Create a data analysis proposal examining hospital readmissions and healthcare outcomes. Construct a capstone project on healthcare data analysis methods.
Capstone Proposal: Reducing Hospital Readmissions through Data Analysis
Problem Statement
High 30-day hospital readmission rates may result in increased healthcare costs, penalties under value-based programs, and reduced patient outcomes (Medicare Payment Advisory Commission, 2021).
Review of the Literature
Ahn, E., Choi, J., & Kim, S. (2021). Predictive analytics for hospital readmissions. Healthcare Informatics Research, 27(3), 198-207. https://doi.org/10.4258/hir.2021.27.3.198
Shows how predictive modeling using electronic health records can identify high-risk patients before discharge.
Berwick, D., Nolan, T., & Whittington, J. (2020). The triple aim: Care, health, and cost. Health Affairs, 39(5), 758-764. https://doi.org/10.1377/hlthaff.2020.00110
Explains why reducing readmissions directly supports the triple aim framework of improving population health, lowering costs, and enhancing care.
Figueroa, J., et al. (2020). Association of Medicare Hospital Readmissions Reduction Program with readmission and mortality outcomes. JAMA Network Open, 3(2), e1920472. https://doi.org/10.1001/jamanetworkopen.2019.20472
Evaluates how financial penalties have driven hospitals to adopt systematic interventions.
Gupta, A., & Krumholz, H. (2021). Hospital performance on readmission measures. BMJ Quality & Safety, 30(6), 463-471. https://doi.org/10.1136/bmjqs-2020-011540
Assesses variation in hospital performance and highlights factors that explain persistent disparities.
Kansagara, D., et al. (2020). Risk prediction models for hospital readmission. Annals of Internal Medicine, 172(1), 39-46. https://doi.org/10.7326/M19-3009
Reviews models and identifies best predictors such as comorbidity, prior utilization, and social determinants.
McIlvennan, C., et al. (2021). Transitional care interventions to reduce readmissions. Circulation: Cardiovascular Quality and Outcomes, 14(4), e007746. https://doi.org/10.1161/CIRCOUTCOMES.120.007746
Presents evidence that structured discharge planning and follow-up improve outcomes.
Medicare Payment Advisory Commission. (2021). Report to the Congress: Medicare and the Health Care Delivery System. https://www.medpac.gov
Official policy document showing the cost and penalty impact of excess readmissions.
Rajkomar, A., et al. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347-1358. https://doi.org/10.1056/NEJMra1814259
Explains applications of machine learning in predicting patient risk and improving clinical decisions.
Rau, J. (2020). Hospitals struggle to curb readmissions. Health Affairs Blog. https://doi.org/10.1377/hblog20200220.293599
Provides real-world examples of challenges hospitals face in meeting federal targets.
Suter, W., et al. (2022). Data-driven leadership in healthcare organizations. Journal of Healthcare Leadership, 14, 11-20. https://doi.org/10.2147/JHL.S344321
Explains how leaders use performance dashboards and analytics to guide decision-making.
Wadhera, R., et al. (2020). Evaluation of the Hospital Readmissions Reduction Program. Annals of Internal Medicine, 172(3), 177-185. https://doi.org/10.7326/M19-1631
Finds readmission penalties have reduced rates but may also increase mortality in some patient groups.
Zhang, Z., et al. (2023). Social determinants of health and hospital readmissions. BMC Health Services Research, 23(1), 119. https://doi.org/10.1186/s12913-023-09001-8
Highlights how housing instability, poverty, and food insecurity raise risk of readmission.
Causal Factors and Metrics
| Factor | Causal/Contributing | Unit of Measurement | Source |
|---|---|---|---|
| Poor discharge planning | Causal | % of discharges without follow-up scheduled | McIlvennan et al., 2021 |
| Comorbid conditions | Causal | Average Charlson Comorbidity Index score | Kansagara et al., 2020 |
| Socioeconomic barriers | Contributing | % of patients from zip codes below federal poverty line | Zhang et al., 2023 |
| Medication adherence | Contributing | % of patients filling prescriptions within 7 days | Ahn et al., 2021 |
| Hospital resource allocation | Causal | $ spent on transitional care per patient | Suter et al., 2022 |
Data Analysis Method
Method: Benchmark variance analysis of hospital readmission rates against national targets.
Rationale: Readmission penalties are calculated by variance from expected benchmarks. Measuring differences between local data and federal standards shows the gap and highlights areas for improvement.
Source: Figueroa et al. (2020).
Data Sets
Path 2: Public Data Sets
Factor #1 Examined: 30-day readmission rate for heart failure patients.
-
Unit: % readmitted within 30 days.
-
Graphic: Bar graph comparing hospital vs national average.
-
Source: Centers for Medicare & Medicaid Services (CMS), Hospital Compare Data, 2023.
Factor #2 Examined: Socioeconomic status of discharged patients.
-
Unit: % of patients in lowest income quintile.
-
Graphic: Pie chart showing income distribution.
-
Source: Agency for Healthcare Research and Quality (AHRQ), HCUP Data, 2023.
Factor #3 Examined: Medication adherence among recently discharged patients.
-
Unit: % of prescriptions filled within 7 days of discharge.
-
Graphic: Histogram showing adherence levels.
-
Source: Medicare Part D Prescription Claims, 2022.
Healthcare Professional Reviewer (Placeholder)
-
Name: To be filled.
-
Organization: To be filled.
-
Date of Review: To be scheduled.
Conclusion
Hospitals face strong financial and clinical pressure to lower readmission rates. Evidence shows that poor discharge planning, comorbid conditions, socioeconomic barriers, and limited transitional care resources increase the risk. Data analysis using benchmark variance against CMS standards provides a clear, measurable way to identify gaps. By combining public datasets with proven predictive models, hospitals can target high-risk patients and design interventions such as structured discharge plans, follow-up appointments, and medication support. The findings emphasize that reducing readmissions is not only about meeting policy benchmarks but also about improving patient care quality and equity.
References
-
Ahn, E., Choi, J., & Kim, S. (2021). Predictive analytics for hospital readmissions. Healthcare Informatics Research, 27(3), 198-207. https://doi.org/10.4258/hir.2021.27.3.198
-
Berwick, D., Nolan, T., & Whittington, J. (2020). The triple aim: Care, health, and cost. Health Affairs, 39(5), 758-764. https://doi.org/10.1377/hlthaff.2020.00110
-
Figueroa, J., et al. (2020). Association of Medicare Hospital Readmissions Reduction Program with readmission and mortality outcomes. JAMA Network Open, 3(2), e1920472. https://doi.org/10.1001/jamanetworkopen.2019.20472
-
Gupta, A., & Krumholz, H. (2021). Hospital performance on readmission measures. BMJ Quality & Safety, 30(6), 463-471. https://doi.org/10.1136/bmjqs-2020-011540
-
Kansagara, D., et al. (2020). Risk prediction models for hospital readmission. Annals of Internal Medicine, 172(1), 39-46. https://doi.org/10.7326/M19-3009
-
McIlvennan, C., et al. (2021). Transitional care interventions to reduce readmissions. Circulation: Cardiovascular Quality and Outcomes, 14(4), e007746. https://doi.org/10.1161/CIRCOUTCOMES.120.007746
-
Medicare Payment Advisory Commission. (2021). Report to the Congress: Medicare and the Health Care Delivery System. https://www.medpac.gov
-
Rajkomar, A., et al. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347-1358. https://doi.org/10.1056/NEJMra1814259
-
Rau, J. (2020). Hospitals struggle to curb readmissions. Health Affairs Blog. https://doi.org/10.1377/hblog20200220.293599
-
Suter, W., et al. (2022). Data-driven leadership in healthcare organizations. Journal of Healthcare Leadership, 14, 11-20. https://doi.org/10.2147/JHL.S344321
-
Wadhera, R., et al. (2020). Evaluation of the Hospital Readmissions Reduction Program. Annals of Internal Medicine, 172(3), 177-185. https://doi.org/10.7326/M19-1631
-
Zhang, Z., et al. (2023). Social determinants of health and hospital readmissions. BMC Health Services Research, 23(1), 119. https://doi.org/10.1186/s12913-023-09001-8
MHA-FPX5020: Capstone Data Analysis Proposal Assignment
Assessment 2
Capstone Data Analysis Proposal
Instructions: Use the provided template to create a draft proposal for your data analysis project and have a healthcare professional review your document and provide feedback.
Introduction
Writing a project proposal is an essential skill for leaders. Presenting a proposal to senior executives requires that you identify the problem, the value to the organization from solving the problem, the relevant aspects of the problem, and your recommendations for action. Your recommendations should be conveyed in a concise but thorough manner, retaining the essential information needed by the decision makers.
This assessment provides an opportunity to draft a proposal for your capstone data analysis project and to present the proposal to a healthcare professional.
Note: Each assessment of your capstone project is built on the work you have completed in previous assessments. Therefore, you must complete the assessments in the order they are presented.
Introduction
For this assessment, you will complete a capstone data analysis proposal in a template with an outline format. This document will include content related to the topic you have chosen for your data analysis in this course. As a part of the assessment, you must have a healthcare professional review your document and provide feedback. The reviewer will sign the document to attest that they have reviewed it.
Instructions
Use the Capstone Data Analysis Proposal Template Download Capstone Data Analysis Proposal Templateto complete this assessment.
For the assessment:
- State the topic in the form of a problem by using the following format:
- Condition X may result in adverse consequence(s) Y (Source, year).
- Conduct a review of authoritative literature related to the topic you chose and select a minimum of 12 current, authoritative sources which directly relate to your selected topic.
- Using APA format, list a minimum of twelve authoritative sources directly related to your stated problem and add a sentence or two about how each source relates to the problem.
- Make a bullet point list of the factors that cause the problem.
- Assign a precise unit of numeric measurement to each factor (percentage, dollars, days, et cetera).
- Identify the method of data analysis you plan to conduct (e.g., compliance audit, benchmark variance analysis, cost benefit analysis, et cetera).
- Provide a precise description of the data sets you are analyzing.
- For Path 1, list the precise data sets from your workplace organization that you will be using.
- Important: For any use of private organizational data, you must obtain written permission to use that data and you must submit that written permission with your assessment.
- For Path 2, list any public data sets you will be using.
- Include a reference list of the sources you identified in APA format at the end of the document.
- Submit your content as a draft to Turnitin for source verification.
- In the Turnitin report, review all highlighted areas and make any needed corrections.
- Have your selected reviewer examine the completed document and provide feedback and sign it to attest to the fact that they have reviewed the document and provided feedback on it.
- For Path 1, the reviewer will be a healthcare professional from your workplace.
- For Path 2, the reviewer will be a healthcare professional you have identified, who has expertise to evaluate your data analysis proposal.
- Submit your completed Capstone Data Analysis Proposal document and any signed permission documents in the Assessment area.
Additional Requirements
- Document Format: Use the provided Capstone Data Analysis Proposal Template Download Capstone Data Analysis Proposal Templateto create your data analysis proposal.
- Document Length: Respond to all prompts in the template.
- Supporting Evidence: Include at least 12 academic or scholarly sources that match in-text citations.
- Supporting evidence may include current accrediting body standards, industry standards, and government agency reports, including such sources as the AHA, National Academy of Medicine, Harvard Business Review (HBR), et cetera.
- APA Formatting: Format in-text citations and references according to current APA style and formatting. Evidence and APAcan help with this.
- Submission Requirements: Submit your Capstone Data Analysis Proposaldocument and any signed permission documents in the Assessment area.
Competencies Measured
By successfully completing this assessment, you will demonstrate your proficiency in the following course competencies and scoring guide criteria:
- Competency 1: Execution: Translate strategy to develop and maintain optimal organizational performance in health care settings.
- Provide a precise description of data sets being analyzed.
- Convey purpose, in an appropriate tone and style, incorporating supporting evidence and adhering to organizational, professional, and scholarly writing standards.
- Competency 4: Change Leadership: Apply evidence based change leadership practices in complex, dynamic healthcare environments.
- State the topic for a data analysis in the form of a problem in a specified format.
- Conduct a review of current, relevant authoritative literature related to a topic for a data analysis and cite at least 12 authoritative sources in APA format that are related to a stated problem and explain how each relates to the problem.
- Articulate the major factors that contribute to a selected problem as stated in a problem statement and assign precise units of measurement to each factor.
- Competency 5: Team Development: Develop high performing teams by inspiring individual excellence and leading talent development in healthcare organizations.
- Identify the method to be used for a data analysis and obtain feedback on the method and data analysis proposal from a healthcare professional.
