Analysis updated 2026-07-04 · repo last pushed 2026-06-16
Build an interactive dashboard to visualize healthcare outcomes for kidney disease patients.
Run SQL queries to identify which patient groups are most at risk of poor outcomes.
Analyze how facility type and insurance status affect diagnosis speed and survival.
Create a portfolio project showing end-to-end data cleaning, analysis, and reporting.
Requires MySQL for database queries and Power BI for viewing the interactive dashboard.
This project is a data analysis portfolio piece that explores what factors influence outcomes for patients with Chronic Kidney Disease (CKD). Using a synthetic dataset of 100,000 patient records spread across five countries (Nigeria, India, Brazil, Kenya, and the United States), it aims to answer practical healthcare questions: what drives patient recovery versus death, how insurance and income affect results, and why some facilities take much longer to diagnose the disease than others. The work is split into two main stages, using two popular data tools. First, MySQL (a database system) is used to clean the raw data, fix formatting issues, and create new categories like age groups or income brackets. Then, over forty database queries are run to find the answers to the core business questions, looking for patterns in mortality rates, diagnosis delays, and treatment adherence. Finally, the results are connected to Power BI, a business intelligence tool, to create an interactive dashboard with six different pages of visual reports. A healthcare administrator or policy researcher would use this project to understand where the healthcare system is failing CKD patients. For example, the analysis found that smaller, primary-level healthcare facilities take nearly twice as long to diagnose the disease compared to larger tertiary hospitals, leading to higher mortality rates. It also revealed that the United States had the longest average diagnosis delay at 35 days and the lowest early detection rate, while uninsured patients struggled with lower drug availability across the board. Because the dataset is synthetic, the insights are meant to demonstrate the author's data analysis and dashboarding skills rather than guide real-world medical decisions. The project is notably well-structured, taking the reader through the entire data pipeline from messy data and database queries to a finished, interactive dashboard with actionable recommendations like investing in smaller facilities and launching targeted early screening programs.
A data analysis project using SQL and Power BI to explore Chronic Kidney Disease patient outcomes across five countries, identifying diagnosis delays, mortality drivers, and insurance-related disparities.
Active — commit in last 30 days (last push 2026-06-16).
No license information is provided in the repository, so usage rights are unclear.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly data.
This repo across BitVibe Labs
Verify against the repo before relying on details.