Icd10 Cpt Coding Assistant
by @aipoch-ai
Automatically recommend ICD-10 diagnosis codes and CPT procedure codes from clinical notes. Trigger when: user provides clinical notes, patient encounter sum...
clawhub install icd10-cpt-coding-assistantπ About This Skill
name: icd10-cpt-coding-assistant description: 'Automatically recommend ICD-10 diagnosis codes and CPT procedure codes from clinical notes. Trigger when: user provides clinical notes, patient encounter summaries, discharge summaries, or asks for medical coding assistance. Use for healthcare providers, medical coders, and billing professionals who need accurate code recommendations.' version: 1.0.0 category: Clinical tags: [] author: AIPOCH license: MIT status: Draft risk_level: Medium skill_type: Tool/Script owner: AIPOCH reviewer: '' last_updated: '2026-02-06'
ICD-10 & CPT Coding Assistant
A medical coding assistant that parses clinical notes and recommends appropriate ICD-10 diagnosis codes and CPT procedure codes with confidence scoring.
Overview
This skill analyzes clinical documentation to extract relevant medical information and map it to standardized coding systems:
Technical Difficulty: HIGH β οΈ
> β οΈ HUMAN REVIEW REQUIRED: Medical coding directly impacts billing, reimbursement, and clinical documentation. All recommendations must be verified by a certified medical coder or healthcare provider.
Usage
python scripts/main.py --input "clinical_note.txt" [--format json|text]
Or use programmatically:
from scripts.main import CodingAssistantassistant = CodingAssistant()
result = assistant.analyze("Patient presents with acute bronchitis...")
print(result.icd10_codes)
print(result.cpt_codes)
Parameters
| Parameter | Type | Default | Required | Description |
|-----------|------|---------|----------|-------------|
| --input, -i | string | - | Yes | Path to clinical note file |
| --format, -f | string | json | No | Output format (json, text) |
| --output, -o | string | stdout | No | Output file path |
| --confidence-threshold | float | 0.7 | No | Minimum confidence score (0.0-1.0) |
| --include-alternatives | flag | false | No | Include alternative code suggestions |
Input Format
Accepts clinical notes in various formats:
Output Format
ICD-10 Recommendations
{
"icd10_codes": [
{
"code": "J20.9",
"description": "Acute bronchitis, unspecified",
"confidence": 0.92,
"evidence": ["cough for 5 days", "wheezing on exam"],
"alternatives": ["J20.0", "J44.9"]
}
]
}
CPT Recommendations
{
"cpt_codes": [
{
"code": "99213",
"description": "Office visit, established patient, moderate complexity",
"confidence": 0.85,
"evidence": ["detailed history", "low complexity decision making"],
"time": "20 minutes"
}
]
}
Confidence Scoring
Limitations
1. No Medical Advice: This tool does not provide clinical advice or diagnoses 2. Coding Complexity: Cannot handle all coding nuances (comorbidities, sequencing, modifiers) 3. Regional Variations: May not account for payer-specific coding requirements 4. Updates: Code sets may not reflect the latest annual updates
References
See references/ folder for:
icd10_common_codes.json: Frequently used ICD-10 codes by specialtycpt_common_codes.json: Frequently used CPT codes by specialtycoding_guidelines.md: General coding guidelines and conventionsSafety & Compliance
Dependencies
requirements.txt for package dependenciesRisk 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
Prerequisites
# Python dependencies
pip install -r requirements.txt
Evaluation Criteria
Success Metrics
Test Cases
1. Basic Functionality: Standard input β Expected output 2. Edge Case: Invalid input β Graceful error handling 3. Performance: Large dataset β Acceptable processing timeLifecycle Status
π‘ Examples
python scripts/main.py --input "clinical_note.txt" [--format json|text]
Or use programmatically:
from scripts.main import CodingAssistantassistant = CodingAssistant()
result = assistant.analyze("Patient presents with acute bronchitis...")
print(result.icd10_codes)
print(result.cpt_codes)
βοΈ Configuration
# Python dependencies
pip install -r requirements.txt