A CONSORT flow diagram reports how many participants were assessed, randomized, allocated, followed up and analyzed in each arm of a randomized trial. Paste the participant-flow paragraph from your manuscript: Vizcept puts each count in its CONSORT 2025 box and typesets the figure with code, so the counts it sets come from your text.
Attach a sketch or an existing image (JPG/PNG/WEBP, up to 10MB)
Free trial: 5 credits, 2K resolution with watermark
Paste your own participant flow on the left to generate your CONSORT diagram
The numbers already sit in your results section or your trial log. What takes the time is retyping them into boxes and keeping the arms lined up every time a count changes. Paste the paragraph and let the generator do the layout.
Write, or paste from your manuscript, how many were assessed for eligibility, excluded (with reasons), randomized and allocated to each arm; then who did not receive the intervention, who discontinued it, who was lost to follow-up and how many were analyzed. Name the arms the way your paper does. Counts, arm names and reasons are all it needs; leave participant identifiers out.
A text model reads the paragraph and assigns each number to a CONSORT 2025 box. Code then lays out the four stages, one column per arm, and sets every count in type. The model is told to leave a count you did not write blank instead of working it out by subtraction, and code drops any count above zero that appears nowhere in your text.
Read each box against your trial log: on a typeset figure the digits come from your text, but which box a number landed in is the model's reading of it. Download a 300 DPI PNG for Word, or an SVG; on a typeset figure its labels stay editable text.
A CONSORT flow diagram is the figure in a randomized trial report that follows every participant from eligibility screening to the analysis: how many were assessed, excluded and randomized, and for each arm how many received the intervention, stopped it, were lost and were analyzed. CONSORT stands for Consolidated Standards of Reporting Trials.
Item 22a of the CONSORT 2025 checklist asks, for each group, for "the numbers of participants who were randomly assigned, received intended intervention, and were analysed for the primary outcome". Item 22b asks for "losses and exclusions after randomisation, together with reasons". Most trial reports answer both in the flow diagram, which has four stages:
| Stage | Boxes in the CONSORT 2025 template |
|---|
| Enrolment | Assessed for eligibility; Excluded (not meeting inclusion criteria, declined to participate, other reasons); Randomised |
| Allocation | For each arm: Allocated to intervention; Received allocated intervention; Did not receive allocated intervention (give reasons) |
| Follow-up | For each arm: Discontinued intervention (give reasons); Lost to follow-up for primary outcome (give reasons) |
| Analysis | For each arm: Analysed for primary outcome; Excluded from analysis (give reasons) |
The template is spelled the British way (Enrolment, Randomised, Analysed). Write randomized and analyzed in your description and the boxes switch to US spelling; if your text mixes the two, check the headings.
CONSORT 2025 was published on 14 April 2025, at the same time in The BMJ, JAMA, The Lancet, Nature Medicine and PLOS Medicine (Hopewell et al.). It replaces CONSORT 2010 with a 30-item checklist, which adds seven items, revises three and deletes one, and it comes with an updated flow diagram. The four stages are the same; the follow-up and analysis boxes changed:
| CONSORT 2010 | CONSORT 2025 | |
|---|---|---|
| Follow-up, first line | Lost to follow-up (give reasons) | Discontinued intervention (give reasons) |
| Follow-up, second line | Discontinued intervention (give reasons) | Lost to follow-up for primary outcome (give reasons) |
| Analysis | Analysed | Analysed for primary outcome |
| Checklist items on participant flow | 13a and 13b | 22a and 22b |
"For primary outcome" makes clear that the loss and analysis counts refer to the primary outcome, not to every measurement in the trial. Vizcept uses the 2025 wording by default. If your journal or protocol still uses the 2010 template, write "CONSORT 2010" in your description to get the 2010 wording and box order.
When we checked on 21 September 2026, three other CONSORT diagram generators (ConceptViz, SciDraw and ChatDiagram) still described their output as CONSORT 2010. The official 2025 Word template is on consort-spirit.org.
Reviewers trace each arm from randomization to analysis. Run these checks before you submit:
Discontinued and lost to follow-up are separate counts, even though they share the follow-up box. Discontinued intervention means the participant stopped the treatment; lost to follow-up for primary outcome means you have no primary outcome data for them. One person can be counted in both.
A worked example, from the first figure in the examples below:
| Box | Telehealth | Usual care | Check |
|---|---|---|---|
| Allocated | 168 | 168 | 168 + 168 = 336 randomized; 523 assessed β 187 excluded = 336 |
| Received / did not receive | 161 / 7 | 168 / 0 | 161 + 7 = 168 |
| Discontinued intervention | 6 | 0 | |
| Lost to follow-up for primary outcome | 14 | 17 | |
| Analyzed for primary outcome |
When an image model draws a flow diagram, every box and digit is painted as pixels from your description, and nothing ties a painted digit to the number you wrote. Vizcept splits the job in two:
Three rules follow:
What still needs your eyes: whether each number landed in the right box, because that is the model's reading of your sentences, and the arm names and reasons, which the model copies from your text.
The image model draws the whole figure instead, so check every number on it, when:
Yes. CONSORT is the reporting guideline for randomized trials. Other study designs have their own guideline, and most of them ask for a flow diagram too:
| Study design | Guideline | Flow diagram |
|---|---|---|
| Randomized trial, parallel groups | CONSORT 2025 | Strongly recommended; the counts are checklist items 22a and 22b |
| Pilot or feasibility randomized trial | CONSORT extension for pilot and feasibility trials | Adapted CONSORT diagram |
| Cohort, case-control or cross-sectional study | STROBE | "Consider use of a flow diagram" (item 13c) |
| Diagnostic accuracy study | STARD 2015 | Flow of participants in a diagram (item 19) |
| Systematic review | PRISMA 2020 | Recommended: item 16a says "ideally using a flow diagram"; use the |
This generator lays out randomized trials with two to five parallel arms. For a cohort study's flow, the will draw it with an image model; check every number.
Yes, and you own the figure. Two things to do before you submit:
Writing a thesis with a systematic review chapter as well? The draws that figure.
The options differ in what you type and who places each number.
| Option | Cost | What you enter | Template | Who places the numbers |
|---|---|---|---|---|
| CONSORT 2025 Word template | Free | Every count, typed into the boxes | CONSORT 2025 | You |
| R package consort | Free, open source | One row per participant, with exclusion, allocation and follow-up columns | CONSORT-style, configurable | The package, from your dataset |
| ConceptViz | Free for the form-based diagram | Counts typed into a form | CONSORT 2010 | Its code, from the form |
| SciDraw | 5 credits a diagram | A description of your trial | CONSORT 2010 | An AI model; its page asks you to check every n= |
| PowerPoint or Word by hand | Free | Every box, arrow and count | Whatever you draw | You |
| Vizcept | Your first 2K diagram on Vizcept is free without an account (watermarked preview), then 5 credits a diagram at 2K; a one-time pack of 150 credits is $19.90 | Your participant-flow paragraph | CONSORT 2025, or 2010 on request |
Students Β· Trialists Β· Methods teachers
CONSORT 2025 asks every randomized trial report for its participant flow, including a flow diagram (checklist item 22). These are the three groups who draw it most often.
Nursing, psychology, education and sports science theses
Your pilot trial goes in chapter four, and your supervisor wants the participant flow in the 2025 format. The numbers are in your spreadsheet; you do not want to spend an evening aligning boxes in Word.
Submission and revision
A reviewer wants the reasons for discontinuation split by arm, and the journal wants a vector figure. Edit the paragraph, regenerate, and export an SVG; on a typeset figure you can still correct its text in Illustrator or Inkscape.
Teaching trial reporting
You teach CONSORT to students who have never read a trial report closely. Hand out a blank CONSORT 2025 template, then a worked example with realistic numbers, and show what changed from 2010.
Six trial designs
Each figure below was generated from the text shown underneath it, with nothing retouched. Reuse an example as a starting point and swap in your own counts.
Telehealth vs usual care, with reasons for exclusion, non-receipt, discontinuation and loss
US spelling, three columns, intention-to-treat analysis
A 6-month and a 12-month row, each with its own losses
Four parallel columns under one randomization box
Every count left empty, for a handout or a protocol appendix
For a journal still on the 2010 template, with grey stage labels
The CONSORT 2025 template has a standard anatomy: four stages, one column per arm, and a reason for every participant who left. The generator starts from that template and fills it with your counts.
2010 on request
Follow-up and analysis boxes say "for primary outcome", and discontinued comes before lost to follow-up, as in the 2025 template. Ask for CONSORT 2010 and you get the older wording and box order for a journal that still uses it.
Your first 2K diagram on Vizcept is free without an account; the download is a watermarked preview. Upgrade for 4K, no watermark and SVG downloads while you revise, or buy a one-time credit pack for a single trial report with no subscription.
Student or teacher? Apply for an education discount
FAQ
Paste your participant flow, check each box against your trial log, and export a PNG at 300 DPI or an SVG.
| 154 |
| 151 |
| 168 β 14 = 154; 168 β 17 = 151 |
In this trial everyone who discontinued still gave primary outcome data, so analyzed = allocated β lost. That will not hold in every trial, which is why the generator is built not to fill a box by subtraction: the figure should show what happened, not what the arithmetic implies. The next section explains the check and what it cannot catch.
The result does not yet show which way a figure was made. To change a count, edit your paragraph and generate again. More on .
| A text model assigns each count; code typesets it; counts above zero not in your text stay blank |
If you want no AI anywhere near the figure, use the Word template or the R package. The R package is also the only option that works from participant-level data, so its counts cannot drift from your dataset. Prices and templates checked 21 September 2026.
Typeset, not painted
Code sets each count in a font, so a digit cannot blur or change. A count the model worked out is dropped and its box left blank if that number appears nowhere in your text; if it matches another number you wrote, it stays, so check each box.
Each reason listed, with its count if you give one
Give reasons for exclusion, non-receipt, discontinuation and loss to follow-up in your paragraph, and each is listed separately under its box. Leave them out and the box keeps "(give reasons)" (the Excluded box lists the template's three reasons with blank counts instead), so the gap shows before a reviewer finds it.
Parallel-group trials
Three-arm dose trials, 2x2 factorial trials drawn as four groups, and trials with 6- and 12-month visits get one column per arm and one row per visit. Crossover trials, and cluster trials that report clusters and participants separately, go to the image model instead; check every number on those.
Word, LaTeX and journal upload
The PNG drops into Word or a slide at print resolution. On a typeset figure, the SVG keeps every label as real text, so you can fix a word in Illustrator or Inkscape without generating again; a figure the image model drew exports as traced shapes. Microsoft 365 and Word 2019 or later place SVG files directly.
US or UK, English or not
On the 2025 template, write randomized and the box says Randomized; write randomised and it says Randomised. The 2010 template keeps its own spelling, Enrollment and Randomized. Describe the trial in Spanish, Portuguese or French and the model translates the box labels; any it leaves out stay in English. Ask for black and white and the stage labels print in grey.
Explore more AI diagram tools across subjects β from the same discipline and beyond.
One subscription unlocks every Vizcept AI diagram tool β from free body diagrams and syntax trees to biology diagrams and more.
