Study Protocol Templates and AI Drafting Kit

What this is

Five editable research-planning templates with instructions, a reusable model prompt, an independent review prompt, and a portable SKILL.md. These are original RWEdnesdays editorial aids, not official society forms, a validated autonomous research system, or approval of a study design.

Choose by goal and design

For noninterventional treatment effects, use the comparative RWE template with HARPER and STaRT-RWE. For incidence, prevalence, burden, utilization, or treatment patterns, use the descriptive template with explicit denominators and capture limits; STROBE/RECORD inform final reporting. For synthesis, use the ITC/NMA template with PRISMA-P for protocol reporting, ISPOR for conduct and feasibility, and PRISMA-NMA for the completed report. For economic value or affordability, use the economic analysis plan with separate modules: CHEERS 2022 concerns economic-evaluation reporting and excludes budget impact, which uses ISPOR BIA. For randomized assignment embedded in routine care, use the pragmatic-trial template with SPIRIT 2025 and relevant extensions; CONSORT concerns completed reports.

When to use

Start after defining the decision and before outcome-dependent analytical choices. Expand a Study Designer intake brief into the matching template; the brief alone is not a full protocol. Use linked documents for mixed goals when estimands, data, or governance differ. An AMCP dossier organizes evidence for a payer rather than replacing the protocol that generates evidence.

When not to use

A completed shell or model response does not establish scientific, statistical, ethics, regulatory, or submission approval. Use an authority-specific required form when applicable. Keep unknown dataset fields, unavailable validation, missing effect modifiers, and unresolved estimands as open decisions rather than inventing values.

Use with a model

Provide the selected template, approved non-sensitive study brief, data dictionary, and relevant guidance. The prompt asks the model to identify consequential missing choices, verify sources, draft independent sections, and return a protocol, decision log, guidance crosswalk, claim/source ledger, and objective-to-analysis-to-output map. Use the review prompt with the actual artifacts in a separate context. The skill does not execute analyses, install itself, or authorize external submission.

Downloads

• Comparative effectiveness and safety RWE: Word · Markdown
• Descriptive epidemiology and utilization: Word · Markdown
• Indirect comparison and network meta-analysis: Word · Markdown
• Health economic analysis plan: Word · Markdown
• Pragmatic randomized trial: Word · Markdown

Instructions and AI resources

Complete kit ZIP · Instructions · Build prompt · Review prompt · SKILL.md. Keep the entire folder together so the skill's local references resolve.

Guidance crosswalk

Record the exact guidance/version, applicable item, protocol location, evidence or implementation artifact, status, and reviewer. Separate protocol planning, reporting guidance, and local reviewer decisions. Add currently applicable ENCePP/PASS or other authority-specific forms when the study pathway requires them.

How it maps to the catalog

Use protocol and SAP elements, data fitness, and anchored ITC for the operational concepts behind the selected template.

Implementation

Link data-fitness, phenotype-validation, and protocol/SAP deviation records. Map every objective to its population, endpoint/time horizon, target quantity, estimator, uncertainty, sensitivity analyses, and table or figure. Preserve source versions and when feasibility and outcome results were viewed.

Checklist

• Select a template by decision and design; distinguish assigned from observed treatment and causal effects from descriptive quantities.
• Map current applicable guidance items to sections, artifacts, completeness, and reviewers; reporting checklists are not protocol approval.
• Specify definitions, denominators, time anchors, assumptions, missingness, uncertainty, feasibility, and decision owners.
• Verify claim-level source support and preserve unresolved decisions; use only authorized non-sensitive inputs.
• Retain version history and obtain qualified human review before execution or external submission.

Citations

1. [1]Wang SV, Pottegård A, Crown W, et al. HARmonized Protocol Template to Enhance Reproducibility of hypothesis evaluating real-world evidence studies on treatment effects: a good practices report of a joint ISPE/ISPOR task force. Pharmacoepidemiology and Drug Safety. 2023;32(1):44-55.
2. [2]Wang SV, Pinheiro S, Hua W, et al. STaRT-RWE: structured template for planning and reporting on the implementation of real world evidence studies. BMJ. 2021;372:m4856.
3. [3]Benchimol EI, Smeeth L, Guttmann A, et al. The REporting of studies Conducted using Observational Routinely-collected health Data (RECORD) Statement. PLOS Medicine. 2015;12(10):e1001885.
4. [4]Moher D, Shamseer L, Clarke M, et al. Preferred reporting items for systematic review and meta-analysis protocols (PRISMA-P) 2015 statement. Systematic Reviews. 2015;4(1):1.
5. [5]Hoaglin DC, Hawkins N, Jansen JP, et al. Conducting indirect-treatment-comparison and network-meta-analysis studies: report of the ISPOR Task Force on Indirect Treatment Comparisons Good Research Practices: Part 2. Value in Health. 2011;14(4):429-437.
6. [6]Husereau D, Drummond M, Augustovski F, et al. Consolidated Health Economic Evaluation Reporting Standards (CHEERS) 2022 Explanation and Elaboration: A Report of the ISPOR CHEERS II Good Practices Task Force. Value in Health. 2022;25(1):10-31.
7. [7]Sullivan SD, Mauskopf JA, Augustovski F, et al. Budget impact analysis—principles of good practice: report of the ISPOR 2012 Budget Impact Analysis Good Practice II Task Force. Value in Health. 2014;17(1):5-14.

1. [8]Chan A-W, Boutron I, Hopewell S, et al. SPIRIT 2025 statement: Updated guideline for protocols of randomised trials. PLoS Medicine. 2025;22(4):e1004589.