clinical-decision-support

Generate publication-ready clinical decision support documents by synthesizing biomarker-guided cohort analyses and GRADE-based evidence into reproducible LaTeX/PDF outputs. The skill applies YAML frontmatter and TikZ templates to ensure regulator-grade formatting.

Yes, you can produce treatment recommendation reports using GRADE methodology and generate clinical pathways with TikZ flowcharts. The skill leverages LaTeX templating to format evidence tables and decision algorithms into standardized outputs.

The skill utilizes pandas, numpy, scipy, and lifelines to perform statistical comparisons and cohort analyses on biomarker-stratified data. These dependencies enable survival analysis and population-level evidence synthesis.

Standardize clinical pathways for regulatory submissions by applying YAML frontmatter-driven structures and GRADE-based recommendations. The skill ensures reproducibility and compliance through predefined templates, references, and asset components.

You can use scikit-learn alongside numpy and scipy to perform biomarker stratification and statistical modeling for cohort analysis. The skill integrates these analytical results into publication-ready clinical decision support documents.

Evidence synthesis document generation requires biomarker-guided data and strict YAML frontmatter formatting. The skill is designed for population-level analyses and guideline development, so outputs depend on the quality of input cohort data and GRADE evidence tables.