clinical-decision-support

Clinical decision support documents integrate GRADE evidence grading, Kaplan-Meier and Cox regression survival analyses, and biomarker-stratified cohort data into LaTeX/PDF output. This Skill automates the generation of treatment recommendation reports and cohort analyses with TikZ flowcharts, regulatory-compliance content, and HIPAA de-identification in publication-ready format.

Yes. The Skill applies biomarker integration and survival analysis—including hazard analyses and evidence synthesis workflows—to patient cohorts and generates structured treatment guidance documents. Output includes GRADE-graded evidence, decision trees, and LaTeX/PDF formatting suitable for regulatory submissions.

Input requirements include structured patient cohort data compatible with pandas and numpy. The Skill depends on scipy, lifelines for survival analysis, matplotlib for visualizations, and PyYAML for configuration. References and templates are provided as components for consistent document structure.

Yes. The Skill generates regulatory-compliance content and includes HIPAA de-identification workflows as needed. Output LaTeX/PDF documents meet publication and submission standards for clinical guidance while protecting patient privacy.

GRADE grading is embedded into the evidence synthesis workflow, automatically applied to biomarker-stratified analyses and survival outcomes. Treatment recommendations incorporate graded evidence levels directly into the LaTeX output, supporting structured decision-tree documentation.

Cohort analyses focus on biomarker-stratified patient populations with survival metrics and hazard comparisons. Treatment recommendation reports layer GRADE evidence grading and decision trees on top of cohort findings to produce actionable clinical guidance in publication-ready format.