Introduce the concept of a capstone project in health informatics, its purpose, scope, and objectives. Discuss the significance of capstone projects in integrating theoretical knowledge with practical applications in the field.
Overview of Health Informatics Capstone Project
Purpose: Provide a concise, organized reference for students and faculty preparing, executing, and evaluating a health‑informatics capstone.
| Aspect | Description |
|---|---|
| Definition | A culminating, project‑based experience that integrates knowledge from coursework, clinical practice, and informatics theory. |
| Goal | Demonstrate the ability to identify a real‑world health‑IT problem, apply informatics methods, and deliver a viable solution or evidence‑based recommendation. |
| Typical Formats | • Software prototype or dashboard • Data‑analytics report (e.g., predictive modeling) • Workflow redesign with process‑mapping • Policy or standards assessment • Implementation plan for a health‑IT system |
| Stakeholders | Students, faculty advisors, clinical partners, IT vendors, IRB (if human data are used), and potential end‑users (clinicians, patients, administrators). |
| Phase | Key Activities | Deliverables |
|---|---|---|
| 1. Initiation | • Choose a problem domain (clinical, public health, administration). • Conduct a brief literature scan. • Secure a sponsor or clinical partner. |
• Project charter (problem statement, objectives, scope). |
| 2. Planning | • Define research questions / functional requirements. • Create a work breakdown structure (WBS). • Develop a timeline (Gantt chart) and risk log. • Obtain IRB/ethical approval if needed. |
• Detailed project plan, data‑use agreement, ethics approval letter. |
| 3. Data Acquisition & Management | • Identify data sources (EHR, claims, registries, sensors, surveys). • Assess data quality, completeness, and privacy constraints. • Perform de‑identification / HIPAA compliance steps. • Store data in a secure, documented repository. |
• Data dictionary, data‑access log, secure storage configuration. |
| 4. Analysis & Development | • Choose appropriate informatics methods (e.g., NLP, machine learning, clinical decision support rules, process mining). • Build prototypes, dashboards, or analytical models. • Conduct iterative testing with mock data or sandbox environments. |
• Code repository, model documentation, prototype screenshots, test‑case results. |
| 5. Evaluation | • Define evaluation metrics (accuracy, sensitivity, usability, workflow impact, cost‑benefit). • Perform validation (cross‑validation, user‑testing, pilot rollout). • Collect qualitative feedback from end‑users. |
• Evaluation report, statistical results, usability survey data. |
| 6. Dissemination | • Prepare final written report (APA/AMA style). • Create a slide deck for oral defense. • Optionally submit a manuscript to a peer‑reviewed journal or conference. |
• Capstone thesis, presentation deck, optional manuscript. |
| 7. Closure | • Archive code, data, and documentation per institutional policy. • Conduct a lessons‑learned session with the project team. |
• Project archive, lessons‑learned summary. |
| Competency | Example Evidence |
|---|---|
| Clinical Knowledge | Understanding of the clinical workflow being improved. |
| Data Literacy | Ability to extract, clean, and transform health data sets. |
| ** |