IntegrityAnalysis — Evaluation of Baseline Data Integrity

What it does

The baseline table of a randomized controlled trial reports samples drawn from a single pre-treatment population, so the arm-to-arm variation of its means and counts is statistically predictable. Fabricated baseline data are routinely too similar across arms — the signature by which John Carlisle unmasked the Fujii fraud [1]. IntegrityAnalysis replays a submitted or published trial’s baseline table many thousands of times by Monte Carlo simulation, reproducing the printed rounding exactly, and reports one probability per trial: the chance that random allocation would produce baseline data at least as homogeneous as those reported [2, 3]. A small value is a screening signal that warrants scrutiny of the original data — it is never, by itself, a verdict of misconduct.

Using it

Upload the article PDF — the baseline table is extracted automatically — or a spreadsheet, or several files at once, or type the table directly into the editable grid.
Validation reports problems by coloring the cells of the grid; fix them in place and revalidate.
Results give a one-sided p value per baseline variable and per trial, with the Monte Carlo precision made explicit.
A journal-style reconstruction of the baseline table can be downloaded for side-by-side comparison against the manuscript.
The engine reproduces Carlisle’s published 2017 analysis of 5,087 trials with r = 0.991 [3].

The user guide documents the method, the input formats, and the statistics in full.

Privacy: nothing you upload or enter is retained. The uploaded PDF or spreadsheet, any data typed into the table, and the analysis results are all purged when the session closes. No record of the analysis is kept, and no document content is ever sent to any third-party service — the analysis is deterministic and self-contained. Manuscripts under review remain confidential.

Launch IntegrityAnalysis →

References

Carlisle JB. The analysis of 168 randomised controlled trials to test data integrity. Anaesthesia. 2012;67:521–537. doi:10.1111/j.1365-2044.2012.07128.x
Carlisle JB, Dexter F, Pandit JJ, Shafer SL, Yentis SM. Calculating the probability of random sampling for continuous variables in submitted or published randomised controlled trials. Anaesthesia. 2015;70:848–858. doi:10.1111/anae.13126
Carlisle JB. Data fabrication and other reasons for non-random sampling in 5087 randomised, controlled trials in anaesthetic and general medical journals. Anaesthesia. 2017;72:944–952. doi:10.1111/anae.13938