🔬 Research
Modified Delphi Consensus Study Protocol Builder: Panel Eligibility and Recruitment, Round 1 Item Generation, 9 Point Rating Rounds, A Priori Consensus and Stopping Rules, Controlled Feedback Reports, and a Reporting Checklist
Plan a modified Delphi study you can defend to reviewers: panel eligibility by stakeholder group, Round 1 items from your evidence plus open suggestions, 9 point rating rounds, consensus and stopping rules fixed before data collection, controlled feedback reports with medians and distributions, attrition tracking, and a reporting checklist that maps each decision to the methods section.
0Reviews
Prompt
Act as a health services researcher who has run modified Delphi studies in REDCap and Qualtrics, sits on a steering group for consensus projects, and has seen papers rejected for consensus thresholds chosen after the data came in and for unreported attrition. Inputs: - The question the panel will answer and what the final list will be used for: [ResearchQuestion] - Stakeholder groups, eligibility criteria, and target number per group: [PanelPlan] - Where the starting items come from (scoping review, interviews, existing framework) and how many: [SeedItems] - Survey platform: [RatingPlatform] - Months available and any fixed deadline: [Timeline] - Ethics body and expected review type: [EthicsContext] - Output format: [Format] Generate: 1. A protocol summary: aim, why a modified Delphi fits (seeded items instead of a blank first round), and the steering group's role. 2. Panel section: eligibility per stakeholder group with checkable criteria, recruitment routes, a sampling note that there is no single correct panel size, and how group balance is protected when one group answers more. 3. Round 1 design: each seed item rated on a 9 point scale (1 to 3 not important, 4 to 6 important but not critical, 7 to 9 critical), an option for unable to score, and a free text box for new items. Two researchers code new items independently and the steering group decides which enter Round 2. 4. A consensus definition written before Round 1 opens, in exact percentages that the steering group chooses and justifies, for consensus in, consensus out, and no consensus. 5. Rounds 2 and 3: who is invited (only Round 1 completers or all), which items are re-rated, and the stopping rule (fixed maximum rounds, or no further items reaching consensus). 6. Controlled feedback reports per item: panel median, interquartile range, percent in each band, the panelist's own previous score, results by stakeholder group, and anonymized comments. 7. Attrition and bias controls: response rate per round per group, reminders schedule, anonymity between panelists, and how missing ratings are handled. 8. A RatingPlatform build note: instruments per round, piping of previous scores, and an export plan. 9. A reporting checklist mapping each decision to the methods section, with a reminder to follow the current consensus reporting guideline your target journal expects (such as ACCORD, or CREDES where requested). Constraints: - Every threshold must be labeled as a team choice set before data collection, never as a universal rule. - Do not invent prior results or response rates. No em dashes.
Instructions
Replace every [bracket] with your details before running. Works on ChatGPT, Claude, and Gemini.
Generated Output
This image was generated using the prompt above.
Examples
Example Input
ResearchQuestion: which competencies must be in a 12 week orientation for newly graduated nurses starting in rural emergency departments; the final list will shape a shared orientation curriculum for a regional health network PanelPlan: three groups: rural ED nurse educators, rural ED charge nurses, nurses with 1 to 3 years of rural ED experience; target 15 per group SeedItems: 42 competency statements from our scoping review RatingPlatform: REDCap at our university Timeline: 5 months, curriculum committee meets in March EthicsContext: university IRB, expecting an exempt determination for an anonymous expert survey Format: protocol sections, consensus table, feedback report mock, reporting checklist
Example Output
1. Protocol summary Aim: agree the competencies a 12 week orientation for new graduate nurses in rural EDs must include. A modified Delphi fits because 42 statements already exist from the scoping review, so Round 1 rates them instead of starting from a blank page. The steering group (two nurse educators, one ED medical director, one researcher) approves items and thresholds and does not rate. 2. Panel - Educators: currently responsible for ED orientation at a facility the network defines as rural, at least 2 years in the role. - Charge nurses: at least 2 years as charge in a rural ED. - Early career: 1 to 3 years in a rural ED after graduation. Recruitment: network education leads, the state ENA chapter list, and snowball referral with eligibility screening in REDCap. Target 15 per group; there is no single correct panel size, so the protocol states the target and reports what was achieved. Results are reported by group so the largest group does not drown out the others. 3. Round 1 Each statement rated 1 to 9 (1 to 3 not important, 4 to 6 important but not critical, 7 to 9 critical), plus unable to score. One free text box per domain for missing competencies. Two researchers code new items independently, meet to resolve differences, and the steering group decides which enter Round 2. 4. Consensus definition (set by the steering group before Round 1 opens) | Outcome | Rule (team choice) | | Consensus in | at least 75 percent rate 7 to 9 and under 15 percent rate 1 to 3 | | Consensus out | at least 75 percent rate 1 to 3 | | No consensus | anything else, re-rated in the next round | Rationale paragraph to be written by the steering group and dated before launch. Unable to score is excluded from the denominator and reported. 5. Rounds 2 and 3 Only Round 1 completers are invited. Re-rate no consensus items and new items. Stop after Round 3, or after Round 2 if no new item reaches either consensus rule. 6. Feedback report mock (one item) Item 17: Recognize and escalate sepsis using the facility screening tool Your Round 1 score: 6 Panel median 8, interquartile range 7 to 9 1 to 3: [n] percent | 4 to 6: [n] percent | 7 to 9: [n] percent By group: educators [median], charge nurses [median], early career [median] Comments: anonymized quotes Fill bracketed values from your REDCap export; none are known yet. 7. Attrition and bias Report invited, started, and completed per round per group. Reminders on day 5 and day 10, close on day 14. Panelists stay anonymous to each other. Missing ratings are excluded per item and counted. 8. REDCap build One instrument per round, survey queue by record, Round 1 scores piped into Round 2 with smart variables, data dictionary versioned per round, CSV export for analysis in R. 9. Reporting checklist - Steering group membership and role - Eligibility and recruitment per group, achieved panel per round - Seed item source and Round 1 additions - Rating scale and consensus rules with the date they were fixed - Stopping rule and rounds run - Feedback content shown to panelists - Attrition per round and handling of missing ratings - IRB determination and consent wording - Guideline: confirm the journal's expected consensus reporting checklist (such as ACCORD) and attach it.