This Power BI Report provides an end-to-end analysis of Heart Disease Patients to help hospital management identify critical health patterns and improve patient outcomes. The dashboard visualizes patient distribution by gender, age, and health metrics, providing valuable insights into heart disease risk factors and overall trends.
- Analyze the demographics of heart disease patients by gender and age.
- Identify patterns in cholesterol levels, blood pressure, and heart rate.
- Evaluate survival outcomes based on key medical indicators.
- Support hospital decision-making for better treatment planning.
- Enhance data-driven health management through actionable visuals.
- Higher occurrence rate observed in middle-aged male patients (40–60 years).
- Elevated cholesterol and resting BP are major contributing factors.
- Lower survival rate in patients with low ejection fraction.
- Females show fewer heart disease cases, but higher survival probability.
- Key risk indicators include serum creatinine and age.
- Lifestyle-based prevention can significantly reduce hospitalization rates.
| Aspect | Details |
|---|---|
| Tools Used | Power BI, Microsoft Excel |
| Visual Types | Line Chart, Ribbon Chart, Clustered Column Chart, KPI Cards, Donut Chart |
| Data Source | UCI Heart Failure Clinical Records Dataset |
| Purpose | To analyze heart disease patterns and support hospital growth & treatment insights |
| File | Heart Disease Report.pbix (can be downloaded for interactive exploration) |
- Data Cleaning & Transformation using Power Query
- Data Modeling (relationships between demographic and medical data)
- DAX Measures for KPIs and survival calculations
- Dynamic Visualizations with slicers and interactive charts
- KPI Dashboard Design for executive-level reporting
- Business Intelligence Storytelling for medical insights
- Total Patients Analyzed
- Male vs Female Patient Ratio
- Average Cholesterol & Blood Pressure Levels
- Survival Rate by Gender
- Average Ejection Fraction & Serum Creatinine Levels
This dashboard empowers healthcare professionals and analysts to:
- Identify high-risk patient segments.
- Monitor vital clinical metrics.
- Improve resource allocation and preventive strategies.
- Use data-driven insights for better patient outcomes.
Dataset Credit: Heart Failure Clinical Records – UCI Machine Learning Repository
Authors: Davide Chicco and Giuseppe Jurman
Source: https://archive.ics.uci.edu/dataset/519/heart+failure+clinical+records
License: Creative Commons Attribution 4.0 International (CC BY 4.0) – https://creativecommons.org/licenses/by/4.0/
Citation: Chicco, D., & Jurman, G. (2020). Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Medical Informatics and Decision Making, 20(1), 1-16.
🎨 Image Credit: Image by Freepik – https://www.freepik.com/free-psd/3d-rendering-realistic-heart_344840361.htm
🎨 Icon Credit: Icon by Flaticon -
Author: Sudowoodo
📌 https://www.flaticon.com/free-icon/person_13482183
📌 https://www.flaticon.com/free-icon/avatar_13482193
Created by: Paramesh Mandapaka
📧 mandapakaparamesh9@gmail.com
⭐ If you find this project helpful, give it a star on GitHub!