README.md

# Healthcare Patient Dataset

<!--
Author: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
-->

Medical patient dataset with health records, diagnostic information, and treatment outcomes for healthcare analytics and predictive modeling.

## 📋 Description

This dataset includes patient demographics, medical history, diagnostic tests, treatment plans, and outcomes. Perfect for healthcare analytics, disease prediction, and medical research applications.

### Key Features

- ✅ Patient demographics
- ✅ Medical history
- ✅ Diagnostic tests
- ✅ Treatment outcomes
- ✅ HIPAA compliant format

## 🛠️ Technologies

- **CSV** - Data storage format
- **Excel** - Spreadsheet format
- **Pandas** - Data manipulation and analysis
- **NumPy** - Numerical computing
- **Python** - Programming language
- **Matplotlib & Seaborn** - Data visualization

## 📊 Dataset Information

- **Total Records**: 30 patients
- **Features**: 26 columns
- **Difficulty Level**: Advanced
- **Category**: Tabular Data

### Dataset Columns

1. `patient_id` - Unique patient identifier
2. `first_name` - Patient first name
3. `last_name` - Patient last name
4. `age` - Patient age
5. `gender` - Patient gender
6. `blood_type` - Blood type
7. `admission_date` - Date of admission
8. `discharge_date` - Date of discharge
9. `diagnosis` - Primary diagnosis
10. `diagnosis_code` - ICD-10 diagnosis code
11. `primary_condition` - Primary medical condition
12. `comorbidities` - Additional conditions
13. `medication_1`, `medication_2`, `medication_3` - Prescribed medications
14. `lab_test_1`, `lab_test_1_result` - Laboratory test 1 and result
15. `lab_test_2`, `lab_test_2_result` - Laboratory test 2 and result
16. `lab_test_3`, `lab_test_3_result` - Laboratory test 3 and result
17. `treatment_type` - Type of treatment received
18. `length_of_stay` - Hospital stay duration in days
19. `readmission_30_days` - 30-day readmission status
20. `outcome` - Treatment outcome (Recovered/Improved/Stable)
21. `insurance_type` - Insurance provider type
22. `charges` - Total medical charges

## 🚀 Getting Started

### Prerequisites

- Python 3.8 or higher
- pip (Python package installer)

### Installation

1. Clone or download this repository

2. Install required dependencies:
```bash
pip install -r requirements.txt
```

### Usage

#### 1. Analyze the Dataset

Run the main analysis script:
```bash
python analyze_patients.py
```

This will:
- Load and analyze the dataset
- Generate statistical summaries
- Create visualizations in the `visualizations/` directory
- Export a comprehensive analysis report

#### 2. Export to Excel

Convert the CSV dataset to Excel format:
```bash
python export_to_excel.py
```

This creates an Excel file with multiple sheets:
- Patient Data
- Summary Statistics
- Diagnosis Summary
- Treatment Summary
- Demographics
- Outcome Analysis

#### 3. View Demo Page

Open `index.html` in a web browser to view an interactive demo of the dataset.

## 📈 Analysis Features

The analysis script provides:

- **Basic Statistics**: Age, gender, length of stay, charges statistics
- **Diagnosis Analysis**: Top diagnoses, primary conditions, comorbidities
- **Treatment Analysis**: Treatment types, outcomes by treatment, costs
- **Demographic Analysis**: Age groups, gender-based outcomes
- **Financial Analysis**: Charges by insurance, diagnosis, cost per day
- **Visualizations**: Multiple charts and graphs

## 📁 Project Structure

```
healthcare-patients/
│
├── healthcare_patients.csv # Main dataset file
├── analyze_patients.py # Analysis script
├── export_to_excel.py # Excel export script
├── index.html # Interactive demo page
├── requirements.txt # Python dependencies
├── README.md # This file
│
└── visualizations/ # Generated charts (created after running analysis)
├── age_distribution.png
├── gender_distribution.png
├── top_diagnoses.png
├── length_of_stay.png
├── charges_distribution.png
├── outcome_distribution.png
├── treatment_charges.png
└── age_vs_charges.png
```

## 📊 Sample Analysis Results

After running the analysis, you'll get insights such as:

- Average patient age and demographics
- Most common diagnoses
- Treatment effectiveness
- Length of stay patterns
- Financial analysis
- Readmission rates

## 🔒 Privacy & Compliance

This dataset is created in a HIPAA-compliant format with:
- De-identified patient information
- Synthetic data for demonstration purposes
- No real patient records

## 📝 License

This dataset and code are provided for educational and research purposes.

## 👤 Author

**RSK World**

- Website: [https://rskworld.in](https://rskworld.in)
- Email: help@rskworld.in
- Phone: +91 93305 39277

## 🤝 Contributing

Contributions, issues, and feature requests are welcome!

## 📄 Acknowledgments

- Dataset created for healthcare analytics and research
- Suitable for machine learning and predictive modeling projects
- Ideal for data science education and training

---

**Note**: This is a synthetic dataset created for educational purposes. It does not contain real patient data.