📖 Description
This is a health analytics project from the LinkedIn Learning "Healthcare SQL" course with Thais Cooke. Included is an index of queries used and sample output for the data set provided in the course.
📈 Project Scenario
Role: Healthcare Data Analyst working with EHR data including multiple tables. Hospital Leadership wants to understand the changing patient population served. They asked the following questions:
- What's the distribution of patients in the healthcare system?
- Which diagnoses are most prevalent among patients, and how do they vary across the different demographic groups, including gender and age?
- What are the most common appointment times throughout the day, and how does the distribution of appointment times vary across different hours?
- What are the most commonly ordered lab tests?
- Typically, fasting blood sugar levels fall between 70–100 mg/dL. Please identify patients whose lab results are outside this normal range to implement early interventions.
- To prevent cardiovascular disease and they need, please assess how many patients are considered High, Medium, and Low Risk?
- To assess readmission risk, can you please identify finding out information about the patients who had multiple visits within 30 days of their previous medical visit?
🧠 Objectives
- Analyze healthcare data by grouping patients by demographics, diagnoses, appointment trends, lab tests, and cardiovascular risk levels using functions like CASE, COUNT, DATEDIFF, DATEPART, JOIN, GROUP BY, and ORDER BY.
- Connect multiple healthcare tables, identify abnormal fasting blood sugar results, classify patient risk categories, and summarize healthcare utilization patterns for better planning and patient care.
- For the readmissions scenario, use a self-join on the outpatient visits table and DATEDIFF to identify patients who returned within 30 days, helping hospitals monitor repeat visits and improve care outcomes.
🛠 Tools & Technologies
- Microsoft SQL Server