Gokulvarthan-Ramesh/aionboarding
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: implement voice-based patient onboarding pipeline with AI orchestration, multi-language STT/TTS support, and clinical state extraction.

Browse Source
This commit is contained in:
Gokulvarthan-Ramesh
2026-08-29 15:09:31 +05:30
parent 5e500dcfbc
commit dc2799a95b
14 changed files with 733 additions and 191 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ai-patient-onboarding/app/services/medical_speech_normalizer.py
+5
View File
@@ -54,6 +54,11 @@ def normalize_medical_speech(transcript: str, language_code: str = "en-IN") -> s
for pattern, replacement in PHONETIC_REPLACEMENTS.items():
cleaned = re.sub(pattern, replacement, cleaned, flags=re.IGNORECASE)
# HIPAA & DPDP Act 2023 PII/SPI Redaction: Scrub sensitive non-medical national IDs & card numbers
cleaned = re.sub(r"\b\d{4}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}\b", "[REDACTED_FINANCIAL_CARD]", cleaned)
cleaned = re.sub(r"\b\d{4}[-\s]?\d{4}[-\s]?\d{4}\b", "[REDACTED_NATIONAL_ID]", cleaned)
cleaned = re.sub(r"\b\d{3}[-\s]?\d{2}[-\s]?\d{4}\b", "[REDACTED_SSN]", cleaned)
# Standardize spaces and punctuation
cleaned = re.sub(r"\s+([.,!?])", r"\1", cleaned)
cleaned = re.sub(r"\s+", " ", cleaned).strip()