Trial Matcher

Shortlists patients for clinical trials by comparing summaries with eligibility criteria.

Industry	Level	Difficulty	Recommended mode
Healthcare	3 of 5	Advanced	flat

Coming soon

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

The problem

• Screening for trials is slow and manual.
• Eligible patients are missed.
• Criteria are long free text.

How SrvDB powers Trial Matcher

1. Each trial’s inclusion criteria are embedded; patient summaries are compared against them.
2. Top matches form a shortlist for coordinators.
3. search_batch screens many patients at once.
4. Closed trials are removed with delete.

What changes

Today	With Trial Matcher on SrvDB
Coordinators read every chart	A ranked shortlist comes first
Patients missed for trials	Every summary is checked against every open trial
Spreadsheets of criteria	Criteria are searchable by meaning

How it works

1. Embed open trials’ criteria.
2. Build de-identified patient summaries.
3. Run search_batch across summaries.
4. Coordinators review the shortlist.
5. Update as trials open and close.

SrvDB features it uses

• Exact search (flat): every query compares against every stored vector, so results are exact and explainable.
• search_batch: runs many queries at once, in parallel inside Rust.
• 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.

Use cases

• Oncology trial pre-screening
• Rare-disease recruitment
• Investigator dashboards
• Feasibility estimates for new trials
• Referral suggestions between sites
• Re-screening when criteria change

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("./trial-matcher-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 matching_trials(patient_summary, k=5):
    hits = db.search(embed(patient_summary), k)
    return [(json.loads(db.get(i)), round(score, 3)) for i, score in hits]

Limits and honest notes

• A shortlist for humans, never an eligibility decision.
• Structured criteria (labs, ages) still need rule checks.

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 (this page)	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)