Health Data Analysis in Pakistan

Overview

This project analyzes a comprehensive health dataset from various hospitals across Pakistan. The dataset includes detailed information on patient visits, including personal and medical data. The analysis aims to provide insights into patient demographics, disease prevalence, treatment costs, and hospital performance.

Objectives

1. Patient Demographics

   • Analyze the distribution of age, gender, height, and weight across different hospitals.

2. Disease Prevalence

   • Identify the most common conditions treated and their distribution across various cities and provinces.

3. Treatment Costs

   • Understand the financial burden on patients by comparing those with and without insurance.

4. Hospital Performance

   • Compare hospitals based on patient volume and treatment costs.
   • Identify peak times for admissions and discharges.

5. Insurance Impact

   • Examine the impact of insurance coverage on healthcare expenses.

6. Blood Group Distribution

   • Study the distribution of blood groups and gain geographical insights.

Dataset

The dataset represents detailed information on patient visits, including:

• Personal data (age, gender, height, weight)
• Medical data (diagnoses, treatments, costs)
• Geographical data (cities, provinces)
• Insurance information

Methodology

• Exploratory Data Analysis (EDA) to understand the dataset.
• Use of pivot tables in Excel to summarize and analyze the data.
• Visualization of key insights and trends.

Key Insights and Findings

For key insights and findings, refer to the project report pdf.

Acknowledgements

• Thanks to atomcamp for the dataset and the excellent learning experience.