AudioScholar·Find Trials ·Method note

How a topic's most-cited trials get to the top of the list

A free tool for trainees: type a topic in any specialty and get the randomised trials, systematic reviews and guidelines it is built on — each with a direct link through your own university library, and one tap to save into Zotero, Mendeley or EndNote. Every number on every card comes from PubMed or the NIH. A model (Claude) chooses and orders the shortlist and writes the one-line reason on each card — it can drop or reorder the papers the search returned, and it cannot add one. The tool shows you the numbers it ranked on.

1 line per card written by a model — every number is NIH’s
3,000 papers scored and ranked per search
2 public sources: PubMed and NIH iCite

How a paper is surfaced

Seven steps, in this order

Each step either widens the net or narrows it. Nothing is hand-picked: PubMed and the NIH supply every paper and every number, and a model is allowed to do exactly two things at the end — choose and order a shortlist from what the search already returned, and say in one line why each paper is there.

1

Search PubMed deep, not shallow

One search per lane, taking up to three thousand papers rather than the first page or two. Depth is the whole point: the papers you are looking for are usually not the ones PubMed shows first.

Why depth matters Searching atrial fibrillation anticoagulation, RE-LY sits at position 867 in PubMed's own relevance order, and ROCKET-AF, ARISTOTLE and ENGAGE-AF are scattered near it. They match the query perfectly; they are simply not ranked highly. Read deep and rank by citation impact and all four come back at positions 1, 2, 3 and 4.
2

Keep only the study types you asked for

Randomised and phase III trials in one lane; systematic reviews and meta-analyses in a second; guidelines in a third. These labels are the National Library of Medicine's own indexing, not our guess. A systematic review that earns a place in the shortlist is also listed under reviews, so a reader looking for the definitive meta-analysis finds it where they expect it.

A deliberate exclusion Multicenter Study is left out of the trials lane on purpose — it lets large observational registries into a list labelled "Trial". Removing it cut one topic's pool from 2,626 papers to 1,041 without losing a single known landmark.
3

Score every candidate against its own field and year

Ranking uses the Relative Citation Ratio from NIH iCite — a citation rate normalised for both research field and year of publication. That is what lets a 2001 nephrology trial and a 2019 oncology trial be compared without one burying the other, which raw citation counts cannot do.

4

Make a paper earn its place before citations can rank it

Ranking on citations alone lets a merely famous paper drift to the top of a loosely worded search. So on a large pool a paper qualifies only if PubMed ranked it near the top for your topic, or its own title carries two of your topic's words — including the synonyms the search was widened with, so a trial titled "renal" is not penalised for a reader who typed "kidney" — or PubMed indexes your topic as one of its major subjects. Papers that fail are pushed below every paper that passes — and labelled — but they are never deleted. On a small pool, where there is nothing for fame to hijack, the test stands down.

Why two words, and why nothing is deleted One word is not enough: a search for peritoneal dialysis put a 1976 paper on peritoneal lavage for pancreatitis at number two, on the strength of "peritoneal" alone. But deleting weak matches is worse than demoting them — the 4S statin trial is titled "Randomised trial of cholesterol lowering in 4444 patients" and contains none of your topic's words, so a filter that deletes would erase a landmark. It ranks lower and stays visible instead.
5

Put the governing guideline first — and look past the tag

An older guideline out-cites its replacement simply for having existed longer, so a plain citation sort would put superseded guidance above the document that replaced it. Guidelines from the last eight years therefore come first, ordered by how heavily they are cited, and everything older follows by date. The same guideline published in two journals is shown once, and where an older edition shares its replacement's title only the newer one is kept. That is what lifts a society's current guideline above the expert opinions and national digests that share its dates.

The gap most tools miss PubMed's own guideline tag is unreliable for specialty societies. Of twenty guideline-shaped documents in Peritoneal Dialysis International, only three carry it — papers titled "ISPD guidelines for peritoneal dialysis in acute kidney injury" are filed as ordinary journal articles. A second, clearly labelled band finds guidance that declares itself in its own title, so society documents are not invisible.
6

Show what was just published, separately

A paper from the last few weeks has no citations yet, so it cannot compete in a citation-ranked list — and the National Library of Medicine often has not yet tagged it as a trial at all. The newest papers from about seventy major journals, over the last four months, get their own section ordered by date, with no study-type gate.

7

Let a model choose and explain the shortlist — but never add to it

Three narrow jobs go to a model (Claude). Before the search, it turns what you typed into the concept groups PubMed actually needs — "SGLT2 inhibitor" also as empagliflozin and dapagliflozin — and says so above the results, with one tap to search your exact words instead. After the search, it reads the forty most-cited candidates and picks up to twenty-five, ordering them by how much a trainee needs to have read each one and writing one line per paper on what it established or changed. It may drop a paper and it may reorder them; it can never add one. Every identifier it returns is checked against what the search found, and anything not in that set is discarded. The one-line reasons are the model's words and are marked as such; every number on the card is the NIH's.

Why the model is not allowed to name papers A model asked for the landmark trials on a topic will confidently list real-sounding papers, some of which do not exist. Keeping it inside the set PubMed returned is the difference between an assistant that reorders and one that invents.

How we check they are real

Four gates, and what each one does

A trainee reading this list may not yet have the background to sense when something is wrong. So the checks have to hold on their own.

Removed

Retracted papers and preprints

Excluded in the search itself. This matters more than it sounds: a citation-ranked list is enriched for retracted work, because a paper the field spent years rebutting accumulates citations while being rebutted.

Flagged

Papers under an expression of concern

These carry no publication-type marker at all — the only trace is inside the paper's own corrections record. Of sixty such papers we checked, sixty would have displayed with no warning. They now carry an amber badge, and a retracted paper that slips past the search filter gets a red one with its citation count removed.

Noted

Published corrections

Where a correction exists, the card says so and points at the record. RE-LY carries one that revised its event counts — worth knowing before you quote a number from the abstract.

Guaranteed

Every identifier belongs to the paper you are looking at

A PubMed record also lists the IDs of every paper it cites. Reading those by accident would badge a card with a different paper's data. Every ID here is anchored to the article's own record, and every citation figure is matched by identifier, never by position in a list.

What it cannot do

Cited is not the same as correct

This is the part worth reading twice, and it is printed on the tool itself, above the results — not buried in a footnote.

The case that proves the point

Search perioperative beta blockade and the top result is a 1999 trial from a group later found to have committed research misconduct — the finding that made perioperative beta blockade standard practice, and that was subsequently overturned.

Its PubMed record carries no retraction, no correction and no expression of concern. The trial that reversed the conclusion does not even appear in the results, because it uses a different word for the drug. Every number on that screen is true, and a reader without the background reads it exactly backwards. That is why the warning sits above the list rather than beneath it.

966 citations RCR 29.5 NIH percentile 100 flags in PubMed: none

Try it on a topic you already know well

That is the honest test — search something you can already judge, and see whether the list matches what you would have taught. Then set your library once, and every result opens full text through your own institution.

Free · No account · No login · Nothing to install