Protocol Assistant

Answers clinicians’ questions from the hospital’s own protocols and formulary, with citations.

Industry	Level	Difficulty	Recommended mode
Healthcare	1 of 5	Beginner	flat

Coming soon

A complete, runnable Protocol Assistant reference implementation is in progress. The architecture and core code below already work with SrvDB 0.3.

The problem

• Clinicians hunt through intranet PDFs for the current protocol.
• Local formulary rules differ from general references.
• Clinical text cannot be sent to external AI services.

How SrvDB powers Protocol Assistant

1. Protocols, formulary entries and local policies are split into passages, embedded and stored in SrvDB on hospital servers.
2. Each question is one search; a local LLM answers only from the retrieved passages and quotes them.
3. Protocol updates replace old passages with upsert; withdrawn documents are removed with delete.
4. persist() keeps the index consistent through restarts.

What changes

Today	With Protocol Assistant on SrvDB
Searching PDFs on the intranet	A plain-language question returns the exact protocol passage
Out-of-date copies circulate	Updates replace old passages the same day
External AI is not permitted	Everything runs on hospital infrastructure

How it works

1. Collect approved protocols, formulary and policies.
2. Chunk and embed with a local model.
3. Store with document, version and section as metadata.
4. Answer questions with citations via a local LLM.
5. Re-ingest on every document release.

SrvDB features it uses

• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.
• delete and compact(): remove items immediately from search, then reclaim disk space.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.
• Fully offline: SrvDB runs in-process and never opens a network connection.

Use cases

• Dosing guidance from the local formulary
• Sepsis or stroke pathway steps
• Infection-control rules
• Pre-operative checklists
• Ward-specific procedures
• Escalation and on-call policies

Core code

embed() is your embedding model (for example sentence-transformers, or a function that turns your records into feature vectors).

import json
import srvdb

db = srvdb.Database("./protocol-assistant-db", dimension=384)

def ingest(items):
    """items: list of (id, text, metadata dict)"""
    db.upsert(
        ids=[i for i, _, _ in items],
        embeddings=[embed(t) for _, t, _ in items],
        metadatas=[json.dumps(m) for _, _, m in items],
    )
    db.persist()                      # crash-safe checkpoint

def find_protocol(question, k=5):
    hits = db.search(embed(question), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• Decision support only; clinicians remain responsible.
• Only approved, current documents should be ingested.

Caution

SrvDB keeps data local, but it is not a certified medical device or a compliance product. Regulatory compliance (HIPAA, GDPR and similar) remains the deployer’s responsibility.

Build roadmap

1. Prototype: load a sample of real data with flat mode and check that searches return what an expert expects.
2. Measure: if you move to an approximate mode, compare its results with flat on the same queries (recall).
3. Pipeline: add continuous upsert and decide when to call persist().
4. Harden: test restarts and crashes, add logging, review every output path with domain experts.
5. Deploy: ship the database directory with the application or service.

All Healthcare projects

Level	Project	What it does
1 · Beginner	Protocol Assistant (this page)	Answers clinicians’ questions from the hospital’s own protocols and formulary, with citations.
2 · Intermediate	Similar Case Finder	Finds de-identified past cases that resemble the patient in front of you.
3 · Advanced	Trial Matcher	Shortlists patients for clinical trials by comparing summaries with eligibility criteria.
4 · Expert	Pharmacovigilance Monitor	Matches new adverse-event reports to known safety signals and groups similar reports.
5 · Frontier	On-prem Clinical AI Stack	A complete hospital AI stack with zero data egress: local embeddings, local LLM, SrvDB.

See also: Use cases · Live examples (coming soon)