Medical Scribe Dictation

Source: https://github.com/aipoch/medical-research-skills

Medical Scribe Dictation

Convert unstructured physician dictation into professionally formatted SOAP (Subjective, Objective, Assessment, Plan) notes with medical terminology normalization and clinical quality assurance.

When to Use

• Use this skill when the task is to Convert physician verbal dictation into structured SOAP notes. Trigger.
• Use this skill for academic writing tasks that require explicit assumptions, bounded scope, and a reproducible output format.
• Use this skill when you need a documented fallback path for missing inputs, execution errors, or partial evidence.

Key Features

See ## Features above for related details.

• Scope-focused workflow aligned to: Convert physician verbal dictation into structured SOAP notes. Trigger.
• Packaged executable path(s): scripts/main.py.
• Reference material available in references/ for task-specific guidance.
• Structured execution path designed to keep outputs consistent and reviewable.

Dependencies

• openai or anthropic - LLM for structure extraction
• spacy + scispacy - Medical NLP processing
• faster-whisper (optional) - Local STT
• pydantic - Data validation

Example Usage

See ## Usage above for related details.

cd "20260318/scientific-skills/Academic Writing/medical-scribe-dictation"
python -m py_compile scripts/main.py
python scripts/main.py --help

Example run plan:

1. Confirm the user input, output path, and any required config values.
2. Edit the in-file CONFIG block or documented parameters if the script uses fixed settings.
3. Run python scripts/main.py with the validated inputs.
4. Review the generated output and return the final artifact with any assumptions called out.

Implementation Details

See ## Workflow above for related details.

• Execution model: validate the request, choose the packaged workflow, and produce a bounded deliverable.
• Input controls: confirm the source files, scope limits, output format, and acceptance criteria before running any script.
• Primary implementation surface: scripts/main.py.
• Reference guidance: references/ contains supporting rules, prompts, or checklists.
• Parameters to clarify first: input path, output path, scope filters, thresholds, and any domain-specific constraints.
• Output discipline: keep results reproducible, identify assumptions explicitly, and avoid undocumented side effects.

Quick Check

Use this command to verify that the packaged script entry point can be parsed before deeper execution.

python -m py_compile scripts/main.py

Audit-Ready Commands

Use these concrete commands for validation. They are intentionally self-contained and avoid placeholder paths.

python -m py_compile scripts/main.py
python scripts/main.py --help
python scripts/main.py -h
python scripts/main.py --help

Workflow

1. Confirm the user objective, required inputs, and non-negotiable constraints before doing detailed work.
2. Validate that the request matches the documented scope and stop early if the task would require unsupported assumptions.
3. Use the packaged script path or the documented reasoning path with only the inputs that are actually available.
4. Return a structured result that separates assumptions, deliverables, risks, and unresolved items.
5. If execution fails or inputs are incomplete, switch to the fallback path and state exactly what blocked full completion.

Features

• Speech-to-Text Processing: Transcribe audio or process pre-transcribed text
• SOAP Structure Generation: Auto-organize clinical content into standard sections
• Medical Terminology Handling: Normalize abbreviations, expand acronyms, verify drug names
• Clinical Quality Checks: Flag missing required elements, suggest clarifications
• Multi-Specialty Support: Adaptable templates for internal medicine, surgery, pediatrics, etc.

Usage

Processing Pre-Transcribed Text

python scripts/main.py --input "patient presents with..." --output-format soap

Processing Audio File (requires whisper/faster-whisper)

python scripts/main.py --audio consultation.wav --output note.md

Python API

from scripts.main import MedicalScribe

scribe = MedicalScribe(specialty="internal_medicine")
soap_note = scribe.process_dictation(transcription_text)
print(soap_note.to_markdown())

Parameters

SOAP Output Structure

# Clinical Note - [Date]

## Subjective
Chief Complaint:
History of Present Illness:
Review of Systems:
Past Medical History:
Medications:
Allergies:
Social History:
Family History:

## Objective
Vital Signs:
Physical Examination:
Diagnostic Studies:

## Assessment
Primary Diagnosis:
Differential Diagnoses:
Clinical Reasoning:

## Plan
Diagnostic:
Therapeutic:
Patient Education:
Follow-up:

Technical Architecture

Components

1. Transcription Module (optional): Whisper-based STT with medical vocabulary fine-tuning
2. Segmentation Engine: NLP-based section identification and content classification
3. Terminology Processor: Medical NER (Named Entity Recognition) and normalization
4. SOAP Assembler: Structured output generation with specialty-specific formatting
5. Quality Validator: Completeness checks and clinical red-flag detection

Technical Difficulty

High - Requires medical domain expertise, complex NLP pipelines, and clinical validation.

Known Limitations

• Medical terminology accuracy depends on speech clarity
• Ambiguous dictation may require human clarification
• Drug name verification recommended before finalizing
• Does not replace physician review for critical cases

References

See references/ for:

• soap-templates.md - Specialty-specific SOAP templates
• medical-abbreviations.json - Common abbreviation mappings
• terminology-sources.md - Medical ontology references (SNOMED CT, ICD-10)
• example-cases.md - Sample dictations with expected outputs