Discharge Summary Writer
Generate standardized, clinically accurate hospital discharge summaries by integrating all inpatient medical data.
When to Use
- Patient discharge preparation requires comprehensive summary documentation
- Compiling admission, treatment, and discharge data into unified records
- Generating follow-up instructions and medication lists for post-discharge care
- Creating legally compliant discharge documentation for medical records
Input Requirements
Required Patient Data
{
"patient_info": {
"name": "string",
"gender": "string",
"age": "number",
"medical_record_number": "string",
"admission_date": "YYYY-MM-DD",
"discharge_date": "YYYY-MM-DD",
"department": "string",
"attending_physician": "string"
},
"admission_data": {
"chief_complaint": "string",
"present_illness_history": "string",
"past_medical_history": "string",
"physical_examination": "string",
"admission_diagnosis": ["string"]
},
"hospital_course": {
"treatment_summary": "string",
"procedures_performed": ["string"],
"significant_findings": "string",
"complications": ["string"],
"consultations": ["string"]
},
"discharge_status": {
"discharge_diagnosis": ["string"],
"discharge_condition": "string",
"hospital_stay_days": "number"
},
"medications": {
"discharge_medications": [
{
"name": "string",
"dosage": "string",
"frequency": "string",
"route": "string",
"duration": "string"
}
]
},
"follow_up": {
"instructions": "string",
"follow_up_appointments": ["string"],
"warning_signs": ["string"],
"activity_restrictions": "string",
"diet_instructions": "string"
}
}
Usage
Python Script
python scripts/main.py --input patient_data.json --output discharge_summary.md --format standard
Parameters
| Parameter | Type | Default | Required | Description |
|---|---|---|---|---|
--input |
string | - | Yes | Path to JSON file containing patient data |
--output |
string | discharge_summary.md | No | Output file path |
--format |
string | standard | No | Output format (standard, structured, json) |
--template |
string | - | No | Custom template file path |
--language |
string | zh | No | Output language (zh or en) |
Output Formats
Standard Format
Human-readable markdown document following clinical discharge summary structure:
- Patient Information
- Admission Information
- Hospital Course
- Discharge Status
- Discharge Medications
- Follow-up Instructions
- Physician Signature
Structured Format
Sectioned markdown with clear headers for EMR integration.
JSON Format
Machine-readable structured data for system integration.
Technical Difficulty
⚠️ HIGH - Manual Review Required
This skill handles critical medical documentation. Output requires:
- Physician verification before use
- Compliance with local medical documentation standards
- Review for accuracy and completeness
- Institutional approval for template formats
Safety Considerations
- Never use generated summaries without physician review
- Verify all medication dosages and instructions
- Confirm follow-up appointments with hospital scheduling system
- Ensure discharge diagnoses match official medical records
- Validate patient identifiers and dates
References
references/discharge_template.md- Standard discharge summary templatereferences/medical_terms.json- Standardized medical terminologyreferences/section_guidelines.md- Guidelines for each section
Limitations
- Does not access live EMR systems (requires manual data input)
- Medication interactions not validated
- Does not generate ICD-10 codes automatically
- Requires structured input data
- Output format must align with institutional requirements
Risk Assessment
| Risk Indicator | Assessment | Level |
|---|---|---|
| Code Execution | Python/R scripts executed locally | Medium |
| Network Access | No external API calls | Low |
| File System Access | Read input files, write output files | Medium |
| Instruction Tampering | Standard prompt guidelines | Low |
| Data Exposure | Output files saved to workspace | Low |
Security Checklist
- No hardcoded credentials or API keys
- No unauthorized file system access (../)
- Output does not expose sensitive information
- Prompt injection protections in place
- Input file paths validated (no ../ traversal)
- Output directory restricted to workspace
- Script execution in sandboxed environment
- Error messages sanitized (no stack traces exposed)
- Dependencies audited
Prerequisites
No additional Python packages required.
Evaluation Criteria
Success Metrics
- Successfully executes main functionality
- Output meets quality standards
- Handles edge cases gracefully
- Performance is acceptable
Test Cases
- Basic Functionality: Standard input → Expected output
- Edge Case: Invalid input → Graceful error handling
- Performance: Large dataset → Acceptable processing time
Lifecycle Status
- Current Stage: Draft
- Next Review Date: 2026-03-06
- Known Issues: None
- Planned Improvements:
- Performance optimization
- Additional feature support