Pharmacovigilance Monitor

Matches new adverse-event reports to known safety signals and groups similar reports.

Industry	Level	Difficulty	Recommended mode
Healthcare	4 of 5	Expert	flat

Coming soon

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

The problem

• Adverse-event reports arrive as free text in volume.
• Duplicates inflate counts.
• Emerging signals are noticed late.

How SrvDB powers Pharmacovigilance Monitor

1. Known signals and past reports are embedded in separate databases.
2. Each new report is matched to the closest signals and to similar reports.
3. Reports far from every known signal are flagged for review.
4. Continuous ingestion with upsert and periodic persist().

What changes

Today	With Pharmacovigilance Monitor on SrvDB
Manual reading of every report	Reports arrive pre-grouped by similarity
Duplicates counted twice	Near-duplicates are linked
Signals emerge slowly	Unmatched clusters surface early

How it works

1. Ingest reports from your intake system.
2. Embed narratives.
3. Match to signal and report databases.
4. Queue unmatched or dense clusters for safety review.
5. Record reviewer decisions.

SrvDB features it uses

• Several databases: each database is a directory, so different data types or tenants stay separate.
• True cosine scores: scores in [-1, 1] mean the same in every mode, so thresholds are stable.
• upsert: inserts new items and replaces changed ones, so the knowledge base stays current.
• Crash-safe persist(): after it returns, data survives a crash or power loss and reopens exactly as committed.

Use cases

• Duplicate report detection
• Signal matching
• Emerging-cluster review
• Literature case matching
• Periodic safety report preparation
• Product-specific dashboards

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("./pharmacovigilance-monitor-db", dimension=768)

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

Limits and honest notes

• Supports, never replaces, regulated pharmacovigilance processes.

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	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 (this page)	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)