Medication Administration & Near-Miss Safety Data
Analyse medication-safety patterns without exposing patient or clinician information.
What you can build
- Medication-safety and incident dashboards
- Near-miss and error classification experiments
- Shift, staffing and experience risk analysis
- SQL, Python, Power BI and Tableau training
- Clinical-software and data-pipeline QA
Designed analytical signals
The generator models relationships between shift type, staffing pressure, experience, medication risk and incident likelihood. Night shifts, higher patient-to-nurse ratios, lower experience and high-risk medication classes produce higher modelled near-miss or error rates.
Schema preview
| Field | Meaning |
|---|---|
| shift_type | AM, PM or night shift |
| staffing_ratio_patients_per_nurse | Operational staffing pressure |
| high_risk_medication | High-risk medicine indicator |
| event_type | Administration outcome, near miss or error |
| severity | Modelled incident severity |
| contributing_factor | Associated operational factor |
Files supplied
Complete CSV, data dictionary, README, licence, methodology and limitations, summary statistics, SQL practice queries, Python analysis notebook, offline dashboard and case study in the supported package.
Responsible-use statement
Every patient, clinician and facility is fictional. The dataset contains no personal or health information from real people and is not clinically validated. It is intended for research, education, analytics, AI/ML development and software testing.