Clinical · Training guide
Clinical Trial Protocol
Write a phase 1, 2 or 3 protocol synopsis to ICH M11, with the elements expected for the phase checked and the sample size recalculated from your assumptions.
Open the tool at https://app.cmcfy.com/app/clinical-trial-protocol.html. This guide is also online at https://cmcfy.com/guides/clinical-trial-protocol.html
1. What this module does
You give the phase, title, population and design, the objectives with their endpoints, the primary estimand, the design elements and the sample size assumptions.
For phase 1 the tool checks the starting dose against the MRSD, sentinel dosing and the dose-limiting toxicity definition. For phases 2 and 3 it checks the estimand, randomisation, blinding, control and multiplicity. It recalculates the sample size for two proportions or two means, with the allocation ratio and dropout.
What you get
- A Word or PDF file: protocol synopsis (ICH M11 section 1).
2. Before you start
Have these ready. You can still start with the example data and replace it piece by piece.
- Objectives and endpoints.
- The primary estimand.
- The sample size assumptions (rates or difference and SD, alpha, power, dropout).
3. Step by step with the example
Open the tool at app.cmcfy.com/app/clinical-trial-protocol.html. The example is loaded when the page opens, so every panel already has realistic data. Follow the steps to see how it works, then replace the example with your own data.
Describe the trial
Choose the phase and give the protocol number, title, population and design.
Enter objectives and design elements
One row per objective with its endpoint. For phase 1, give the starting dose, MRSD and DLT definition.
Read the result
The headline gives the outcome: "Phase 3 protocol complete · 43 subjects needed, 450 planned".
Objectives and endpoints. Resolve alerts and download
No primary objective, a non-randomised phase 3, a starting dose above the MRSD and no DLT definition are critical. A missing estimand, multiplicity strategy or schedule of activities, and a sample size below the calculation, are flagged. Then preview and download.
4. Field reference
Every input in the tool, panel by panel. Tables accept rows pasted straight from Excel, comma-separated text, or a loaded file; check the columns after loading a file. Fields marked “when it applies” appear only for the choices that need them.
1 · Trial
| Field | What to enter |
|---|---|
| Investigational product | Type it in. |
| Protocol number | Type it in. |
| Phase | Choose one: Phase 1; Phase 2; Phase 3. |
| Title | Type it in. |
| Population | Type it in. |
| Design | Type or paste text. |
2 · Objectives and endpoints
One row per objective. Type: primary, key secondary, secondary, exploratory or safety.
| Field | What to enter |
|---|---|
| Objectives | Type is primary, key secondary, secondary, exploratory or safety. A table. Columns: Type | Objective | Endpoint. Paste rows from Excel, type comma-separated rows, or press Load file (Excel, CSV, Word, PDF or a scan). |
| Primary estimand (ICH E9(R1): population, variable, intercurrent events and strategy, summary measure) | Type or paste text. |
3 · Design elements
| Field | What to enter |
|---|---|
| Randomised when it applies | Tick the box if it applies. |
| Blinding | Choose one: Double-blind; Single-blind; Open label. |
| Control | Choose one: Placebo; Active comparator; Dose comparison; None. |
| Multiplicity control for more than one primary or key secondary endpoint when it applies | Type it in. |
| Independent data monitoring committee | Tick the box if it applies. |
| Schedule of activities included | Tick the box if it applies. |
| Starting dose (mg) when it applies | Type a number. |
| MRSD from the NOAEL (mg) when it applies | Type a number. |
| Sentinel dosing when it applies | Tick the box if it applies. |
| Dose-limiting toxicity definition and stopping rules when it applies | Type it in. |
4 · Sample size
| Field | What to enter |
|---|---|
| Primary endpoint type | Choose one: Two proportions; Two means; No formal calculation (phase 1 or pilot). |
| Response, test arm (%) when it applies | Type a number. |
| Response, control arm (%) when it applies | Type a number. |
| Difference to detect when it applies | Type a number. |
| Standard deviation when it applies | Type a number. |
| Two-sided alpha when it applies | Type a number. |
| Power (%) when it applies | Type a number. |
| Allocation ratio (test : control) when it applies | Type a number. |
| Expected dropout (%) when it applies | Type a number. |
| Planned total sample size | Type a number. |
5. Checks and alerts
Calculations and pass/fail outcomes always come from fixed rules, never from AI. The tool checks:
- Every objective has an endpoint.
- Phase-specific design elements.
- Sample size from the assumptions.
How to resolve alerts
- Critical alerts block the download and must be fixed in the data. A failing result can instead be linked to an investigation: type the investigation reference and outcome and press Record.
- Major alerts block the download until you fix them or type a justification and press Accept justification.
- Minor alerts do not block anything. They are listed in the documents so the reviewer sees them.
- Some alerts have an Apply fix button that makes the change for you. Reopen undoes a justification.
Narratives
This module writes: Synopsis rationale and design. Each narrative is written by fixed rules from your data. You can edit it in the box. Rewrite with AI (where your plan includes AI) rewrites it in regulatory style; every number in the text is checked against your data, and a number that does not match is flagged under the box and blocks the download until you correct it. Reset to rule-based text brings back the original.
6. Preview, gap review and download
- Press Preview next to a section, or Preview and download all. The document opens in a preview window, exactly as the Word file will read.
- The left side lists the review, run on your device: gaps in the data (missing values, open alerts), gaps in the report (missing content the guidance expects, placeholders such as [site] or TBD left in the text) and, if you load the approved protocol under Compare with the protocol, differences from the protocol (requirements, criteria, batches or time points it plans that the report does not show).
- Click a finding to jump to the place in the preview. Fix it in the tool, then preview again.
- Optional AI review: a second read for contradictions, claims without data and vague wording. The report text is sent to Claude only when you press it, and only where your plan includes AI. Check every AI finding; AI can be wrong.
- Press Download Word (.docx) or Download PDF. With several documents open, All as Word (.zip) and All as PDF (.zip) download the set. The download buttons stay disabled while a blocking alert is open; the preview still works.
Documents this module produces
| Section | Document |
|---|---|
| Protocol | Protocol synopsis (ICH M11) |
Use Save project to keep your work as a file on your computer, and Open project to continue later. Start blank clears every field; Load example brings the example back. Nothing is stored on CMCfy servers.
7. US and EU submissions
ICH M11, E6(R3) and E9(R1) apply in the US and the EU; first-in-human checks follow FDA (2005) and the EMA FIH guideline (2017).
8. Working with other modules
- The protocol is part of the IND Application; report the trial in the Clinical Study Report. CMC study protocols are in the Protocol Builder.
9. Common pitfalls
- Two primary endpoints and no multiplicity strategy.
- A sample size that leaves out the dropout.
10. Practice exercises
Each exercise starts from the example (press Load example to reset). We run these on every update of this guide, so the result you see should match.
Plan a smaller trial
Change the planned total sample size from 450 to 40.
Expected resultThe headline shows the sample size is below what the assumptions need.