Link Records Across Medical Datasets

Add the everyrow connector if you haven't already. Then upload papers_700.csv and trials_200.csv and ask Claude:

Match these PubMed papers to the clinical trials they report results for. A paper matches a trial if it describes the results of that trial. Look for matching interventions/drugs, conditions, study design, and outcomes. Drug names may appear as brand or generic. Not every paper has a matching trial.

73 paper-trial matches found with 84.7% F1 score. Results take about 7.5 minutes.

Claude Code is great at reading a paper abstract and matching it to a clinical trial. When you have 700 papers and 200 trials, the matching requires evaluating thousands of potential pairs for drug aliases, rewritten trial titles, and study design terminology.

Here, we get Claude Code to match PubMed papers to the clinical trials they report results for.

Add everyrow to Claude Code if you haven't already:

claude mcp add futuresearch --scope project --transport http https://mcp.futuresearch.ai/mcp

With the papers and trials CSVs in your working directory, tell Claude:

Match these PubMed papers to the clinical trials they report results for.
A paper matches a trial if it describes the results of that trial. Look for
matching interventions/drugs, conditions, study design, and outcomes. Drug
names may appear as brand or generic. Not every paper has a matching trial.

Claude calls everyrow's merge MCP tool with many-to-one relationship:

Tool: everyrow_merge
├─ task: "Match publications to the clinical trial they report results for..."
├─ left_csv: "/Users/you/papers_700.csv"
├─ right_csv: "/Users/you/trials_200.csv"
└─ relationship_type: "many_to_one"

→ Submitted: 700 rows for merging.
  Session: https://futuresearch.ai/sessions/d02d59b7-29fd-4e23-b35c-38c6a9096c34
  Task ID: d02d...

Tool: everyrow_progress
→ Running: 0/700 complete (30s elapsed)

...

Tool: everyrow_progress
→ Completed: 700/700 (0 failed) in 448s.

Tool: everyrow_results
→ Saved 700 rows to /Users/you/matched_trials.csv

73 paper-trial matches found. View the session.

Scored against 64 gold-labeled pairs:

627 papers were correctly left unmatched (distractors with no corresponding trial). The many-to-one relationship correctly models that multiple papers can report results from the same trial.

The everyrow SDK's merge() handles semantic matching across medical terminology, drug aliases, and study design descriptions. This notebook demonstrates matching papers to clinical trials with gold-label evaluation.

pip install everyrow
export EVERYROW_API_KEY=your_key_here  # Get one at futuresearch.ai/api-key

import asyncio
import pandas as pd
from everyrow import create_session
from everyrow.ops import merge

trials_df = pd.read_csv("trials_200.csv")
papers_df = pd.read_csv("papers_700.csv")

async def main():
    async with create_session(name="Clinical Trials to Papers") as session:
        result = await merge(
            session=session,
            task="""
                Match publications to the clinical trial they report results for.
                Look for matching interventions/drugs, conditions, study design,
                outcomes, and sponsor/institution. Drug names may appear as brand
                or generic. Not every paper has a matching trial.
            """,
            left_table=papers_df,
            right_table=trials_df,
        )
        return result.data

merged = asyncio.run(main())
matched = merged.dropna(subset=["nct_id"])

EveryRow maintains accuracy as datasets grow by dynamically allocating more agents. Its higher recall (90.6% vs ~59%) comes from finding matches that require deeper semantic understanding of medical terminology.