Pilot study report¶
AI agents create yamaa specifications and derive ADaM datasets from SDTM data in pilot submission packages. AI agents also check consistency between the datasets and documents in those packages. This report summarizes the findings.
- Studies
- 3 / 3validated
- ADaM datasets
- 20 / 20100% matched
- Columns
- 847 / 847100% matched
- Cells
- 13.7M / 13.7M100% matched
- Review items
- 34open questions
Studies¶
| Study | CDISC Pilot 01 | Submission Pilot 3 | Submission Pilot 5 |
|---|---|---|---|
| Study information | |||
| Description | The original CDISC SDTM/ADaM pilot study, with ten active derivations and official reference datasets. | Five ADaM datasets from the R Consortium's Pilot 3 FDA submission, derived from the staged SDTM data. | The Dataset-JSON pilot: SDTM converted from Dataset-JSON 1.1 and five official ADaM reference datasets. |
| Source | cdisc-org/sdtm-adam-pilot-project | RConsortium/submissions-pilot3-adam | RConsortium/submissions-pilot5-datasetjson |
| Documents | define-adam.xml, define-sdtm.xml, SAP.pdf, dataguide.pdf | define-adam.xml, define-sdtm.xml, adam-pilot-3.xlsx, adrg.pdf | define-adam.xml, define-sdtm.xml, adam-pilot-5.xlsx, adrg.pdf |
| Subjects | 306 | 306 | 306 |
| SDTM | |||
| SDTM inputs | 10 of 22 staged domainsDM, EX, VS, SV, DS, QS, SC, MH, AE, LB | 11 of 22 staged domainsDM, DS, EX, QS, SV, VS, SC, MH, LB, SUPPLB, AE | 11 of 21 staged domainsDM, EX, VS, DS, SC, MH, SV, QS, LB, SUPPLB, AE |
| Define-XML version | 1.0.0 | 1.0.0 | 1.0.0 |
| ADaM | |||
| ADaM datasets matched | 10 / 10 (100%) | 5 / 5 (100%) | 5 / 5 (100%) |
| Columns matched | 415 / 415 (100%) | 216 / 216 (100%) | 216 / 216 (100%) |
| Cells matched | 9.1M / 9.1M (100%) | 2.3M / 2.3M (100%) | 2.3M / 2.3M (100%) |
| Define-XML version | 1.0.0Generated: 2.0.0 | 2.0.0 | 2.0.0 |
| Define-XML match | Different | Matched | Matched |
Versions refer to the published Define-XML. ADaM matching compares generated metadata with the published source. Not compared means the study has no Define-XML comparison result.
Dataset results¶
| Dataset | Description | CDISC Pilot 01 | Submission Pilot 3 | Submission Pilot 5 |
|---|---|---|---|---|
| ADSL | Subject-Level Analysis Dataset | Matched254 × 4829 issues | Matched254 × 491 issue | Matched254 × 491 issue |
| ADAE | Adverse Events Analysis Dataset | Matched1,191 × 551 issue | Matched1,191 × 551 issue | Matched1,191 × 551 issue |
| ADLBC | Analysis Dataset Lab Blood Chemistry | Matched74,264 × 460 issues | Matched37,132 × 460 issues | Matched37,132 × 460 issues |
| ADTTE | AE Time To 1st Derm. Event Analysis | Matched254 × 260 issues | Matched254 × 260 issues | Matched254 × 260 issues |
| ADADAS | ADAS-Cog Analysis | - | Matched12,463 × 400 issues | Matched12,463 × 400 issues |
| ADLBH | Analysis Dataset Lab Hematology | Matched49,932 × 460 issues | - | - |
| ADLBHY | Analysis Dataset Lab Hy's Law | Matched9,954 × 430 issues | - | - |
| ADQSADAS | ADAS-Cog Analysis | Matched12,463 × 400 issues | - | - |
| ADQSCIBC | CIBIC+ Analysis | Matched730 × 360 issues | - | - |
| ADQSNPIX | NPI-X Item Analysis Data | Matched31,140 × 410 issues | - | - |
| ADVS | Vital Signs Analysis Dataset | Matched32,139 × 340 issues | - | - |
Status with rows × columns of the yamaa output. Matched: the study comparator found the output equal to the official ADaM dataset, labels included, under that study's comparison policy. A dash means the dataset is not part of that study.
Issue badges count distinct consistency review items for each study and dataset, including documentation gaps and questions awaiting human review. Each issue counts once even when it has multiple supporting checks. Issue counts are separate from ADaM reference agreement. Select a nonzero badge to view the issues.