Comprehensive Family Medicine Medical Records Dataset

**Key Highlights**

- Total Character Count: 735,110 (in sample dataset)
- Specialties Covered: Comprehensive coverage of family medicine physician documentation and transcripts, including progress notes, history and physicals, and outpatient follow-up notes.
- Geographical Coverage: Data collected from family medicine physicians across multiple US states, representing a diverse range of care settings and patient populations.

**Privacy:** All documents are de-identified according to Safe Harbor Guidelines and HIPAA compliance, ensuring the protection of patient information

<p><br/></p>

**General Overview**

This dataset offers a wide range of family medicine-specific medical records, providing high-quality documentation that supports healthcare AI model development and enhances patient care in primary care and family practice. The dataset includes the following document types:

- **Progress** (1,061 documents, 569,712 characters)
- **History and Physical** (158 documents, 134,796 characters)
- **Outpatient Follow-up Note** (26 documents, 14,467 characters)
- **Consultation** (13 documents, 11,911 characters)
- **Other (Specify type)** (5 documents, 1,882 characters)
- **Other (Specify type) / Under Report Type** (2 documents, 493 characters)
- **Operative** (2 documents, 749 characters)
- **Discharge Planning** (2 documents, 1,446 characters)
- **Nursing** (1 document, 654 characters)

Each document type is categorized with detailed information, providing a comprehensive view of family medicine medical records for machine learning and clinical use.