clinical-decision-support

Generate LaTeX/PDF clinical decision support documents with statistical tables and plots.

74|5|Updated Dec 10, 2025
One-click install
npx skills add https://github.com/dralkh/seerai --skill clinical-decision-support-dralkh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: clinical-decision-support
Source: https://github.com/dralkh/seerai/tree/main/skills/clinical-decision-support
Command: npx skills add https://github.com/dralkh/seerai --skill clinical-decision-support-dralkh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, matplotlib, lifelines, requests, pyyaml, python-dotenv, scikit-learn, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill turns complex clinical and biomarker data into polished decision-support documents, removing the manual effort of building cohort analyses, treatment recommendations, and evidence summaries for research teams.

Core Features & Use Cases

  • Patient Cohort Analysis: Stratify cohorts by biomarkers, molecular subtypes, stage, or prior therapy and compare outcomes such as response rates, progression-free survival, and overall survival.
  • Treatment Recommendation Reports: Produce evidence-based guideline documents with GRADE grading, line-of-therapy sequencing, biomarker decision criteria, and monitoring guidance.
  • Publication-Ready Outputs: Generate compact LaTeX/PDF documents with tables, Kaplan-Meier curves, forest plots, waterfall plots, and decision flowcharts for pharmaceutical and clinical research workflows.
  • Use Case: A research team can ask for a HER2-positive breast cancer cohort analysis or a PD-L1-guided NSCLC treatment algorithm and receive a structured, professional report ready for review.

Quick Start

Use the clinical-decision-support skill to create a publication-ready treatment recommendation report for advanced NSCLC with biomarker-guided therapy, a GRADE evidence summary, and a decision flowchart.

Frequently Asked Questions about clinical-decision-support

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

FAQPage Schema
How do I generate a clinical decision support report with GRADE evidence grading and biomarker stratification?

Clinical decision support reports with GRADE evidence grading are generated by stratifying patient cohorts by biomarkers, analyzing survival and response outcomes, and producing publication-ready LaTeX/PDF documents complete with statistical tables and decision flowcharts.

Can I create Kaplan-Meier curves and forest plots for a biomarker-guided cohort analysis?

Yes, biomarker-guided cohort analysis output includes Kaplan-Meier curves, forest plots, and waterfall plots. The skill uses matplotlib and lifelines to render these survival and response visualizations directly within the final LaTeX/PDF document.

What is the best way to build a treatment recommendation algorithm for oncology patient subtyping?

The best way to build oncology treatment recommendation algorithms is to stratify cohorts by molecular subtypes and prior therapy, apply GRADE evidence grading, and generate decision flowcharts using TikZ to map line-of-therapy sequencing and biomarker decision criteria.

Does this clinical decision support workflow require Python libraries like pandas and scipy for survival analysis?

Yes, the clinical decision support workflow requires pandas, numpy, scipy, and lifelines to perform survival analysis, cohort stratification, and statistical computations before compiling the results into publication-ready reports.

How do I produce publication-ready LaTeX tables and TikZ flowcharts from clinical trial data?

Publication-ready LaTeX tables and TikZ flowcharts are produced by processing clinical trial data through Python scripts that calculate statistical outcomes, which are then formatted into compact LaTeX/PDF documents for pharmaceutical and clinical research workflows.