Put your methods, statistics, and conclusions to the test.
RigorMD reviews whether your study design and analysis support your claims, recalculates statistics where your reported numbers allow, and identifies conclusions that reach beyond the evidence. Receive a severity-scored report with findings tied to your manuscript and concrete recommendations for revision.
- Address methodological concerns before submission
- Reconcile inconsistent numbers across your manuscript
- Calibrate your conclusions to the evidence
$99 per manuscript.
Free to create an account — you only pay when you confirm a package for review. If we cannot deliver a usable report, the fee is refunded in full.
Works from your manuscript and supporting files. Statistical recomputation requires sufficient reported information; it does not rerun your underlying dataset.
32 deterministic checks · 22 checks recompute numbers or test arithmetic possibility.
| 01 | Design / claim fit | Serious |
| 02 | Results / conclusion | Moderate |
| 03 | Statistical method | Serious |
| 04 | Reporting guideline | Mild |
| 05 | Numerical consistency | Critical |
▸ opened — the same trace stands behind every row In your Table 2In-hospital mortality — 4.2% vs 6.1% In your abstract“…mortality fell to 2.4%…” What to doYou revised the table but the abstract still carries the old figure. Reconcile them before a reviewer does. | ||
| 06 | Clinical verdict | Moderate |
| 07 | Contribution & positioning | Mild |
Does the design support the claim?
A manuscript can report internally consistent numbers and still draw a conclusion its design cannot support. RigorMD examines the relationship between the research question, study design, analysis, and interpretation.
Illustrative review questions
- A treatment caused better outcomes in an observational study
- Whether selection, confounding, and adjustment support that causal interpretation
- An analysis treats patients as independent observations
- Whether hospital clustering or repeated measurements are addressed
- A nonsignificant result demonstrates ‘no difference’
- Whether the confidence interval still permits a clinically important difference
Recalculate the statistic. Show the discrepancy.
When the manuscript supplies enough information, RigorMD rebuilds the statistic and compares it with the reported value.
Constructed example. These are not patient or client data.
- Reported infection counts
- 18/90 versus 27/90
- Reported p-value
- 0.028
- Recomputed Pearson χ² p-value
- 0.121
The reported statistical significance is not supported by these counts at α = 0.05.
See the calculation
“Surgical-site infection occurred in 18 of 90 patients (20.0%) in the bundle group versus 27 of 90 (30.0%) with standard care (χ² = 4.83; p = 0.028).”a constructed specimen — and this sentence is the check’s entire input
| study arm | SSI | no SSI | total |
|---|---|---|---|
| bundle | 18 | 72 | 90 |
| standard care | 27 | 63 | 90 |
| total | 45 | 135 | 180 |
What we look at
Methods & statistical support
Whether the numbers hold up, and whether the design supports the kind of claim being made.
Integrity of the external record
Whether cited identifiers resolve, available retraction records raise concerns, and novelty claims agree with the prior literature retrieved for the report.
Results and conclusions in step
Whether the conclusions match what the data actually showed — tighter where the data will not carry them, bolder where they will.
Reporting completeness
Whether the paper meets the reporting standards its design and its target journal require.
An independent, outside read — statistical and methodological. The review before the reviewers.
Or start free with our abstract-deadline directory — 73 meetings, every date sourced →
Not sure it fits your paper? See what we'll recompute for your study →
Every manuscript that leaves carries your program's name.
Focus your reviewers. Reviewer time is the scarcest thing a department or an editorial office has, and it is spent badly when a methodological problem surfaces on the third pass. RigorMD gives one consistent methodological and statistical checkpoint before submission — so the reading your people do is the reading only they can do.
Authors keep their reports private. Leaders see adoption, workflow status, and aggregate usage — not findings or severity. The author gets a candid review they control; the program gets a common methodological checkpoint before submission.
Catch the flaw first
A severity-scored report with separate statistical checks and findings linked to manuscript passages, calculations, or reference records.
Check the revised draft
After you revise, the full review runs again — compared finding-by-finding with your first report: no longer flagged, still flagged, or new.
Two things you can use today, free. The paid review reads the whole manuscript.
Track the abstract deadlines that decide your calendar, and check that your citations resolve — no upload, and no account to browse a deadline or run a check. The $99 pre-submission review examines the whole manuscript. Two independent AI appraisers review the methods and conclusions. Separate numerical checks recalculate statistics from reported inputs.
Abstract deadlines
Abstract-submission deadlines for 73 research meetings across 24 clinical and surgical fields. Every deadline we show carries the society page it was checked against and the date; a meeting that hasn’t announced yet is listed as TBA rather than guessed at. Browse and download a calendar entry without an account, or sign in free to save meetings and get an email reminder before each one.
Browse the directory →Reference integrity
Do your DOIs and PMIDs actually resolve — and to the work you cited? The same reference layer the paid review runs, against Crossref, the DOI handle registry, and PubMed.
Check your references →Review the methods. Strengthen the manuscript.
Before submission, authors can examine whether the analysis supports the conclusions and whether the reported numbers agree. RigorMD provides a structured checkpoint for that review.
A 2021 review of accepted biomedical articles found reported median submission-to-publication times ranging from 70 to 558 days across included studies.
A report from one academic medical center describes demand straining statistical-support capacity. Authors can use a structured review to prepare questions for their research team.
In a 2012 survey of 100 orthopaedic papers, reviewers judged that a different statistical analysis could affect the conclusions in 17%.
Reference checks resolve cited identifiers and check available retraction records. The report identifies concerns and records which references could not be checked.
Errors in analysis can distort how clinicians interpret a study.
Upload the package
Manuscript, tables, figures, supplement, cover letter, title page. PDF and DOCX. Confirm what's included.
Review the design and claims
We classify the study design and claim type, appraise the manuscript across six domains, and a separate literature layer positions it against retrieved prior work as a seventh.
Recompute & verify
Deterministic checks recompute p-values, denominators, percentages, and means where the reported numbers allow. The report shows the supporting manuscript passage, calculation, or reference record.
Severity-scored report
Your PDF and web report are available in your private dashboard. We send a content-free email notification when they are ready.
Processing takes time and varies by package complexity and service availability. Your PDF and web report are available in your private dashboard; we email you when they are ready.
Seven domains, every manuscript. The first question is always: does the design support the claim?
Design / claim fit
Whether a causal, comparative, or equivalence claim is supported by the study design actually used.
Results / conclusion alignment
Whether the abstract, results, and conclusions agree — without spin or reframed null findings.
Statistical appropriateness
Models, power, missing-data handling, and multiplicity, matched to the design and endpoints.
Reporting guideline adherence
Design-specific reporting requirements, item by item, with the gaps named.
Numerical / statistical consistency
Whether numbers, denominators, p-values, intervals, tables, and text agree with one another.
Clinical interpretability / verdict
What a clinician or editor can legitimately take from the manuscript as written.
Contribution & literature positioning
Whether the manuscript's novelty and framing hold up against retrieved prior work — overstated firsts and unacknowledged priors flagged.
Every finding shows its work.
Findings point to supporting manuscript passages, calculations, or reference records so you can examine the evidence behind each concern.
≈ 58% illustrated reduction in apparent gain after excluding early events.
Read a full sample report →See every check we run →Try a free check yourself →
Three workflows. One rigor standard.
RigorMD serves authors preparing a manuscript, journals and publishers triaging submissions, and departments standardizing pre-submission QC across research groups.
Before and after peer review
Pre-submission review, reviewer-response scaffolds, and re-review for medical manuscript authors who need a methods-and-statistics second read.
Triage before review
Structured editorial decision support to route manuscripts, focus reviewer attention, and identify methods or statistical follow-up needs.
Protect the program's name
One consistent review across trainees, faculty, and clinical research groups, with author-private reports and aggregate adoption visibility.
How we examine your manuscript. Independent appraisals and calculations from your reported numbers.
Two independent AI appraisers examine your manuscript's methods, analysis, and conclusions. Separate numerical checks recalculate statistics when reported inputs allow. The report explains each concern and shows the supporting passage, calculation, or reference record.
A worked example: see a worked review of the corrected PREDIMED paper →
The report explains what the manuscript supports and what needs revision. Appraisal findings include statistical reasoning where applicable, with bias mechanisms and relevant framework detail when supported. Numerical findings show reported and recalculated values. Reference findings show the records checked. The headline conclusion also receives a calibration grade reflecting how its confidence compares with the evidence.
Fully automated, and we show our work: no human reads your manuscript as part of the analysis (operational access is limited to logged security review). Two independent engines and recomputed statistics produce a report you can verify yourself; delivery timing varies by package complexity and service availability.
And we are explicit about the limits: the report distinguishes checked and passed from not checkable from the submitted files. Without raw data, some questions can't be answered — and we say so. The report flags for your judgment and does not promise journal acceptance.
No paper is perfect — every study makes compromises. Use the findings to discuss limitations and revisions with your research team, mentors, and statistician.
RigorMD gives authors a structured review of the methods, reported statistics, and conclusions in a finished manuscript before submission.
The system draws on the research-on-research literature, statistical standards, and reporting guidelines. Its reports connect methodological concerns to their clinical implications, with statistical detail available for your co-authors.
Per report. Or licensed for your organization.
- Seven-domain severity scorecard
- Contribution & literature positioning — your novelty claims checked against retrieved prior work
- Deterministic statistical forensics
- Findings, supporting evidence, and suggested revisions
- PDF & web report in your private dashboard; email notification when ready
- Usage-based pilots for manuscript QC programs
- Author-private reports with an administrative activity view
- Editorial triage workflows for journals and publishers
Launch pricing — current rates apply to any report you start now. Every report is fully automated — two independent engines plus deterministic checks, with no human review in the analysis. Delivery time varies with package complexity and service availability. Pricing details & author FAQ →
Before you upload.
What is RigorMD?
RigorMD is an automated pre-submission review for clinical research manuscripts. You upload a manuscript package — text, tables, figures, supplement — and receive a severity-scored methodological and statistical report before you submit to a journal: two independent engines appraise the paper across multiple passes, a deterministic layer recomputes your reported statistics, cited DOIs and PMIDs are resolved against Crossref and PubMed, and the report shows the supporting passage, calculation, or reference record.
How does RigorMD review my manuscript?
RigorMD combines independent AI appraisal with separate numerical checks. Appraisal findings are reconciled across repeated readings, with additional verification required for some serious or critical concerns. Numerical checks show the calculation when reported inputs allow. Reference checks resolve cited DOIs and PMIDs and identify unchecked records. The Methods page explains the recurrence and verification rules.
Does RigorMD actually check my statistics?
Yes, and it goes further than arithmetic. A deterministic layer recomputes p-values, denominators, percentages, effect estimates against their confidence intervals, and related values from the manuscript's reported numbers, flagging any that do not reconcile — the recomputed number is shown in the finding. It also checks the study's reasoning the same way: it recomputes the interaction test behind a subgroup claim, whether a non-inferiority conclusion clears the paper's own margin, whether a "no difference" interval still reaches the important difference the authors themselves named, events per variable, the fragility index against loss to follow-up, the participant-flow arithmetic, I² from the reported Q, and the sample size the stated design requires.
How does RigorMD check my references?
Cited DOIs and PMIDs are resolved against Crossref, doi.org, and NCBI PubMed; identifiers that do not resolve, or that resolve to a different article than the one cited, are flagged in the report.
Is the report written for a clinician or a statistician?
Both. The report explains the concern, shows its supporting evidence, and suggests a next step. Appraisal findings include clinical explanations and statistical reasoning where applicable. Numerical findings show reported and recalculated values; reference findings show the records checked.
Does RigorMD read my paper in the context of the medical literature?
A dedicated literature layer retrieves a bounded set of PubMed titles and abstracts and compares your framing and novelty claims with that prior work. The report cites the retrieved records. This is not a complete literature search.
Send a stronger manuscript the first time.
Upload your package and we'll email you when the severity-scored report is ready. Delivery time varies with package complexity and service availability. Use the findings to address methodological concerns raised in your report.