timely clinical notifications for problematic weight patterns (De Lathauwer et al., 2025)..

IT Project 2: Automated EHR Weight-Compliance Dashboard. In real-time, a dashboard would alert nursing staff to missing any daily weights by showing the number of nursing observations that did not result in a recorded weight (the same automation and large-scale data feedback that supports nursing-led quality improvement efforts, as described in Goodfellow & Bird, 2022).

IT Project 3: Patient-Facing Mobile Reminder Application. Reminding and logging tool to improve adherence for patients becoming discharged, basically bringing RPM monitoring into the transition from hospital to home, and has been found to lower hospitalization and death risk (De Lathauwer et al., 2025).

Data Analysis & AI

There are two general types of machine learning techniques. In supervised learning, models are trained on labeled data, such as a historical dataset of patients that were compliant with treatment and those that were not to predict an outcome such as the risk of a patient being readmitted (An et al., 2023). Unsupervised learning is a method used to identify patterns in unlabeled data, which may not be known beforehand and can be applied to cluster patients into groups based on risk factors (An et al., 2023). Both methods involve the use of interdisciplinary teams and significant resources as a reliable model requires well-structured, clean data, clinical knowledge of the domain to interpret the results, and statistical knowledge to validate its performance (An et al., 2023).

Health Data Literacy

Nurse leaders are expected to demonstrate high levels of health data literacy, as they influence the effectiveness that frontline staff are able to achieve when implementing digital systems; managers with greater informatics skills have been associated with increased digital health system documentation and increased documentation consistency (Hariyati et al., 2024). Even the best systems can be designed to be adopted without this literacy (Hariyati et al., 2024).

Data Sources & Data Types

This project will utilize clinical data from the EHR, RPM reading from devices and nursing documentation/audit logs. The ability to use automated data analytics for quality improvement is increasingly being seen as the primary method as it enables a larger sample size, and provides quick and easy feedback for staff, which are not possible through manual chart audits (Goodfellow & Bird, 2022). This requires key resources such as time to train staff, data visualization tools, and support with integration of EHRs (Goodfellow & Bird, 2022).

Project Team Members

Frontline nursing staff: Primary users of the RPM and dashboard tools, nursing staff on the front lines: provide ongoing feedback on workflow fit.

Data analyst (ETL): Extracts, transforms and loads weight and compliance data from EHR and RPM platform for reporting and analysis (Goodfellow & Bird, 2022).

Statistician: constructs and tests predictive models, e.g., supervised classification in the risk of re-hospitalization, and assesses the significance of the outcome data (An et al., 2023).

Nurse informaticist/IT liaison: creates a bridge between the clinical workflow demands and technical requirements and to support the development of digital literacy skills among staff (Hariyati et al., 2024).

Unit nurse manager (project lead): coordinates the team and is aligned with the priorities of the clinical team within the unit.

Follow-Up & Sustainability

Follow-up will be incorporated in all IT projects from the beginning instead of added on to the end, as the retention of IT projects in healthcare QI is highly correlated with its integration, maintaining competency in the QI method within the team, and ongoing alignment to clinical needs (Lee & Chang, 2026). Future plans involve 3, 6, and 12-month compliance audits, periodic staff retraining related to system changes (Lee & Chang, 2026); and the unit's QI team to review the dashboard on a regular basis.

Conclusion

This Heart Failure/Cardiac step-down unit needs more than one change to improve daily weight compliance. The three recommended IT projects solve the problem from admission to discharge and beyond: Remote patient monitoring, Automated compliance dashboard, Reminder app to patient. They must be coupled with improved health data literacy amongst staff, strategic deployment of machine learning and a team that includes front-line nurses, a data analyst and a statistician alongside nursing leadership. This initiative is best placed to achieve long-lasting and impactful patient outcomes if it is approachable from the outset and takes a holistic and integrated approach to building follow-up and sustainability planning.

References

An, Q., Rahman, S., Zhou, J., & Kang, J. J. (2023). A comprehensive review on machine learning in healthcare industry: Classification, restrictions, opportunities and challenges. Sensors, 23(9), Article 4178. https://doi.org/10.3390/s23094178

De Lathauwer, I. L. J., Nieuwenhuys, W. W., Hafkamp, F., Regis, M., Brouwers, R. W. M., Funk, M., & Kemps, H. M. C. (2025). Remote patient monitoring in heart failure: A comprehensive meta-analysis of effective programme components for hospitalization and mortality reduction. European Journal of Heart Failure, 27(9), 1670–1685. https://doi.org/10.1002/ejhf.3568

Goodfellow, D., & Bird, J. (2022). Using data analytics to enhance quality improvement projects. Nursing Management, 29(4), 32–40. https://doi.org/10.7748/nm.2022.e2042

Hariyati, R. T. S., Handiyani, H., Wildani, A. A., Afriani, T., Nuraini, T., & Amiruddin, M. H. (2024). Disparate digital literacy levels of nursing manager and staff, specifically in nursing informatics competencies and their causes: A cross-sectional study. Journal of Healthcare Leadership, 16, 415–425. https://doi.org/10.2147/JHL.S470456

Lee, J.-Y., & Chang, J.-T. (2026). Predicting the sustainability of quality improvement initiatives in healthcare: A data-driven study. The Joint Commission Journal on Quality and Patient Safety, 52(8), 358–364. https://doi.org/10.1016/j.jcjq.2026.04.006