Single-arm interventional study
What happens after a specified intervention when no randomized concurrent comparator is included?
When to use this project
Estimate response, safety or another prespecified outcome after a common intervention, often in early development or a setting where the objective justifies a single arm.
How it differs
Without a concurrent randomized comparison, outcome changes can reflect prognosis, selection or background care. A historical benchmark adds assumptions and does not create randomization.
Decisions before you start
- Define the estimand, follow-up horizon and enrolled versus treated populations.
- Justify any benchmark by population, calendar era, endpoint definition and uncertainty.
- Prespecify success and stopping rules, including multiplicity, and retain outcomes after discontinuation when relevant.
How the flows work together
Each flow below links to its diagram, steps and tables. Flow order organizes the project; it does not imply that all work is strictly sequential. Data assessment, analysis planning and protocol refinement may inform one another.
1. Single-arm study overview
Overview · Question through intervention study reporting
Use this overview to state the purpose and link to detailed decisions. Keep a versioned protocol and decision register, and add evidence references for the rationale.
2. Recruitment and treatment
Selection · Track enrollment and intervention receipt
Retain screening, enrollment and intervention receipt as distinct statuses. Participants not treated or discontinuing early still matter for the prespecified study population and safety accounting.
3. Endpoints and benchmark rationale
Design · Define outcomes and comparison basis
A success threshold, an aggregate historical benchmark and participant-level external controls are different comparison bases. Record why the benchmark is applicable; none creates randomized exchangeability.
4. Sample size and decision rules
Statistics · Specify precision thresholds and stopping
Justify precision or the complete decision rule, including any multistage stopping. A nominal one-sample test does not account automatically for uncertainty or changes in a historical benchmark.
5. Follow-up and safety
Conduct · Plan assessments monitoring and disposition
Stopping treatment need not end outcome follow-up. Distinguish adverse-event seriousness from severity, define ascertainment windows and keep clinical safety review separate from statistical efficacy monitoring.
6. Data and analysis plan
Statistics · Define populations methods and sensitivity
State the denominator before examining response. Restricting analysis to evaluable participants can induce selection. Retain uncertainty in the outcome and in any comparison basis, and limit causal claims accordingly.
Equations and statistical interpretation
These explanations describe notation and assumptions. Flow does not calculate these values.
Observed response proportion
r is the number meeting the response definition and n is the prespecified analysis denominator.
State how missing assessments and deaths enter the estimand. An evaluable-only denominator can introduce selection. Comparing this proportion with historical experience requires comparability assumptions.
Published example
Inspect the single-cohort design, response definition and distinction between enrollment and infusion. Consider what the absence of a randomized comparator permits the study to conclude.
This publication illustrates a study design, not an endorsement of every method or a reproduction of its results. Follow its protocol, supplement and update history when studying the example.
Hypothetical scenario
An early development team wants to estimate response and safety of a new intervention in a narrowly defined population.
- Single-arm study overview: State the estimation objective and justify using one arm; obtain approvals and register before recruitment.
- Recruitment and treatment: Record screening, consent, intervention receipt and continued follow-up.
- Endpoints and benchmark rationale: Define response, safety and any benchmark using comparable populations and assessments.
- Sample size and decision rules: Choose sample size for precision or a specified decision rule with verified operating characteristics.
- Follow-up and safety: Schedule outcome and safety follow-up and document discontinuation separately from withdrawal.
- Data and analysis plan: Analyze the prespecified population and examine missing outcomes and benchmark sensitivity.
Deliver a populated protocol, decision log, data specification, and planned outputs. Enter numerical findings only after analysis and verification. Keep decisions made before seeing results distinguishable from later amendments.
Sources
- ICH E9(R1): estimands and sensitivity analysis (2019)
- WHO: clinical trials and prospective registration
- WHO: primary registries in the trial registry network
- ISRCTN: what the clinical study registry records
- ClinicalTrials.gov: about the registry
Source check: 2026-09-17. Record the version of each reporting or appraisal tool used in your actual protocol.
Compare all Clinical trials project types · Open editor in a new tab