Clinical trial feasibility with a cited reason for every country and site — and a forecast that moves with the plan
Every country and site ranked with a cited reason; move one and the forecast follows.
See one case, screen by screen ↓Software that helps a sponsor or CRO decide which countries and sites will recruit a study's patients, and forecast when enrollment will finish. Clinical Trial Feasibility adds six agents that read the protocol, CTMS site history, returned questionnaires, public trial registries and licensed patient counts, rank every country and site with a cited reason, and forecast last patient in from P10 to P90.
How to choose AI solutions for life sciences →
Updated
Before a Phase 2 or 3 study starts, the feasibility lead decides which countries and which sites will recruit its patients. Today that is a questionnaire round, a CTMS export and a spreadsheet. For a 480-participant Crohn's study, questionnaires go to 186 sites in 14 countries, 131 come back and 90 are usable — and someone has to read every one, pull each site's history, check the registries for competing trials and estimate the patient pool, country by country.
The reasons behind each choice end up in people's heads. Sites overstate the patients they can find, competing trials are checked by hand, the forecast is a single date with no range, and when a country manager asks “what if we open Brazil?” nobody can answer before the next meeting. ICH E6(R3) asks sponsors to select qualified investigators with adequate resources and to document it — the spreadsheet rarely says why.
Estimated split of working days for one Phase 3 study with about 130 returned questionnaires, by spreadsheet and with the solution. The 11-day target is calendar time, including waiting for sites and approvers. People still review, approve and sign.
Six specialist agents read the protocol, site history, questionnaires, registries and patient counts, then rank, cite and forecast; the study lead approves, the feasibility lead signs.
VLT-401 — veltrimab in moderate-to-severe Crohn's disease, Phase 3, 480 participants, target last patient in June 2028. Questionnaires went out on Sep 12 and closed on Oct 2. Here is what happens next, screen by screen, in the working solution.
Fourteen countries sit on the map, sized by patients allocated — the US with 140 and Poland with 78 as lead countries, Europe in its own close-up, Brazil and France held as back-up. Under the map, the forecast: most likely last patient in May 2028, 7 weeks before the June 2028 target, with a range from February to September 2028 across 64 primary sites.
“Each site enrolls at its own past rate and opens when its approval path allows; 15 of 64 primary sites open by the Feb 2027 first-patient target.”
Brazil ranks 13th of 14 with a score of 60. Its evidence opens beside the forecast, five factors each with a value and a source: past enrollment 1.70 a site a month from site history on 4 of 4 sites, 11,500 eligible a year from real-world counts, 1 same-population trial of 6 recruiting, a 27-week start-up with 150 days of approval, and 4 questionnaires with claims consistent.
“Three strong sites (2.0–2.6 participants a month in NXL-118) and a large pool, held back only by approval: about 150 days for ANVISA and national ethics, so its sites open in April 2027, after first patient in.”
Lena switches Brazil from back-up to core. Its three ready sites open as primary and take 36 participants from the US, Canada and Italy. The forecast is recalculated from each site's own history: most likely last patient in March 2028 instead of May, optimistic January, cautious July, on 67 primary sites.
“Back-up → Core · 3 back-up sites open as primary and take 36 participants (20 from United States, 10 from Canada, 6 from Italy).”
The change goes to Sam Patel, the study lead, with the forecast and the evidence. Brazil's page shows the rest: the patient funnel from 98,900 living with Crohn's to 11,500 who meet the endoscopic score, one same-population competitor (OAK-21) among 6 Crohn's studies recruiting — the others are in different populations and are not counted against sites, and the approval path — ANVISA review about 90 days, national ethics about 60, import licence about 4 weeks.
“Proposed as core on the map: three sites open in April 2027 and carry 36 participants. Sent to Sam Patel for approval.”
Every site that returned a usable questionnaire is scored on six weighted factors: past enrollment 30%, patient pool 20%, start-up speed 15%, competition 15%, questionnaire quality 10%, representation 10%. Each row shows the site's rate a month, start-up weeks, competing trials within 25 km and its claim against history — 23 sites claim more than 3× what they screened. Move a weight and the ranking and the live forecast follow.
“Move a weight — agents re-propose inside each country's allocation; decisions made by people stay.”
Tom asks to make Universitätsklinikum Rheinhafen in Duisburg a primary site. The cited rationale says why it ranks #85 of 90: in VLT-208 it enrolled 3 participants against a plan of 10 in 12 months, start-up took 29 weeks, and its questionnaire claims about 80 eligible a year where it screened 14 — 5.7× its history, so it is counted at 28. Four Crohn's trials in the same patient group recruit within 25 km, one at the hospital itself.
“Please make Rheinhafen a primary site. Prof. Albers leads the national IBD society and other sites follow his lead.”
The agents propose; Lena decides. She keeps Rheinhafen as back-up for Germany — it opens if a primary German site falls behind after month 6 — and the reason goes to the country manager and is filed with the list. Tom reads it and signs Germany, the UK and France.
“Keep as back-up: 3 of 10 enrolled in VLT-208, 29-week start-up and four competing trials nearby. Opens if a German primary site falls behind after month 6.”
The site list shows each approval: the agents' proposal, five of five country managers, the study lead's allocation. Lena signs VLT-401 site list v3 with her password and chooses the meaning — “I approve this site list and the rationale for each site” or “I have reviewed this site list”.
The site list, the country allocation, the P10–P90 forecast and the approval record are filed to the trial master file under site selection, with a cited rationale for each of the 76 primary and back-up sites. The people's own changes stay on the record — Omar Haddad's and Priya Raman's moves to back-up, each with its reason.
“Signed · 76 site rationales filed to the trial master file.”
Amendment 1 lowers the endoscopic entry score to SES-CD ≥ 4 (≥ 3 isolated ileal) and allows up to four prior advanced therapies. The agents re-read the criteria, recount the pool — up 14% overall — and re-score all 90 sites in 3 min 12 s. Three proposals change, each shown with its reason, and nothing reaches the plan until Lena applies or discards it.
Protocol reader: “2 criteria changed · thresholds copied with section citations.”
The same study, seen by the five people who shape its site list — what their feasibility round looked like, and what it looks like now.
Six specialist agents read the protocol, site history, questionnaires, registries and patient counts, then rank, cite and forecast; the study lead approves, the feasibility lead signs.
Reads the synopsis or amendment and extracts the population, every inclusion and exclusion criterion as a structured rule, procedures that need site equipment such as ileocolonoscopy, visit burden and target size, citing the protocol section for each.
Applies the criteria, in protocol order, to licensed real-world counts per country and region, and keeps the funnel from diagnosed to moderate–severe to advanced-therapy failure to the endoscopic score — eligible patients a year.
Reads public registries for recruiting studies, matches them on condition, phase, line of therapy and age, and marks each as same or different population — per country and within 25 km of each site.
Reads the CTMS: enrolled against planned in similar studies, months recruiting, screen failure, start-up weeks split into contract, ethics and activation, data quality and inspections.
Reads every returned questionnaire — portal, PDF or email — with its question numbers, checks completeness, compares the eligible-patient claim with what the site screened, and drafts plain follow-up questions.
Scores six factors 0–100, combines them with the study's weights, writes a rationale where every sentence cites its source, proposes primary, back-up or not selected within each country's allocation, and forecasts last patient in from 2,000 simulations.
Signs the list and allocation. The agents propose; a named person decides.
Ask in plain words — or tell it what to change. Every answer points to the site history, questionnaire or registry entry it came from.
Why is Rheinhafen only a back-up?
Universitätsklinikum Rheinhafen ranks #85 of 90. In VLT-208 it enrolled 3 of 10 planned in 12 months. The questionnaire claims 80 eligible a year — 5.7× what it screened; we count 28. Four Crohn's trials recruit within 25 km, one at the hospital itself. Its start-up took 29 weeks, about 5 weeks slower than the German median of 24. Tom Becker asked to make it primary — that decision is yours.
What if Brazil moves to core?
Brazil is back-up only because of approval: about 150 days for ANVISA and national ethics, so its sites open in April 2027, after first patient in elsewhere. Centro Mineiro de DII enrolled 31 in 12 months on NXL-118. Moving Brazil to core opens its three sites with 36 participants and moves the most likely last patient in from May 2028 to March 2028. France stays back-up. Sam Patel approves any allocation change.
Which sites overstate their patient numbers?
23 sites claim more than 3× the patients they screened per year on their last Northwind study. Each is counted at 2× its history until the site confirms, and follow-up questions are drafted for you to send.
When will we finish enrolling?
With the 64 primary sites, the last patient is most likely in May 2028 — 7 weeks before the June 2028 target. Optimistic February 2028, cautious September 2028. The range comes from 2,000 simulations of when each site opens and how fast it enrolls, based on its own history and start-up.
13 screens from the working solution, on its sample data. Pick one to see it large.
How sites are scored, who approves and where the evidence comes from are settings — every change is recorded in the audit trail.
| Setting | Default | Choose from |
|---|---|---|
| Default factor weights | Past enrollment 30% · patient pool 20% · start-up 15% · competition 15% · questionnaire 10% · representation 10% | Set each weight; presets Balanced · Proven sites · Fast start-up · Representation |
| Count questionnaire claims at most 2× screening history | On | On · Off |
| Radius for competing trials | 25 km | 15 km · 25 km · 50 km |
| Ask for follow-up below this questionnaire completeness | 90% | 80% · 90% · 100% |
| Representation counts in the score | On — supports the study's diversity plan | On · Off (sets its weight to 0) |
| Re-score weekly when registries change | Mondays 06:00 · told when a site moves more than 5 places | On · Off |
| Country allocation approver | Sam Patel · Study lead | Sam Patel · Dana Okafor |
| Final site list signer | Lena Ortiz · Feasibility lead | Lena Ortiz · Sam Patel |
Every figure is labelled: a target the solution is built to, an estimate, a typical published result, or a proven one.
“demo” = seen in the working solution, on its sample study data · “target” = the design goal, measured in the live solution · “estimated” = our estimate · “typical” = published figures (Tufts CSDD — about 11% of activated sites enroll no one; enrollment-barriers review, 2020 — about 80% of trials miss their enrollment timeline). ICH E6(R3) is named as context. People, companies, studies, sites and competing trials named on this page are fictional — characters and sample data in the working solution.
Software that helps a sponsor or CRO decide which countries and sites will recruit a study's patients, and forecast when enrollment will finish. Clinical Trial Feasibility adds six agents that read the protocol, CTMS site history, returned questionnaires, public trial registries and licensed patient counts, rank every country and site with a cited reason, and forecast last patient in from P10 to P90.
The questionnaire reader compares each site's eligible-patient claim with what the site actually screened on past studies and reports the ratio. A claim is counted at most 2× the site's history until the site confirms it, and follow-up questions are drafted for sites with missing answers or claims far above their history — a person sends them.
It runs 2,000 simulations in which each site opens when its approval path allows and enrolls at its own past rate, and shows the optimistic (P10), most likely (P50) and cautious (P90) last patient in. Move a country between lead, core and back-up, or change a weight, and the forecast is recalculated on the spot.
Yes. The competing-trial scanner reads public registries for recruiting studies, marks each as same or different population with the reason, and counts same-population studies per country and within the radius you set — 25 km by default. Different-population studies never count against a site.
No. Eligible patients a year come from licensed real-world counts, with a minimum cell size of 11, and the criteria applied in protocol order. Every number shows its data cut.
Yes. The agents propose; they never decide. Country managers review their sites and can swap or add one with a reason, the study lead approves the country allocation, and the feasibility lead decides each site and signs the final list, which is filed to the trial master file with every rationale.
Add the amendment and re-run. The agents re-read the criteria, recount the patient pool, re-score every site and show what changes — eligible patients by country, site proposals and last patient in. Nothing reaches the plan until the feasibility lead applies it.
The Agentic Solution Engine builds and deploys it from your requirements and documents — your feasibility questionnaire, CTMS history and a past study's protocol — and it goes live once every quality gate has passed. We will walk you through it on one of your own studies first.
A checked first-draft protocol in days, in your approved language.
1-min demoeTMF Quality CheckAn inspection-ready trial master file every day, each site scored on what is due today.
1-min demoClinical Study Report AuthoringResults drafted within days of database lock, linked to tables.
1-min demoWe'll run Clinical Trial Feasibility on a past study of yours — its protocol, questionnaires and site history.