Compare laboratory results with baseline with ADaMIG 1.1

Review ask

As a clinical trial statistician or programmer, answer three short questions in Your review: the task, the inputs and outputs, and the AI-assisted review. Agreeing with all three approves this benchmark; disagreeing with any needs a comment. Propose a fix with the Edit button on any source file, or add it to your comments.

We suggest spending no more than 5 minutes on a review. The other tabs beside Your review are background for assessment, not under review.

Summary

EditUnder reviewWhat this benchmark means

README.md

Public entries: Python and R. Passing coverage requires an installed inventory.

Goal: Carry the flagged baseline value and compute the change for each laboratory result.

Input: SDTM laboratory results and subject-level treatment dates and names.

Variables:

PARAMCD and PARAM identify alanine aminotransferase.
ADT is the collection date and ADY is its day relative to first treatment, with no day zero.
TRT01A carries the subject's treatment.
AVAL and AVALU retain the standardized result and its units.
ABLFL retains the baseline flag.
BASE repeats the flagged value for the subject and parameter.
CHG is the result minus baseline; it is absent when baseline is absent.

Note: project.yaml declares ADaMIG 1.1. The data-definition document records that guide and points to the SAS Transport version 5 dataset.

YAML specification

1 spec file

spec.yaml

Edit205 lines

1yamaa: '1.0'2type: spec3model: ADaM4domain: ADLB5keys:6- STUDYID7- USUBJID8- PARAMCD9- ADT10input:11  LB:12    path: input/lb.csv13    types:14      LBDTC: date15      LBSTRESN: float16  ADSL:17    path: input/adsl.csv18    types:19      TRTSDT: date20    key:21    - STUDYID22    - USUBJID23base: LB2425output:26  path: adlb.csv27  columns:28  - STUDYID29  - USUBJID30  - PARAMCD31  - PARAM32  - ADT33  - TRT01A34  - ADY35  - AVAL36  - AVALU37  - ABLFL38  - BASE39  - CHG4041columns:42- name: STUDYID43  type: str44  label: Study Identifier45  derivation: LB.STUDYID46  submission:47    core: Req48    mandatory: true49    length: 8050    origins:51    - type: Predecessor52      description: LB.STUDYID5354- name: USUBJID55  type: str56  label: Unique Subject Identifier57  derivation: LB.USUBJID58  submission:59    core: Req60    mandatory: true61    length: 8062    origins:63    - type: Predecessor64      description: LB.USUBJID6566- name: PARAMCD67  type: str68  label: Parameter Code69  derivation: LB.LBTESTCD70  submission:71    core: Req72    mandatory: true73    length: 8074    origins:75    - type: Predecessor76      description: LB.LBTESTCD7778- name: PARAM79  type: str80  label: Parameter81  derivation: '''Alanine Aminotransferase'''82  submission:83    core: Req84    mandatory: true85    length: 8086    origins:87    - type: Assigned8889- name: ADT90  type: date91  label: Analysis Date92  derivation: LB.LBDTC93  submission:94    core: Cond95    mandatory: true96    origins:97    - type: Predecessor98      description: LB.LBDTC99100- name: TRT01A101  type: str102  label: Actual Treatment for Period 01103  derivation: ADSL.TRT01A104  submission:105    core: Cond106    mandatory: true107    length: 80108    origins:109    - type: Predecessor110      description: ADSL.TRT01A111112- name: TRTSDT113  type: date114  derivation: ADSL.TRTSDT115116- name: ADY117  type: int118  label: Analysis Relative Day119  derivation:120    study_day:121      source: ADT122      reference: TRTSDT123  submission:124    core: Perm125    mandatory: true126    length: 8127    origins:128    - type: Derived129    method: Study day of ADT relative to TRTSDT, with no day zero.130131- name: AVAL132  type: float133  label: Analysis Value134  derivation: LB.LBSTRESN135  submission:136    core: Cond137    mandatory: true138    length: 8139    significant_digits: 1140    origins:141    - type: Predecessor142      description: LB.LBSTRESN143144- name: AVALU145  type: str146  label: Analysis Value Unit147  derivation: LB.LBSTRESU148  submission:149    core: Perm150    mandatory: false151    length: 80152    origins:153    - type: Predecessor154      description: LB.LBSTRESU155156- name: ABLFL157  type: str158  label: Baseline Record Flag159  derivation: LB.LBBLFL160  submission:161    core: Cond162    mandatory: false163    length: 80164    origins:165    - type: Predecessor166      description: LB.LBBLFL167168- name: BASE169  type: float170  label: Baseline Value171  derivation:172    aggregate:173      filter: ABLFL = 'Y'174      group_by:175      - STUDYID176      - USUBJID177      - PARAMCD178      expr: ONLY(AVAL)179  submission:180    core: Cond181    mandatory: false182    length: 8183    significant_digits: 1184    origins:185    - type: Derived186    method: Repeat the flagged baseline value within subject and parameter.187188- name: CHG189  type: float190  label: Change from Baseline191  derivation: AVAL - BASE192  submission:193    core: Cond194    mandatory: false195    length: 8196    significant_digits: 1197    origins:198    - type: Derived199    method: Analysis value minus baseline; missing when no baseline exists.200201submission:202  label: Laboratory Analysis Dataset203  class: BASIC DATA STRUCTURE204  structure: One record per subject per parameter per date205  repeating: true

Inputs

Under review2 source files

input/adsl.csv

Edit2 rows

input/adsl.csv
STUDYID	USUBJID	TRTSDT	TRT01A
CATH		2025-01-08	DRUG
CATH		2025-01-08	PLACEBO

input/lb.csv

Edit3 rows

input/lb.csv
STUDYID	LBTESTCD	LBDTC	LBSTRESN	LBSTRESU	LBBLFL
CATH	ALT	2025-01-07	10	U/L	Y
CATH	ALT	2025-01-09	15	U/L	—
CATH	ALT	2025-01-09	20	U/L	—

Expected output

Under review3 expected rows

expected/adlb.csv

Edit3 rows

expected/adlb.csv
STUDYID	PARAMCD	PARAM	ADT	TRT01A	ADY	AVAL	AVALU	ABLFL	BASE	CHG
CATH	ALT	Alanine Aminotransferase	2025-01-07	DRUG	-1	10	U/L	Y	10	0
CATH	ALT	Alanine Aminotransferase	2025-01-09	DRUG	2	15	U/L	—	10	5
CATH	ALT	Alanine Aminotransferase	2025-01-09	PLACEBO	2	20	U/L	—	—	—

expected/define.xml

EditDefine-XML

Define-XML 2.1.11: CATH

Laboratory Analysis Dataset; CATH-01; ADaMIG 1.1

Datasets
Dataset	Description	Class	Structure	Purpose	Keys	Documentation	Location
ADLB	Laboratory Analysis Dataset	BASIC DATA STRUCTURE	One record per subject per parameter per date	Analysis	STUDYID, USUBJID, PARAMCD, ADT		adlb.xpt

ADLB

ADLB variables
Variable	Label / Description	Type	Length or Display Format	Origin / Source / Method / Comment
STUDYID	Study Identifier	text	4	Predecessor; LB.STUDYID
USUBJID	Unique Subject Identifier	text	7	Predecessor; LB.USUBJID
PARAMCD	Parameter Code	text	3	Predecessor; LB.LBTESTCD
PARAM	Parameter	text	24	Assigned; Sponsor
ADT	Analysis Date	integer	DATE9.	Predecessor; LB.LBDTC
TRT01A	Actual Treatment for Period 01	text	7	Predecessor; ADSL.TRT01A
ADY	Analysis Relative Day	integer	8	Derived; Sponsor Study day of ADT relative to TRTSDT, with no day zero.
AVAL	Analysis Value	float	8	Predecessor; LB.LBSTRESN
AVALU	Analysis Value Unit	text	3	Predecessor; LB.LBSTRESU
ABLFL	Baseline Record Flag	text	1	Predecessor; LB.LBBLFL
BASE	Baseline Value	float	8	Derived; Sponsor Repeat the flagged baseline value within subject and parameter.
CHG	Change from Baseline	float	8	Derived; Sponsor Analysis value minus baseline; missing when no baseline exists.

Original source

<?xml version="1.0" encoding="UTF-8"?>
<ODM xmlns="http://www.cdisc.org/ns/odm/v1.3" xmlns:def="http://www.cdisc.org/ns/def/v2.1" xmlns:xlink="http://www.w3.org/1999/xlink" ODMVersion="1.3.2" FileType="Snapshot" FileOID="CATH.adam.Define-XML_2.1" CreationDateTime="2026-09-11T00:00:00" SourceSystem="yamaa" SourceSystemVersion="1.0" def:Context="Submission">
  <Study OID="STDY.CATH">
    <GlobalVariables>
      <StudyName>CATH</StudyName>
      <StudyDescription>Laboratory Analysis Dataset</StudyDescription>
      <ProtocolName>CATH-01</ProtocolName>
    </GlobalVariables>
    <MetaDataVersion OID="MDV.CATH.adam" Name="CATH adam metadata" def:DefineVersion="2.1.11">
      <def:Standards>
        <def:Standard OID="STD.ADaMIG" Name="ADaMIG" Type="IG" Version="1.1" Status="Final"/>
      </def:Standards>
      <ItemGroupDef OID="IG.ADLB" Name="ADLB" Purpose="Analysis" SASDatasetName="ADLB" Repeating="Yes" IsReferenceData="No" def:Structure="One record per subject per parameter per date" def:ArchiveLocationID="LF.ADLB" def:StandardOID="STD.ADaMIG">
        <Description>
          <TranslatedText xml:lang="en">Laboratory Analysis Dataset</TranslatedText>
        </Description>
        <ItemRef ItemOID="IT.ADLB.STUDYID" OrderNumber="1" Mandatory="Yes" KeySequence="1"/>
        <ItemRef ItemOID="IT.ADLB.USUBJID" OrderNumber="2" Mandatory="Yes" KeySequence="2"/>
        <ItemRef ItemOID="IT.ADLB.PARAMCD" OrderNumber="3" Mandatory="Yes" KeySequence="3"/>
        <ItemRef ItemOID="IT.ADLB.PARAM" OrderNumber="4" Mandatory="Yes"/>
        <ItemRef ItemOID="IT.ADLB.ADT" OrderNumber="5" Mandatory="Yes" KeySequence="4"/>
        <ItemRef ItemOID="IT.ADLB.TRT01A" OrderNumber="6" Mandatory="Yes"/>
        <ItemRef ItemOID="IT.ADLB.ADY" OrderNumber="7" Mandatory="Yes" MethodOID="MT.ADLB.ADY"/>
        <ItemRef ItemOID="IT.ADLB.AVAL" OrderNumber="8" Mandatory="Yes"/>
        <ItemRef ItemOID="IT.ADLB.AVALU" OrderNumber="9" Mandatory="No"/>
        <ItemRef ItemOID="IT.ADLB.ABLFL" OrderNumber="10" Mandatory="No"/>
        <ItemRef ItemOID="IT.ADLB.BASE" OrderNumber="11" Mandatory="No" MethodOID="MT.ADLB.BASE"/>
        <ItemRef ItemOID="IT.ADLB.CHG" OrderNumber="12" Mandatory="No" MethodOID="MT.ADLB.CHG"/>
        <def:Class Name="BASIC DATA STRUCTURE"/>
        <def:leaf ID="LF.ADLB" xlink:href="adlb.xpt">
          <def:title>adlb.xpt</def:title>
        </def:leaf>
      </ItemGroupDef>
      <ItemDef OID="IT.ADLB.STUDYID" Name="STUDYID" DataType="text" Length="4" SASFieldName="STUDYID">
        <Description>
          <TranslatedText xml:lang="en">Study Identifier</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.STUDYID</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.USUBJID" Name="USUBJID" DataType="text" Length="7" SASFieldName="USUBJID">
        <Description>
          <TranslatedText xml:lang="en">Unique Subject Identifier</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.USUBJID</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.PARAMCD" Name="PARAMCD" DataType="text" Length="3" SASFieldName="PARAMCD">
        <Description>
          <TranslatedText xml:lang="en">Parameter Code</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.LBTESTCD</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.PARAM" Name="PARAM" DataType="text" Length="24" SASFieldName="PARAM">
        <Description>
          <TranslatedText xml:lang="en">Parameter</TranslatedText>
        </Description>
        <def:Origin Type="Assigned" Source="Sponsor"/>
      </ItemDef>
      <ItemDef OID="IT.ADLB.ADT" Name="ADT" DataType="integer" Length="8" SASFieldName="ADT" def:DisplayFormat="DATE9.">
        <Description>
          <TranslatedText xml:lang="en">Analysis Date</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.LBDTC</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.TRT01A" Name="TRT01A" DataType="text" Length="7" SASFieldName="TRT01A">
        <Description>
          <TranslatedText xml:lang="en">Actual Treatment for Period 01</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">ADSL.TRT01A</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.ADY" Name="ADY" DataType="integer" Length="8" SASFieldName="ADY">
        <Description>
          <TranslatedText xml:lang="en">Analysis Relative Day</TranslatedText>
        </Description>
        <def:Origin Type="Derived" Source="Sponsor"/>
      </ItemDef>
      <ItemDef OID="IT.ADLB.AVAL" Name="AVAL" DataType="float" Length="8" SignificantDigits="1" SASFieldName="AVAL">
        <Description>
          <TranslatedText xml:lang="en">Analysis Value</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.LBSTRESN</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.AVALU" Name="AVALU" DataType="text" Length="3" SASFieldName="AVALU">
        <Description>
          <TranslatedText xml:lang="en">Analysis Value Unit</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.LBSTRESU</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.ABLFL" Name="ABLFL" DataType="text" Length="1" SASFieldName="ABLFL">
        <Description>
          <TranslatedText xml:lang="en">Baseline Record Flag</TranslatedText>
        </Description>
        <def:Origin Type="Predecessor">
          <Description>
            <TranslatedText xml:lang="en">LB.LBBLFL</TranslatedText>
          </Description>
        </def:Origin>
      </ItemDef>
      <ItemDef OID="IT.ADLB.BASE" Name="BASE" DataType="float" Length="8" SignificantDigits="1" SASFieldName="BASE">
        <Description>
          <TranslatedText xml:lang="en">Baseline Value</TranslatedText>
        </Description>
        <def:Origin Type="Derived" Source="Sponsor"/>
      </ItemDef>
      <ItemDef OID="IT.ADLB.CHG" Name="CHG" DataType="float" Length="8" SignificantDigits="1" SASFieldName="CHG">
        <Description>
          <TranslatedText xml:lang="en">Change from Baseline</TranslatedText>
        </Description>
        <def:Origin Type="Derived" Source="Sponsor"/>
      </ItemDef>
      <MethodDef OID="MT.ADLB.ADY" Name="ADLB.ADY" Type="Computation">
        <Description>
          <TranslatedText xml:lang="en">Study day of ADT relative to TRTSDT, with no day zero.</TranslatedText>
        </Description>
      </MethodDef>
      <MethodDef OID="MT.ADLB.BASE" Name="ADLB.BASE" Type="Computation">
        <Description>
          <TranslatedText xml:lang="en">Repeat the flagged baseline value within subject and parameter.</TranslatedText>
        </Description>
      </MethodDef>
      <MethodDef OID="MT.ADLB.CHG" Name="ADLB.CHG" Type="Computation">
        <Description>
          <TranslatedText xml:lang="en">Analysis value minus baseline; missing when no baseline exists.</TranslatedText>
        </Description>
      </MethodDef>
    </MetaDataVersion>
  </Study>
</ODM>

Shaded columns are derived— = missing value

Human review and assessment

Dataset Name	Variable Name	Variable Label	Type	Codelist/Controlled Terms	Core	Computational Method	Origin
ADLB	STUDYID	Study Identifier	character		Req	Copy value from LB.STUDYID.	Predecessor
ADLB	USUBJID	Unique Subject Identifier	character		Req	Copy value from LB.USUBJID.	Predecessor
ADLB	PARAMCD	Parameter Code	character		Req	Copy value from LB.LBTESTCD.	Predecessor
ADLB	PARAM	Parameter	character		Req	Set constant value "Alanine Aminotransferase".	Assigned
ADLB	ADT	Analysis Date	numeric	ISO 8601	Cond	Copy value from LB.LBDTC.	Predecessor
ADLB	TRT01A	Actual Treatment for Period 01	character		Cond	Copy value from ADSL.TRT01A.	Predecessor
ADLB	ADY	Analysis Relative Day	numeric		Perm	Study day of ADT relative to TRTSDT, with no day zero.	Derived
ADLB	AVAL	Analysis Value	numeric		Cond	Copy value from LB.LBSTRESN.	Predecessor
ADLB	AVALU	Analysis Value Unit	character		Perm	Copy value from LB.LBSTRESU.	Predecessor
ADLB	ABLFL	Baseline Record Flag	character		Cond	Copy value from LB.LBBLFL.	Predecessor
ADLB	BASE	Baseline Value	numeric		Cond	Repeat the flagged baseline value within subject and parameter.	Derived
ADLB	CHG	Change from Baseline	numeric		Cond	Analysis value minus baseline; missing when no baseline exists.	Derived

Version	Date	Author	Description
1.7	2026-10-20	yamaa docs build	Read a specification in the 1.0 surface as its 0.5 counterpart; state that missing values stay missing where a mapping declares no missing handler, and leave out a declared missing answer that restates a handler's default
1.6	2026-10-17	yamaa docs build	Describe collected date parts written as ISO 8601 date text and times of day counted in seconds since midnight
1.5	2026-10-17	yamaa docs build	Name collected precision in words instead of letter codes; state imputation fallbacks, minimum source precision, bounds ignored outside the collected period, and invalid text with no handler as an error; describe date and datetime shifts, imputation flag codes, and partial text giving no date part
1.4	2026-10-15	yamaa docs build	State datetime precision codes through the hour and minute, and complete only the time parts a collected datetime lacks
1.3	2026-09-29	yamaa docs build	Show study codelist names, external dictionaries, and ISO 8601 formats in variable rows; list the document's codelist values and metadata
1.2	2026-09-29	yamaa docs build	Classify ADaM copies from a declared input as Predecessor and recodes as Derived, and SDTM recodes of locally derived columns as Derived
1.1	2026-09-29	yamaa docs build	Resolve lookups into the donor record they select, and give every derivation shape a plain-language rule instead of its raw YAML
1.0		yamaa docs build	Initial generation from spec.yaml

prompts/adam-adlb-adamig11/full.md

Edit20 lines

Following CDISC ADaM standards, use the provided ADSL and LB datasets to create an ADLB dataset with one record per subject per parameter per collection date.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, ADT, TRT01A, ADY, AVAL, AVALU, ABLFL, BASE, CHG

Use ADaMIG 1.1. PARAM is "Alanine Aminotransferase". ADY is relative to the subject's first treatment date in ADSL. BASE is the AVAL of the record with ABLFL "Y", repeated on every record for the same study, subject, and parameter. BASE has no value when no record is flagged "Y" for that study, subject, and parameter. CHG is AVAL minus BASE on every record, including the baseline record, and has no value when BASE has no value. BASE and CHG are not rounded.

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

prompts/adam-adlb-adamig11/conventions.md

Edit12 lines

Following CDISC ADaM standards, use the provided ADSL and LB datasets to create an ADLB dataset with one record per subject per parameter per collection date.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, ADT, TRT01A, ADY, AVAL, AVALU, ABLFL, BASE, CHG

Use ADaMIG 1.1. PARAM is "Alanine Aminotransferase". ABLFL is "Y". BASE and CHG are not rounded.

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

prompts/adam-adlb-adamig11/brief.md

Edit9 lines

Following CDISC ADaM standards, use the provided ADSL and LB datasets to create an ADLB dataset with one record per subject per parameter per collection date.

The output dataset should contain the following columns in this order: STUDYID, USUBJID, PARAMCD, PARAM, ADT, TRT01A, ADY, AVAL, AVALU, ABLFL, BASE, CHG

Read the source datasets from /app/input and save the completed dataset as /app/output/adlb.csv.

R

Edit3 lines

1library(yamaa)23yamaa_project("project.yaml")$spec("ADLB")$run()$output

Python

Edit3 lines

1import yamaa23yamaa.project("project.yaml").spec("ADLB").run().output

solutions/adam-adlb-adamig11/result.R

Edit47 lines

1# Create the ALT analysis dataset from the supplied subject and laboratory data.2options(stringsAsFactors = FALSE)3adsl <- read.csv("/app/input/adsl.csv", na.strings = c("", "NA"), check.names = FALSE)4lb <- read.csv("/app/input/lb.csv", na.strings = c("", "NA"), check.names = FALSE)5lb <- lb[lb$LBTESTCD == "ALT" & !is.na(lb$LBTESTCD), , drop = FALSE]67subject_key <- paste(adsl$STUDYID, adsl$USUBJID, sep = "\r")8stopifnot(!anyDuplicated(subject_key))9subject_match <- match(paste(lb$STUDYID, lb$USUBJID, sep = "\r"), subject_key)10stopifnot(!anyNA(subject_match))1112adt <- as.Date(substr(lb$LBDTC, 1L, 10L))13trtsdt <- as.Date(adsl$TRTSDT[subject_match])14day_difference <- as.integer(adt - trtsdt)15ady <- ifelse(is.na(day_difference), NA_integer_,16              ifelse(day_difference >= 0L, day_difference + 1L, day_difference))17aval <- as.numeric(lb$LBSTRESN)18ablfl <- ifelse(!is.na(lb$LBBLFL) & lb$LBBLFL == "Y", "Y", "")1920out <- data.frame(21  STUDYID = lb$STUDYID,22  USUBJID = lb$USUBJID,23  PARAMCD = lb$LBTESTCD,24  PARAM = "Alanine Aminotransferase",25  ADT = adt,26  TRT01A = adsl$TRT01A[subject_match],27  ADY = as.integer(ady),28  AVAL = aval,29  AVALU = lb$LBSTRESU,30  ABLFL = ablfl,31  BASE = NA_real_,32  CHG = NA_real_,33  check.names = FALSE34)35parameter_key <- paste(out$STUDYID, out$USUBJID, out$PARAMCD, sep = "\r")36for (key in unique(parameter_key)) {37  rows <- which(parameter_key == key)38  baseline_rows <- rows[out$ABLFL[rows] == "Y"]39  stopifnot(length(baseline_rows) <= 1L)40  if (length(baseline_rows) == 1L) {41    out$BASE[rows] <- out$AVAL[baseline_rows]42  }43}44out$CHG <- out$AVAL - out$BASE45out <- out[order(out$STUDYID, out$USUBJID, out$PARAMCD, out$ADT), , drop = FALSE]46stopifnot(!anyDuplicated(out[c("STUDYID", "USUBJID", "PARAMCD", "ADT")]))47write.csv(out, "/app/output/adlb.csv", row.names = FALSE, na = "")

solutions/adam-adlb-adamig11/result.py

Edit60 lines

1"""Create ADLB from the supplied ADSL and LB data (ADaMIG 1.1)."""23from pathlib import Path45import pandas as pd678def main():9    adsl = pd.read_csv(Path("/app/input") / "adsl.csv", dtype=str)10    lb = pd.read_csv(Path("/app/input") / "lb.csv", dtype=str)1112    # The requested analysis parameter is ALT.13    adlb = lb.loc[lb["LBTESTCD"].eq("ALT")].copy()14    adlb = adlb.merge(15        adsl[["STUDYID", "USUBJID", "TRTSDT", "TRT01A"]],16        on=["STUDYID", "USUBJID"],17        how="left",18        validate="many_to_one",19    )20    adlb["PARAMCD"] = "ALT"21    adlb["PARAM"] = "Alanine Aminotransferase"22    collection_date = pd.to_datetime(adlb["LBDTC"].str[:10], errors="coerce")23    treatment_date = pd.to_datetime(adlb["TRTSDT"], errors="coerce")24    adlb["ADT"] = collection_date.dt.strftime("%Y-%m-%d")25    day_difference = (collection_date - treatment_date).dt.days26    # ADaM study day has no day zero.27    adlb["ADY"] = (day_difference + day_difference.ge(0)).astype("Int64")28    adlb["AVAL"] = pd.to_numeric(adlb["LBSTRESN"], errors="coerce")29    adlb["AVALU"] = adlb["LBSTRESU"]30    adlb["ABLFL"] = adlb["LBBLFL"].where(adlb["LBBLFL"].eq("Y"), "")3132    keys = ["STUDYID", "USUBJID", "PARAMCD"]33    baseline = adlb.loc[adlb["ABLFL"].eq("Y"), keys + ["AVAL"]].rename(34        columns={"AVAL": "BASE"}35    )36    adlb = adlb.merge(baseline, on=keys, how="left", validate="many_to_one")37    adlb["CHG"] = adlb["AVAL"] - adlb["BASE"]38    columns = [39        "STUDYID",40        "USUBJID",41        "PARAMCD",42        "PARAM",43        "ADT",44        "TRT01A",45        "ADY",46        "AVAL",47        "AVALU",48        "ABLFL",49        "BASE",50        "CHG",51    ]52    adlb = adlb[columns].sort_values(keys + ["ADT"], kind="stable")53    if adlb.duplicated(keys + ["ADT"]).any():54        raise ValueError("More than one ALT record per subject and collection date")55    Path("/app/output").mkdir(exist_ok=True)56    adlb.to_csv(Path("/app/output") / "adlb.csv", index=False)575859if __name__ == "__main__":60    main()

solutions/adam-adlb-adamig11/result.sas

Edit61 lines

1proc import datafile='/app/input/adsl.csv' out=adsl dbms=csv replace;2  getnames=yes;3run;45proc import datafile='/app/input/lb.csv' out=lb dbms=csv replace;6  getnames=yes;7run;89proc sql;10  create table source as11  select l.*, a.TRTSDT, a.TRT01A12  from lb as l13  left join adsl as a14    on l.STUDYID=a.STUDYID and l.USUBJID=a.USUBJID;15quit;1617data derived;18  length PARAMCD $8 PARAM $40 AVALU $20 ABLFL $1;19  set source;20  PARAMCD=LBTESTCD;21  PARAM='Alanine Aminotransferase';22  ADT=LBDTC;23  _TRTSDT=TRTSDT;24  if ADT ne . and _TRTSDT ne . then do;25    if ADT < _TRTSDT then ADY=ADT-_TRTSDT;26    else ADY=ADT-_TRTSDT+1;27  end;28  AVAL=LBSTRESN;29  AVALU=LBSTRESU;30  ABLFL=LBBLFL;31  format ADT yymmdd10.;32run;3334proc sql;35  create table adlb_joined as36  select d.STUDYID, d.USUBJID, d.PARAMCD, d.PARAM,37         d.ADT format=yymmdd10., d.TRT01A, d.ADY, d.AVAL,38         d.AVALU, d.ABLFL, b.AVAL as BASE,39         case when d.AVAL is not null and b.AVAL is not null then d.AVAL-b.AVAL else . end as CHG40  from derived as d41  left join derived as b42    on d.STUDYID=b.STUDYID and d.USUBJID=b.USUBJID43       and d.PARAMCD=b.PARAMCD and b.ABLFL='Y'44  order by d.STUDYID, d.USUBJID, d.PARAMCD, d.ADT;45quit;4647data adlb;48  set adlb_joined;49  format ADT yymmdd10.;50run;5152proc sql;53  create table adlb_csv as54  select STUDYID, USUBJID, PARAMCD, PARAM,55         put(ADT,yymmdd10.) as ADT, TRT01A, ADY, AVAL, AVALU,56         ABLFL, BASE, CHG57  from adlb;58quit;5960proc export data=adlb_csv outfile='/app/output/adlb.csv' dbms=csv replace;61run;

input/adsl.csv

input/lb.csv

expected/adlb.csv

expected/define.xml

Define-XML 2.1.11: CATH

ADLB

Your review

Mapping spec

Agent prompt

prompts/adam-adlb-adamig11/full.md

prompts/adam-adlb-adamig11/conventions.md

prompts/adam-adlb-adamig11/brief.md

yamaa code

R

Python

Solution without yamaa

solutions/adam-adlb-adamig11/result.R

solutions/adam-adlb-adamig11/result.py

solutions/adam-adlb-adamig11/result.sas