Generate YAML-ready phenotype and lab-usage definitions from EHR data.
npx skills add https://github.com/tito-gh/healthcare --skill phenotype-lab-spec
Please help me install this Agent Skill. Skill: phenotype-lab-spec Source: https://github.com/tito-gh/healthcare/tree/main/.claude/skills/phenotype-lab-spec Command: npx skills add https://github.com/tito-gh/healthcare --skill phenotype-lab-spec
This Skill enables researchers and clinicians to translate complex phenotype and laboratory value criteria into machine-executable definitions, ensuring reproducibility and scalable validation across large EHR datasets.
Create a phenotype definition for an NDMM exposure to daratumumab using IMWG criteria, and generate an accompanying validation plan.
High-intent search queries and answers about installing and using this skill.
To create computer-executable phenotype definitions from EHR data, you input structured parameters like PHENOTYPE_NAME, DRUG, INDICATION, and REFERENCE_DEFINITION to generate YAML-ready, machine-executable outputs covering population, exposure, outcome, and covariate phenotypes.
Mapping lab values and handling time-series data for EHR phenotypes requires defining lab variable mappings, normal ranges, and longitudinal processing specifications, which are structured to support robust clinical research analyses and reproducible execution.
Generating a validation plan for exposure phenotypes using IMWG criteria involves applying built-in validation templates that specify PPV targets, sensitivity targets, and evaluation plans to ensure clinical relevance across large EHR datasets.
Yes, building covariate and outcome phenotypes from EHR data requires structured inputs such as PHENOTYPE_NAME, DRUG, and INDICATION to automate the creation of reproducible, machine-executable definitions and lab-usage specifications.
Automated phenotype definitions for EHR data processing are output in a YAML-ready format, enabling researchers to directly execute structured population, exposure, outcome, and covariate definitions against large datasets.
Yes, you can define phenotypes for both drug exposure and disease indications by providing structured inputs like DRUG and INDICATION, translating complex clinical criteria into machine-executable definitions with scalable validation planning.
tito-ghDesign EHR-RWD study designs from research questions and clinical data inputs.
inflexa-aiAnalyze pharmacokinetic and pharmacodynamic data with RECIST 1.1 response classification.
dathereMap natural language topics to BLS series IDs and fetch values.
KjellKodGenerate structured implementation plans with acceptance criteria and validation strategies.
