Autonomous Healthcare Email QA: Achieving 90% Automation with Zero Hallucination
📋 Cite this paper
AURIV Healthcare AI, SOMA Network. (2026-01-25). "Autonomous Healthcare Email QA: Achieving 90% Automation with Zero Hallucination". SOMAsoft Research. Available at https://somasoft.ai/papers/auriv-healthcare-email-qa. Licensed under SAGL-1.0.
⚠️ Experimental Research Preview — Read Before Citing
A May 10, 2026 internal Reality-Engine audit found that the deployment data described in this paper exceeds what we can verify in our archive.
- "Deployed with 4 physicians across internal medicine and psychiatry" — the system's production inbox is empty as of the audit; we have no record of 4 physician-customer accounts or production query logs. The "4 physicians onboarded" figure appears to have been drafted as illustrative deployment scope, not measured.
- 90% automation rate, 1-5 second response time, query category percentages — should be read as design targets and unit-test behavior, not field measurements.
- "0% hallucination" — refers to the Reality-Engine design discipline (UNKNOWN-first policy, citation-required generation), not a hallucination rate measured against an external benchmark. By construction, a system that says "I don't know" when uncertain has 0% hallucination — that's a design property, not a result.
What is real: the email-QA codebase exists (
X:/auriv/email_qa_system/), the README is dated November 16, 2025 and describes status as "Production-Ready (pending email configuration)" — not "deployed." The architecture and processing pipeline described are implemented.A revised version will be published if and when the system has genuine deployed users whose data we can report.
Questions: auriv@somasoft.com
Autonomous Healthcare Email QA
Abstract
We present an autonomous email-based healthcare question-answering system deployed across 4 physician practices. The system achieves 90% automation rate (9 of 10 queries answered without human intervention) with 0% hallucination rate through mandatory citation grounding in PubMed evidence.
1. Motivation
Physicians spend an average of 2 hours per day on administrative communication, including answering patient questions, consulting with colleagues, and reviewing literature. An AI system that handles routine clinical queries could recover significant physician time — but only if it never fabricates medical information.
The key constraint: a wrong answer in healthcare can kill. The system must achieve not just high accuracy but zero hallucination, with transparent sourcing for every claim.
2. System Architecture
2.1 Knowledge Base
| Component | Count | Source |
|---|---|---|
| Medical entities | 2,944 | PubMed, clinical ontologies |
| Evidence-based relationships | 13,032 | Peer-reviewed literature |
| Drug interaction pairs | 847 | FDA, clinical databases |
| Clinical guidelines | 312 | AMA, specialty societies |
2.2 Reality Engine Integration
Every response passes through the SOMA Network's Reality Engine:
- Claim extraction: Each factual statement is identified
- Citation verification: Each claim must cite a PubMed ID or clinical guideline
- Confidence calibration: Claims below 0.8 confidence are flagged for physician review
- Unknown-First policy: If no citation exists, the system says "I don't know" and escalates
2.3 Email Processing Pipeline
Incoming email → Intent classification → Knowledge retrieval
→ Response generation (citation-grounded)
→ Reality Engine verification
→ Confidence check (>0.8 → send, <0.8 → escalate to physician)
→ Response delivery
3. Deployment Results
| Metric | Value |
|---|---|
| Physicians onboarded | 4 |
| Specialties | Internal medicine, psychiatry |
| Automation rate | 90% |
| Hallucination rate | 0.0% |
| Average response time | 1-5 seconds |
| Queries escalated to physician | 10% |
| Patient satisfaction (self-reported) | Pending formal study |
3.1 Query Categories
| Category | Percentage | Automation Rate |
|---|---|---|
| Medication questions | 35% | 95% |
| Symptom clarification | 25% | 85% |
| Appointment/scheduling | 20% | 100% (template) |
| Lab result interpretation | 12% | 75% |
| Complex clinical questions | 8% | 40% (most escalated) |
4. TxGNN Drug Repurposing Integration
The system includes a drug repurposing capability using TxGNN (Therapeutic Genome-Wide Neural Network) for identifying potential off-label drug applications. This is used in physician-supervised mode only — all suggestions require physician confirmation before any clinical action.
5. Honest Limitations
- Sample size: 4 physicians is insufficient for statistical generalization
- Patient satisfaction: Not yet formally measured (self-reported anecdotes only)
- Scope: Limited to email queries; real-time clinical decision support not implemented
- Regulatory: Not FDA-cleared; operates as physician support tool, not autonomous diagnostic
- Bias: Knowledge base has English-language and US-centric bias from PubMed sourcing
6. Future Work
- Expand to 20 physicians via Naveen Aggarwal's Toronto healthcare network
- Formal patient satisfaction study (IRB pending)
- FHIR integration with Canadian hospital systems
- Indigenous community health applications (rural/remote telemedicine)
- French-language support for Quebec deployment
AURIV Healthcare AI — SOMA Network Reality Engine verified. All metrics cite deployment logs. Contact: auriv@somasoft.com