Is this skill intended for individual patient bedside care?

No, this skill is designed specifically for group-level pharmaceutical research, cohort analysis, and evidence synthesis. For individual patient treatment plans at the bedside, use the treatment-plans skill.

How are visual diagrams and algorithms generated?

The skill includes a mandatory integration with the scientific-schematics tool to automatically produce publication-quality clinical flowcharts, treatment pathways, and stratification trees.

What statistical outputs does the skill support?

The skill supports a wide range of analytical metrics including Hazard Ratios (HR), p-values, 95% confidence intervals, Kaplan-Meier survival curves, Cox regression, and waterfall plots.

Can I use this for regulatory submissions?

Yes, the skill generates professional LaTeX/PDF documents aligned with ICH-GCP standards and HIPAA de-identification principles, suitable for IND/NDA documentation and regulatory summaries.

Clinical Decision Support

Name: Clinical Decision Support
Author: plurigrid

byplurigrid

•

Ciencia de Datos y ML

Generates professional, publication-ready clinical decision support documents and biomarker-stratified cohort analyses for pharmaceutical and clinical research.

The Clinical Decision Support skill empowers pharmaceutical researchers and medical decision-makers to automate the creation of high-fidelity, evidence-based documentation. It specializes in generating patient cohort analyses with complex statistical outcomes—such as Hazard Ratios and Kaplan-Meier curves—and treatment recommendation reports utilizing the GRADE evidence grading system. By integrating biomarker data and mandatory scientific schematics, the skill produces LaTeX-formatted, regulatory-compliant PDFs optimized for drug development, clinical trial reporting, and medical society guideline synthesis.

Características Principales

01Biomarker-stratified patient cohort analysis and molecular subtype classification

028 GitHub stars

03Publication-ready LaTeX/PDF output with professional executive summaries and regulatory alignment

04Automated generation of clinical decision algorithms via scientific-schematics integration

05Evidence-based treatment guidelines with GRADE grading (1A-2C) and strength assessments

06Advanced statistical visualizations including survival curves, waterfall plots, and forest plots

Casos de Uso

01Developing Phase 2/3 clinical trial subgroup analyses and regulatory submission documents for IND/NDA

02Synthesizing real-world evidence (RWE) from EMR data to compare treatment effectiveness across populations

03Creating biomarker-guided treatment sequencing algorithms for medical affairs and KOL education materials

Características Principales

01Biomarker-stratified patient cohort analysis and molecular subtype classification

028 GitHub stars

03Publication-ready LaTeX/PDF output with professional executive summaries and regulatory alignment

04Automated generation of clinical decision algorithms via scientific-schematics integration

05Evidence-based treatment guidelines with GRADE grading (1A-2C) and strength assessments

06Advanced statistical visualizations including survival curves, waterfall plots, and forest plots

Casos de Uso

01Developing Phase 2/3 clinical trial subgroup analyses and regulatory submission documents for IND/NDA

02Synthesizing real-world evidence (RWE) from EMR data to compare treatment effectiveness across populations

03Creating biomarker-guided treatment sequencing algorithms for medical affairs and KOL education materials