findings-domains

Model SDTM Findings domains with vertical data structures and naming conventions.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/siddharthchauhan/ETL --skill findings-domains
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: findings-domains
Source: https://github.com/siddharthchauhan/ETL/tree/main/sdtm_pipeline/deepagents/skills/findings-domains
Command: npx skills add https://github.com/siddharthchauhan/ETL --skill findings-domains

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides detailed guidance for implementing SDTM Findings domains (LB, VS, EG, PE, QS, SC, FA, PC, PP, MB, MS, MI, RP, DD, FT, GF, IS, CP) using a vertical data structure, standardized variable naming patterns, result handling (original vs standardized), reference ranges, and baseline/derived flag logic to ensure SDTMIG conformance.

Core Features & Use Cases

  • Vertical data modeling guidance for Findings domains, including test code naming patterns (--TESTCD/--TEST/--ORRES/--STRESC) and domain-specific variable requirements.
  • Transformation and validation patterns to convert horizontal source data into SDTM LB, VS, EG and specimen-based domains, with baseline flags and derived values clearly defined.
  • Practical use cases: standardizing laboratory, vital signs, ECG, and other observational data into consistent SDTM findings datasets for regulatory submission and analysis.

Quick Start

Load a sample horizontal dataset and run the skill to generate SDTM LB, VS, and EG findings datasets with properly mapped tests, results, baseline flags, and reference ranges.

Frequently Asked Questions about findings-domains

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert horizontal clinical data into SDTM Findings domains?

Vertical data modeling converts horizontal source data into SDTM Findings domains by mapping observations into standardized datasets using naming conventions like --TESTCD, --ORRES, and --STRESC for LB, VS, and EG domains.

What is the correct variable naming pattern for SDTM Findings domain tests?

SDTM Findings domains use standardized variable naming patterns including --TESTCD for test codes, --TEST for test names, --ORRES for original results, and --STRESC for standardized character results to maintain SDTMIG conformance.

How do I handle baseline flags and derived values in SDTM LB and VS datasets?

Baseline flags and derived values in SDTM LB and VS datasets are handled by applying logical rules during transformation, clearly defining baseline observation records and derived calculation values to meet submission standards.

Which specific SDTM domains are supported for vertical data modeling?

Vertical data modeling supports SDTM domains including LB, VS, EG, PE, QS, SC, FA, PC, PP, MB, MS, MI, RP, DD, FT, GF, IS, and CP for standardizing laboratory, vital signs, ECG, and specimen-based observational data.

Does this approach to SDTM Findings data include reference range and result standardization?

Yes, SDTM Findings vertical data modeling includes result handling for original versus standardized values and maps reference ranges to ensure consistent observational data for regulatory submission and analysis.

When do I need to use vertical data structures for SDTMIG conformance?

Vertical data structures are required for SDTMIG conformance when transforming clinical observations like laboratory tests and vital signs into unified datasets, ensuring standardized variables and baseline logic across all Findings domains.