Automated Soap Note Generator — Automated Soap Note 生成器

Automated SOAP Note 生成器 Overview

AI-powered 命令行工具nical documentation 工具 that converts unstructured 命令行工具nical 输入 into professionally 格式化ted SOAP notes compliant with medical documentation standards.

Key Capabilities:

Intelligent Parsing: 提取s structured in格式化ion from free-text 命令行工具nical narratives SOAP Classification: Automatically categorizes content into Subjective, Objective, Assessment, Plan sections Medical Entity Recognition: Identifies symptoms, 诊断s, medications, procedures, and anatomical locations Temporal Analysis: 提取s timeline in格式化ion (on设置, duration, 进度ion) Template Generation: Produces standardized SOAP 格式化 suitable for EHR integration Multi-modal 输入: Accepts text dictation, transcripts, or 命令行工具nical notes When to Use

✅ Use this 技能 when:

Converting physician dictation into structured SOAP 格式化 for efficiency Processing audio-to-text transcripts from patient encounters 转换ing consultation rough notes into formal documentation Generating initial draft documentation to reduce administrative burden Standardizing 命令行工具nical encounter summaries for consistency Creating preliminary notes for routine follow-up visits

❌ Do NOT use when:

输入 contAIns PHI that hasn't been de-identified for 测试/trAIning Complex psychiatric cases requiring nuanced mental 状态 documentation → Use specialized psychiatric documentation 工具s Surgical procedures requiring operative 报告 detAIl → Use operative-报告-生成器 Patient requires nuanced 命令行工具nical reasoning beyond text 提取ion Legal or forensic documentation requiring exact transcription → Use verbatim transcription 服务s Critical care situations requiring real-time precise documentation Cases requiring differential diagnosis prioritization without physician 输入

⚠️ ALWAYS Required:

Physician review and 应用roval before entering into patient record Verification of medical facts and 命令行工具nical accuracy Confirmation of medication names, dosages, and instructions Integration with Other 技能s

Up流 技能s:

medical-scribe-dictation: Convert physician verbal dictation to text 输入 ehr-semantic-压缩or: Summarize lengthy EHR notes for SOAP generation dicom-anonymizer: Prepare imaging 报告s for SOAP inclusion audio-script-writer: Convert audio recordings to text 格式化

Down流 技能s:

medical-emAIl-polisher: Professional communication of SOAP summaries to patients 命令行工具nical-data-清理er: Standardize 提取ed data for re搜索 databases hipaa-合规-审计or: 验证 de-identification before sharing documentation discharge-summary-writer: 生成 discharge summaries from SOAP encounters referral-letter-生成器: 创建 referral letters based on Assessment and Plan sections

Complete 工作流:

Medical Scribe Dictation (audio→text) → Automated SOAP Note 生成器 (this 技能) → Physician Review → EHR Entry / Medical EmAIl Polisher (patient communication) / Referral Letter 生成器 (referrals)

Core Capabilities

• 输入 Processing and Preprocessing

Handle various 输入 格式化s and prepare for NLP analysis:

from scripts.soap_生成器 导入 SOAPNote生成器

生成器 = SOAPNote生成器()

# Process text 输入 soap_note = 生成器.生成( 输入_text="Patient presents with 2-day 历史 of chest pAIn, radiating to left arm...", patient_id="P12345", encounter_date="2026-01-15", 提供者="Dr. Smith" )

# Process from audio transcript soap_note = 生成器.生成_from_transcript( transcript_path="consultation_transcript.txt", patient_id="P12345" )

输入 Preprocessing Steps:

Text 清理ing: 移除 filler words ("um", "uh"), timestamps, speaker labels Sentence Segmentation: Split into 命令行工具nically meaningful segments Normalization: Standardize abbreviations and medical shorthand Encoding 检测ion: Handle various file 格式化s (UTF-8, ASCII, etc.)

Parameters:

Parameter Type Required Description Default 输入_text str Yes Raw 命令行工具nical text or dictation None transcript_path str Yes Path to transcript file None patient_id str No Patient identifier (MUST be de-identified for 测试) None encounter_date str No Date in ISO 8601 格式化 (YYYY-MM-DD) Current date 提供者 str No 健康care 提供者 name None specialty str No Medical specialty 上下文 "general" verbose bool No Include confidence scores False

*Either 输入_text or transcript_path required

Best Practices:

Always 验证 输入 text 质量 (clear audio → better transcription → better SOAP) 移除 patient identifiers before processing unless in 安全 环境 Split long encounters (>30 minutes) into 记录ical segments Flag ambiguous abbreviations for manual review

• Medical Named Entity Recognition (NER)

Identify and 提取 medical concepts from unstructured text:

# 提取 entities with 上下文 entities = 生成器.提取_medical_entities( "Patient has 历史 of hypertension and diabetes, currently taking lisinopril 10mg dAIly and metformin 500mg B