mugabepatricia/Kenya-Health-System-Analytics-SQL-Tableau-

An end-to-end health data analysis project built on a synthetic but clinically realistic dataset modelled on the Kenyan public health system. # Kenya Health System Analytics Project ## Overview An end-to-end health data analysis project built on a synthetic but clinically realistic dataset modelled on the Kenyan public health system. The project demonstrates proficiency in relational database design, advanced SQL querying, and interactive data visualisation using Tableau. ## Dataset - 4 relational tables: patients, visits, lab_results, prescriptions - 1,200 patients | 1,800 clinical visits | 1,400 lab results | 1,200 prescriptions - Data covers 28 facilities across 15 Kenyan counties (2022–2024) - Diagnoses coded using ICD-10 classification - Realistic clinical variables: vitals, BMI, length of stay, discharge outcomes ## Tools Used - MySQL — database design, querying, and analysis - Tableau Public — interactive dashboard visualisation - Claude AI to create dataset ## SQL Concepts Demonstrated - Complex JOINs across multiple tables - Aggregations with GROUP BY and HAVING - Common Table Expressions (CTEs) - Window functions: RANK(), DENSE_RANK(), ROW_NUMBER(), LAG() - Date functions: DATEDIFF(), DATE_FORMAT() - CASE WHEN statements for clinical classification - Subqueries and flag-then-aggregate pattern - Rolling averages for time series analysis ## Key Analytical Questions Answered - What is the 30-day readmission rate by disease category? - Which disease categories have the highest patient mortality rates? - How does average visit cost vary by insurance type and facility? - Which counties carry the highest infectious disease burden? - Are there patients with critical lab results who were discharged without admission? - What is the monthly trend of malaria, TB, and HIV cases over 2 years? ## Key Insights - Respiratory disease carries the highest patient mortality rate at 5.9%, followed by Perinatal conditions at 4.9% — highlighting neonatal and respiratory care as priority intervention areas - Cardiovascular disease accounts for the highest number of deaths (7) despite a moderate mortality rate, r …