Clinical study report writing from the locked outputs, every number linked to its table cell
Results sections and patient narratives are drafted within days of database lock, every number linked to its table.
See one case, screen by screen ↓The database locks, biostatistics delivers hundreds of tables, listings and figures, and the clock on the clinical study report starts. The medical writer has to turn them into ICH E3 results sections — disposition, baseline, efficacy, safety, conclusions — and write a narrative for every death, serious adverse event, discontinuation and event of special interest.
Most of that time is not writing. It is copying numbers from RTF tables into the draft by hand, piecing each narrative together from the adverse event, dosing, medical history, concomitant medication and laboratory listings and the SAE report, then a QC pass that checks every number again. When biostatistics re-issues a listing, someone has to find every sentence that quotes it.
Estimated split of the 68 days a first full draft took by hand, in the categories the solution’s dashboard tracks, and with the solution.
Five specialist agents read, write and check every section and narrative; a biostatistician and a medical writer sign.
VLT-302, a Phase 3 study of Veltrimab 150 mg against placebo in moderate-to-severe plaque psoriasis, locked on Oct 2. Here is what happens next, screen by screen, in the working solution.
Maya opens the solution to 412 outputs received, 32 narratives waiting for her review of the 53 drafted at lock, and the first full draft due Oct 16. The results sections are ready to draft, and the fatal myocardial infarction narrative is back with a change the medical monitor asked for.
Agents at work: “Read 412 outputs from the locked database and indexed 9,840 table cells.”
186 tables, 142 listings and 84 figures from the locked database, each with its population and its program run. The values are kept exactly as printed — never rounded or reformatted — because this is the only place a number in the report may come from.
“Tables, listings and figures from the VLT-302 locked database — the only place a number in the report may come from.”
The agents read the locked outputs and match the endpoints to the statistical analysis plan: co-primary PASI 75 and sPGA 0/1 at Week 16, non-responder imputation, CMH stratified. The results writer drafts 8 sections in the ICH E3 template while the number verifier checks every number as it lands.
“Number verifier checks every number — 79 numbers traced to their table cells · 79 match.”
“Veltrimab 150 mg was superior to placebo on both co-primary endpoints at Week 16.” 62.4% reached PASI 75 against 5.1% on placebo, a difference of 57.3 percentage points. Point at any number and its cell opens: Table 14.2.1.1, PASI 75 responders, Veltrimab 150 mg (N=428), 267 (62.4) — matches the text.
“19 numbers · all 19 linked to a table cell — point at any number to see its source.”
Every number in the section on one list: what the text says, the source cell by row and column, the value in the cell, and the check. The confidence interval, the p-value and the participants who stopped before Week 16 are traced the same way as the headline result. If one does not match, the section cannot be approved.
“19 numbers · 19 match their table cell · 0 typed by hand.”
Omar asks for the stratification factors next to the CMH p-value, as in SAP Section 9.4. The results writer adds “stratified by body weight and prior biologic use” to the Table 14.2.1.1 footnote reference and proposes it as version 0.2.
Narratives for ICH E3 Sections 12.3.2 and 14.3.3: 38 serious adverse events including 1 death, 9 participants who stopped because of an adverse event, and 6 events of special interest. Each row shows the participant, event, arm, onset day, seriousness and where it stands — 11 approved, 2 waiting on a site answer.
A 58-year-old man on Veltrimab 150 mg presented on Day 61 with a three-day history of redness, swelling and pain of the left lower leg and a temperature of 38.6 °C. He was hospitalized, treated with IV cefazolin then oral cefalexin, and discharged when the event resolved on Day 68. The listings and the SAE report sit beside the text; every ICH E3 12.3.2 element is ticked.
“14 facts checked against the listings · all match.”
Maya signs as Dr. Maya Chen · Lead medical writer, with the meaning “Approved — medical writing review” and her password. The narrative locks as version 1.0, and the history keeps every step: drafted from listings 16.2.4–16.2.8 and the SAE report, 14 facts checked, re-checked after the Listing 16.2.7.1 re-issue, approved.
“Your signature is recorded with your name, date, time and meaning, and kept in the audit trail.”
Narrative 302-0207-0119, acute cholecystitis, has no discharge date in the source. The narrative writer drafted a query to site 0207 instead of filling the gap, and approval stays on hold until the site answers. The narrative is re-drafted and checked again the moment the answer arrives.
“1 fact is missing in the source · Discharge date missing in source — query sent to site 0207.”
The same report, seen by the four people who carry it — what their weeks looked like, and what they look like now.
Five specialist agents read, write and check every section and narrative; a biostatistician and a medical writer sign.
Reads every table, listing and figure from the locked database and turns each one into addressable cells — row, column, population and program run.
Drafts the ICH E3 results sections — disposition, baseline, efficacy and safety — in the report template, following the SAP for endpoint names, populations and analysis methods.
Writes patient narratives for deaths, serious events, discontinuations and events of special interest from the participant listings and SAE reports, with the ICH E3 12.3.2 elements.
Checks every number in every section and narrative against its linked cell — value, rounding, population and column — and reports mismatches with the expected value.
Confirms every required ICH E3 heading is present, every “Table x” and “Section y” cross-reference resolves, and the house style is followed.
Sign efficacy and narratives. The agents propose; a named person decides.
Writers, statisticians and the medical monitor can ask about the report in plain words — or tell it what to change. Every answer is cited.
Where does 62.4% come from?
62.4% is the PASI 75 response at Week 16 with Veltrimab 150 mg — 267 of 428 participants. It comes from Table 14.2.1.1, row “PASI 75 responders”, column “Veltrimab 150 mg (N=428)”, full analysis set with missing data counted as non-response. Program t_eff_prim.sas, run Oct 2 at 18:42. It is quoted in sections 11.4.1 and 13, and the number verifier confirmed both.
Which narratives are waiting on a site?
Two: 302-0207-0119 (acute cholecystitis — discharge date missing) and 302-0618-0026 (pulmonary embolism — CT report not yet received). Both queries went out on Oct 3; the narrative writer will re-draft as soon as the site replies.
Add a rule: flag any narrative without a hospital discharge date
Done. A new rule now checks every serious-event narrative that involves a hospital stay: if the discharge date is not in the listings or the SAE report, the narrative is flagged and a query is drafted for the site. It applies to all 38 serious-event narratives — 1 is flagged today (302-0207-0119).
Summarize safety for the medical monitor
To Week 16, adverse events were reported in 57.9% of Veltrimab and 52.3% of placebo participants. Serious events: 6.1% versus 5.6%; serious infections 1.4% versus 0.9%. One death — a fatal myocardial infarction on Day 97, adjudicated as cardiovascular death and assessed as not related. Injection site erythema was the only event clearly more frequent with Veltrimab (3.3% versus 0.9%).
13 screens from the working solution, on its sample data. Pick one to see it large.
What differs between programmes and sponsors is a setting, not a project.
| Setting | Default | Choose from |
|---|---|---|
| Report template | ICH E3 house template v4.2 | ICH E3 house template v4.2 · ICH E3 abbreviated report v2.0 · Phase 1 report template v1.3 |
| Percentages quoted from a table | As in the table (one decimal) | As in the table (one decimal) · Whole numbers in the summary only |
| Writing style | House style guide 2026 | House style guide 2026 · Journal style (AMA 11th) |
| Efficacy sections are approved by | Omar Haddad · Biostatistics | Omar Haddad · Biostatistics · Dana Okafor · Biostatistics |
| Safety sections are approved by | Dr. Sam Patel · Medical monitor | Dr. Sam Patel · Medical monitor · Dr. Maya Chen · Medical writing |
| Patient narratives are approved by | Dr. Maya Chen · Medical writing | Dr. Maya Chen · Medical writing · Dr. Sam Patel · Medical monitor |
| Final report is signed by | Lena Ortiz · Clinical lead | Lena Ortiz · Clinical lead · Dr. Maya Chen · Medical writing |
| Send safety sections to the medical monitor before medical writing | Off | On · Off |
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 · by hand = the same team’s last six reports · report structure follows ICH E3. People, companies and products named on this page are fictional — characters and sample data in the working solution.
Software that helps write the clinical study report after database lock — the ICH E3 results sections and the patient narratives — from the study’s tables, listings and figures. The CSR Writer adds agents that read the locked outputs, draft the sections and narratives in your template, and check every number against its table cell before anyone signs.
Every number the results writer quotes is linked to a cell in the locked outputs — table, row, column and program run. The number verifier checks each one for value, rounding, population and column, and a section or narrative cannot be approved while any number lacks a source cell or does not match.
The narrative writer drafts a narrative for every death, serious adverse event, discontinuation due to an adverse event and event of special interest, from the participant listings and the SAE report. Each fact is cited to its listing row or report, the ICH E3 12.3.2 elements are checked, and a missing fact becomes a site query instead of a guess.
Every section and narrative that quotes it is re-checked and, if needed, re-drafted for the writer. When Listing 16.2.7.1 was re-issued with two corrected adverse event end dates, the 3 narratives that quote those participants were re-checked and all facts still matched.
No. The results writer follows the SAP for endpoint names, populations and methods, quotes only numbers it can link to a table cell and never interprets beyond what the tables show. Your writers and reviewers edit and sign every section, including the discussion and overall conclusions.
Yes. Agents draft, check and propose — they never approve. Efficacy sections are signed by a biostatistician, safety sections by the medical monitor, narratives by the medical writer and the final report by the clinical lead, each with an electronic signature that records its meaning, date and time.
Yes. The report template, rounding of percentages and writing style are settings, and the draft exports to Word in your template with each number link kept as a comment, so reviewers can check it outside the solution too.
The Agentic Solution Engine builds and deploys it from your requirements — your CSR template, style guide, SAP and a set of locked outputs — and it goes live once every quality gate has passed. We will walk you through it on one of your own studies first.
A trial synopsis becomes a checked first-draft protocol in days, in your own approved language.
1-min filmTMF CheckEvery trial document is read, filed in the right place and checked, so the file is inspection-ready every day.
1-min filmProtocol Risk ReviewEvery draft protocol checked against past amendments, so avoidable changes are fixed before the committee meets.
1-min filmWe’ll run the CSR Writer on the tables, listings and figures of one of your locked studies.