Clinical Decision Support Documents

Description

Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development:

1. Patient Cohort Analysis - Biomarker-stratified group analyses with statistical outcome comparisons
2. Treatment Recommendation Reports - Evidence-based clinical guidelines with GRADE grading and decision algorithms

All documents are generated as publication-ready LaTeX/PDF files optimized for pharmaceutical research, regulatory submissions, and clinical guideline development.

Note: For individual patient treatment plans at the bedside, use the treatment-plans skill instead. This skill focuses on group-level analyses and evidence synthesis for pharmaceutical/research settings.

Capabilities

Document Types

Patient Cohort Analysis

• Biomarker-based patient stratification (molecular subtypes, gene expression, IHC)
• Molecular subtype classification (e.g., GBM mesenchymal-immune-active vs proneural, breast cancer subtypes)
• Outcome metrics with statistical analysis (OS, PFS, ORR, DOR, DCR)
• Statistical comparisons between subgroups (hazard ratios, p-values, 95% CI)
• Survival analysis with Kaplan-Meier curves and log-rank tests
• Efficacy tables and waterfall plots
• Comparative effectiveness analyses
• Pharmaceutical cohort reporting (trial subgroups, real-world evidence)

Treatment Recommendation Reports

• Evidence-based treatment guidelines for specific disease states
• Strength of recommendation grading (GRADE system: 1A, 1B, 2A, 2B, 2C)
• Quality of evidence assessment (high, moderate, low, very low)
• Treatment algorithm flowcharts with TikZ diagrams
• Line-of-therapy sequencing based on biomarkers
• Decision pathways with clinical and molecular criteria
• Pharmaceutical strategy documents
• Clinical guideline development for medical societies

Clinical Features

• Biomarker Integration: Genomic alterations (mutations, CNV, fusions), gene expression signatures, IHC markers, PD-L1 scoring
• Statistical Analysis: Hazard ratios, p-values, confidence intervals, survival curves, Cox regression, log-rank tests
• Evidence Grading: GRADE system (1A/1B/2A/2B/2C), Oxford CEBM levels, quality of evidence assessment
• Clinical Terminology: SNOMED-CT, LOINC, proper medical nomenclature, trial nomenclature
• Regulatory Compliance: HIPAA de-identification, confidentiality headers, ICH-GCP alignment
• Professional Formatting: Compact 0.5in margins, color-coded recommendations, publication-ready, suitable for regulatory submissions

Pharmaceutical and Research Use Cases

This skill is specifically designed for pharmaceutical and clinical research applications:

Drug Development

• Phase 2/3 Trial Analyses: Biomarker-stratified efficacy and safety analyses
• Subgroup Analyses: Forest plots showing treatment effects across patient subgroups
• Companion Diagnostic Development: Linking biomarkers to drug response
• Regulatory Submissions: IND/NDA documentation with evidence summaries

Medical Affairs

• KOL Education Materials: Evidence-based treatment algorithms for thought leaders
• Medical Strategy Documents: Competitive landscape and positioning strategies
• Advisory Board Materials: Cohort analyses and treatment recommendation frameworks
• Publication Planning: Manuscript-ready analyses for peer-reviewed journals

Clinical Guidelines

• Guideline Development: Evidence synthesis with GRADE methodology for specialty societies
• Consensus Recommendations: Multi-stakeholder treatment algorithm development
• Practice Standards: Biomarker-based treatment selection criteria
• Quality Measures: Evidence-based performance metrics

Real-World Evidence

• RWE Cohort Studies: Retrospective analyses of patient cohorts from EMR data
• Comparative Effectiveness: Head-to-head treatment comparisons in real-world settings
• Outcomes Research: Long-term survival and safety in clinical practice
• Health Economics: Cost-effectiveness analyses by biomarker subgroup

When to Use

Use this skill when you need to:

• Analyze patient cohorts stratified by biomarkers, molecular subtypes, or clinical characteristics
• Generate treatment recommendation reports with evidence grading for clinical guidelines or pharmaceutical strategies
• Compare outcomes between patient subgroups with statistical analysis (survival, response rates, hazard ratios)
• Produce pharmaceutical research documents for drug development, clinical trials, or regulatory submissions
• Develop clinical practice guidelines with GRADE evidence grading and decision algorithms
• Document biomarker-guided therapy selection at the population level (not individual patients)
• Synthesize evidence from multiple trials or real-world data sources
• Create clinical decision algorithms with flowcharts for treatment sequencing

Do NOT use this skill for:

• Individual patient treatment plans (use treatment-plans skill)
• Bedside clinical care documentation (use treatment-plans skill)
• Simple patient-specific treatment protocols (use treatment-plans skill)

Visual Enhancement with Scientific Schematics

⚠️ MANDATORY: Every clinical decision support document MUST include at least 1-2 AI-generated figures using the scientific-schematics skill.

This is not optional. Clinical decision documents require clear visual algorithms. Before finalizing any document:

1. Generate at minimum ONE schematic or diagram (e.g., clinical decision algorithm, treatment pathway, or biomarker stratification tree)
2. For cohort analyses: include patient flow diagram
3. For treatment recommendations: include decision flowchart

How to generate figures:

• Use the scientific-schematics skill to generate AI-powered publication-quality diagrams
• Simply describe your desired diagram in natural language
• Nano Banana Pro will automatically generate, review, and refine the schematic

How to generate schematics:

python scripts/generate_schematic.py "your diagram description" -o figures/output.png

The AI will automatically:

• Create publication-quality images with proper formatting
• Review and refine through multiple iterations
• Ensure accessibility (colorblind-friendly, high contrast)
• Save outputs in the figures/ directory

When to add schematics:

• Clinical decision algorithm flowcharts
• Treatment pathway diagrams
• Biomarker stratification trees
• Patient cohort flow diagrams (CONSORT-style)
• Survival curve visualizations
• Molecular mechanism diagrams
• Any complex concept that benefits from visualization

For detailed guidance on creating schematics, refer to the scientific-schematics skill documentation.

Document Structure

CRITICAL REQUIREMENT: All clinical decision support documents MUST begin with a complete executive summary on page 1 that spans the entire first page before any table of contents or detailed sections.

Page 1 Executive Summary Structure

The first page of every CDS document should contain ONLY the executive summary with the following components:

Required Elements (all on page 1):

1. Document Title and Type

   • Main title (e.g., "Biomarker-Stratified Cohort Analysis" or "Evidence-Based Treatment Recommendations")
   • Subtitle with disease state and focus

2. Report Information Box (using colored tcolorbox)

   • Document type and purpose
   • Date of analysis/report
   • Disease state and patient population
   • Author/institution (if applicable)
   • Analysis framework or methodology

3. Key Findings Boxes (3-5 colored boxes using tcolorbox)

   • Primary Results (blue box): Main efficacy/outcome findings
   • Biomarker Insights (green box): Key molecular subtype findings
   • Clinical Implications (yellow/orange box): Actionable treatment implications
   • Statistical Summary (gray box): Hazard ratios, p-values, key statistics
   • Safety Highlights (red box, if applicable): Critical adverse events or warnings

Visual Requirements:

• Use \thispagestyle{empty} to remove page numbers from page 1
• All content must fit on page 1 (before \newpage)
• Use colored tcolorbox environments with different colors for visual hierarchy
• Boxes should be scannable and highlight most critical information
• Use bullet points, not narrative paragraphs
• End page 1 with \newpage before table of contents or detailed sections

Example First Page LaTeX Structure:

\maketitle
\thispagestyle{empty}

% Report Information Box
\begin{tcolorbox}[colback=blue!5!white, colframe=blue!75!black, title=Report Information]
\textbf{Document Type:} Patient Cohort Analysis\\
\textbf{Disease State:} HER2-Positive Metastatic Breast Cancer\\
\textbf{Analysis Date:} \today\\
\textbf{Population:} 60 patients, biomarker-stratified by HR status
\end{tcolorbox}

\vspace{0.3cm}

% Key Finding #1: Primary Results
\begin{tcolorbox}[colback=blue!5!white, colframe=blue!75!black, title=Primary Efficacy Results]
\begin{itemize}
    \item Overall ORR: 72\% (95\% CI: 59-83\%)
    \item Median PFS: 18.5 months (95\% CI: 14.2-22.8)
    \item Median OS: 35.2 months (95\% CI: 28.1-NR)
\end{itemize}
\end{tcolorbox}

\vspace{0.3cm}

% Key Finding #2: Biomarker Insights
\begin{tcolorbox}[colback=green!5!white, colframe=green!75!black, title=Biomarker Stratification Findings]
\begin{itemize}
    \item HR+/HER2+: ORR 68\%, median PFS 16.2 months
    \item HR-/HER2+: ORR 78\%, median PFS 22.1 months
    \item HR status significantly associated with outcomes (p=0.041)
\end{itemize}
\end{tcolorbox}

\vspace{0.3cm}

% Key Finding #3: Clinical Implications
\begin{tcolorbox}[colback=orange!5!white, colframe=orange!75!black, title=Clinical Recommendations]
\begin{itemize}
    \item Strong efficacy observed regardless of HR status (Grade 1A)
    \item HR-/HER2+ patients showed numerically superior outcomes
    \item Treatment recommended for all HER2+ MBC patients
\end{itemize}
\end{tcolorbox}

\newpage
\tableofcontents  % TOC on page 2
\newpage  % Detailed content starts page 3

Patient Cohort Analysis (Detailed Sections - Page 3+)

• Cohort Characteristics: Demographics, baseline features, patient selection criteria
• Biomarker Stratification: Molecular subtypes, genomic alterations, IHC profiles
• Treatment Exposure: Therapies received, dosing, treatment duration by subgroup
• Outcome Analysis: Response rates (ORR, DCR), survival data (OS, PFS), DOR
• Statistical Methods: Kaplan-Meier survival curves, hazard ratios, log-rank tests, Cox regression
• Subgroup Comparisons: Biomarker-stratified efficacy, forest plots, statistical significance
• Safety Profile: Adverse events by subgroup, dose modifications, discontinuations
• Clinical Recommendations: Treatment implications based on biomarker profiles
• Figures: Waterfall plots, swimmer plots, survival curves, forest plots
• Tables: Demographics table, biomarker frequency, outcomes by subgroup

Treatment Recommendation Reports (Detailed Sections - Page 3+)

Page 1 Executive Summary for Treatment Recommendations should include:

1. Report Information Box: Disease state, guideline version/date, target population
2. Key Recommendations Box (green): Top 3-5 GRADE-graded recommendations by line of therapy
3. Biomarker Decision Criteria Box (blue): Key molecular markers influencing treatment selection
4. Evidence Summary Box (gray): Major trials supporting recommendations (e.g., KEYNOTE-189, FLAURA)
5. Critical Monitoring Box (orange/red): Essential safety monitoring requirements

Detailed Sections (Page 3+):

• Clinical Context: Disease state, epidemiology, current treatment landscape
• Target Population: Patient characteristics, biomarker criteria, staging
• Evidence Review: Systematic literature synthesis, guideline summary, trial data
• Treatment Options: Available therapies with mechanism of action
• Evidence Grading: GRADE assessment for each recommendation (1A, 1B, 2A, 2B, 2C)
• Recommendations by Line: First-line, second-line, subsequent therapies
• Biomarker-Guided Selection: Decision criteria based on molecular profiles
• Treatment Algorithms: TikZ flowcharts showing decision pathways
• Monitoring Protocol: Safety assessments, efficacy monitoring, dose modifications
• Special Populations: Elderly, renal/hepatic impairment, comorbidities
• References: Full bibliography with trial names and citations

Output Format

MANDATORY FIRST PAGE REQUIREMENT:

• Page 1: Full-page executive summary with 3-5 colored tcolorbox elements
• Page 2: Table of contents (optional)
• Page 3+: Detailed sections with methods, results, figures, tables

Document Specifications:

• Primary: LaTeX/PDF with 0.5in margins for compact, data-dense presentation
• Length: Typically 5-15 pages (1 page executive summary + 4-14 pages detailed content)
• Style: Publication-ready, pharmaceutical-grade, suitable for regulatory submissions
• First Page: Always a complete executive summary spanning entire page 1 (see Document Structure section)

Visual Elements:

• Colors:
  • Page 1 boxes: blue=data/information, green=biomarkers/recommendations, yellow/orange=clinical implications, red=warnings
  • Recommendation boxes (green=strong recommendation, yellow=conditional, blue=research needed)
  • Biomarker stratification (color-coded molecular subtypes)
  • Statistical significance (color-coded p-values, hazard ratios)
• Tables:
  • Demographics with baseline characteristics
  • Biomarker frequency by subgroup
  • Outcomes table (ORR, PFS, OS, DOR by molecular subtype)
  • Adverse events by cohort
  • Evidence summary tables with GRADE ratings
• Figures:
  • Kaplan-Meier survival curves with log-rank p-values and number at risk tables
  • Waterfall plots showing best response by patient
  • Forest plots for subgroup analyses with confidence intervals
  • TikZ decision algorithm flowcharts
  • Swimmer plots for individual patient timelines
• Statistics: Hazard ratios with 95% CI, p-values, median survival times, landmark survival rates
• Compliance: De-identification per HIPAA Safe Harbor, confidentiality notices for proprietary data

Integration

This skill integrates with:

• scientific-writing: Citation management, statistical reporting, evidence synthesis
• clinical-reports: Medical terminology, HIPAA compliance, regulatory documentation
• scientific-schematics: TikZ flowcharts for decision algorithms and treatment pathways
• treatment-plans: Individual patient applications of cohort-derived insights (bidirectional)

Key Differentiators from Treatment-Plans Skill

Clinical Decision Support (this skill):

• Audience: Pharmaceutical companies, clinical researchers, guideline committees, medical affairs
• Scope: Population-level analyses, evidence synthesis, guideline development
• Focus: Biomarker stratification, statistical comparisons, evidence grading
• Output: Multi-page analytical documents (5-15 pages typical) with extensive figures and tables
• Use Cases: Drug development, regulatory submissions, clinical practice guidelines, medical strategy
• Example: "Analyze 60 HER2+ breast cancer patients by hormone receptor status with survival outcomes"

Treatment-Plans Skill:

• Audience: Clinicians, patients, care teams
• Scope: Individual patient care planning
• Focus: SMART goals, patient-specific interventions, monitoring plans
• Output: Concise 1-4 page actionable care plans
• Use Cases: Bedside clinical care, EMR documentation, patient-centered planning
• Example: "Create treatment plan for a 55-year-old patient with newly diagnosed type 2 diabetes"

When to use each:

• Use clinical-decision-support for: cohort analyses, biomarker stratification studies, treatment guideline development, pharmaceutical strategy documents
• Use treatment-plans for: individual patient care plans, treatment protocols for specific patients, bedside clinical documentation

Example Usage

Patient Cohort Analysis

Example 1: NSCLC Biomarker Stratification

> Analyze a cohort of 45 NSCLC patients stratified by PD-L1 expression (<1%, 1-49%, ≥50%) 
> receiving pembrolizumab. Include outcomes: ORR, median PFS, median OS with hazard ratios 
> comparing PD-L1 ≥50% vs <50%. Generate Kaplan-Meier curves and waterfall plot.

Example 2: GBM Molecular Subtype Analysis

> Generate cohort analysis for 30 GBM patients classified into Cluster 1 (Mesenchymal-Immune-Active) 
> and Cluster 2 (Proneural) molecular subtypes. Compare outcomes including median OS, 6-month PFS rate, 
> and response to TMZ+bevacizumab. Include biomarker profile table and statistical comparison.

Example 3: Breast Cancer HER2 Cohort

> Analyze 60 HER2-positive metastatic breast cancer patients treated with trastuzumab-deruxtecan, 
> stratified by prior trastuzumab exposure (yes/no). Include ORR, DOR, median PFS with forest plot 
> showing subgroup analyses by hormone receptor status, brain metastases, and number of prior lines.

Treatment Recommendation Report

Example 1: HER2+ Metastatic Breast Cancer Guidelines

> Create evidence-based treatment recommendations for HER2-positive metastatic breast cancer including 
> biomarker-guided therapy selection. Use GRADE system to grade recommendations for first-line 
> (trastuzumab+pertuzumab+taxane), second-line (trastuzumab-deruxtecan), and third-line options. 
> Include decision algorithm flowchart based on brain metastases, hormone receptor status, and prior therapies.

Example 2: Advanced NSCLC Treatment Algorithm

> Generate treatment recommendation report for advanced NSCLC based on PD-L1 expression, EGFR mutation, 
> ALK rearrangement, and performance status. Include GRADE-graded recommendations for each molecular subtype, 
> TikZ flowchart for biomarker-directed therapy selection, and evidence tables from KEYNOTE-189, FLAURA, 
> and CheckMate-227 trials.

Example 3: Multiple Myeloma Line-of-Therapy Sequencing

> Create treatment algorithm for newly diagnosed multiple myeloma through relapsed/refractory setting. 
> Include GRADE recommendations for transplant-eligible vs ineligible, high-risk cytogenetics considerations, 
> and sequencing of daratumumab, carfilzomib, and CAR-T therapy. Provide flowchart showing decision points 
> at each line of therapy.

Key Features

Biomarker Classification

• Genomic: Mutations, CNV, gene fusions
• Expression: RNA-seq, IHC scores
• Molecular subtypes: Disease-specific classifications
• Clinical actionability: Therapy selection guidance

Outcome Metrics

• Survival: OS (overall survival), PFS (progression-free survival)
• Response: ORR (objective response rate), DOR (duration of response), DCR (disease control rate)
• Quality: ECOG performance status, symptom burden
• Safety: Adverse events, dose modifications

Statistical Methods

• Survival analysis: Kaplan-Meier curves, log-rank tests
• Group comparisons: t-tests, chi-square, Fisher's exact
• Effect sizes: Hazard ratios, odds ratios with 95% CI
• Significance: p-values, multiple testing corrections

Evidence Grading

GRADE System

• 1A: Strong recommendation, high-quality evidence
• 1B: Strong recommendation, moderate-quality evidence
• 2A: Weak recommendation, high-quality evidence
• 2B: Weak recommendation, moderate-quality evidence
• 2C: Weak recommendation, low-quality evidence

Recommendation Strength

• Strong: Benefits clearly outweigh risks
• Conditional: Trade-offs exist, patient values important
• Research: Insufficient evidence, clinical trials needed

Best Practices

For Cohort Analyses

1. Patient Selection Transparency: Clearly document inclusion/exclusion criteria, patient flow, and reasons for exclusions
2. Biomarker Clarity: Specify assay methods, platforms (e.g., FoundationOne, Caris), cut-points, and validation status
3. Statistical Rigor:
   • Report hazard ratios with 95% confidence intervals, not just p-values
   • Include median follow-up time for survival analyses
   • Specify statistical tests used (log-rank, Cox regression, Fisher's exact)
   • Account for multiple comparisons when appropriate
4. Outcome Definitions: Use standard criteria:
   • Response: RECIST 1.1, iRECIST for immunotherapy
   • Adverse events: CTCAE version 5.0
   • Performance status: ECOG or Karnofsky
5. Survival Data Presentation:
   • Median OS/PFS with 95% CI
   • Landmark survival rates (6-month, 12-month, 24-month)
   • Number at risk tables below Kaplan-Meier curves
   • Censoring clearly indicated
6. Subgroup Analyses: Pre-specify subgroups; clearly label exploratory vs pre-planned analyses
7. Data Completeness: Report missing data and how it was handled

For Treatment Recommendation Reports

1. Evidence Grading Transparency:
   • Use GRADE system consistently (1A, 1B, 2A, 2B, 2C)
   • Document rationale for each grade
   • Clearly state quality of evidence (high, moderate, low, very low)
2. Comprehensive Evidence Review:
   • Include phase 3 randomized trials as primary evidence
   • Supplement with phase 2 data for emerging therapies
   • Note real-world evidence and meta-analyses
   • Cite trial names (e.g., KEYNOTE-189, CheckMate-227)
3. Biomarker-Guided Recommendations:
   • Link specific biomarkers to therapy recommendations
   • Specify testing methods and validated assays
   • Include FDA/EMA approval status for companion diagnostics
4. Clinical Actionability: Every recommendation should have clear implementation guidance
5. Decision Algorithm Clarity: TikZ flowcharts should be unambiguous with clear yes/no decision points
6. Special Populations: Address elderly, renal/hepatic impairment, pregnancy, drug interactions
7. Monitoring Guidance: Specify safety labs, imaging, and frequency
8. Update Frequency: Date recommendations and plan for periodic updates

General Best Practices

1. First Page Executive Summary (MANDATORY):
   • ALWAYS create a complete executive summary on page 1 that spans the entire first page
   • Use 3-5 colored tcolorbox elements to highlight key findings
   • No table of contents or detailed sections on page 1
   • Use \thispagestyle{empty} and end with \newpage
   • This is the single most important page - it should be scannable in 60 seconds
2. De-identification: Remove all 18 HIPAA identifiers before document generation (Safe Harbor method)
3. Regulatory Compliance: Include confidentiality notices for proprietary pharmaceutical data
4. Publication-Ready Formatting: Use 0.5in margins, professional fonts, color-coded sections
5. Reproducibility: Document all statistical methods to enable replication
6. Conflict of Interest: Disclose pharmaceutical funding or relationships when applicable
7. Visual Hierarchy: Use colored boxes consistently (blue=data, green=biomarkers, yellow/orange=recommendations, red=warnings)

References

See the references/ directory for detailed guidance on:

• Patient cohort analysis and stratification methods
• Treatment recommendation development
• Clinical decision algorithms
• Biomarker classification and interpretation
• Outcome analysis and statistical methods
• Evidence synthesis and grading systems

Templates

See the assets/ directory for LaTeX templates:

• cohort_analysis_template.tex - Biomarker-stratified patient cohort analysis with statistical comparisons
• treatment_recommendation_template.tex - Evidence-based clinical practice guidelines with GRADE grading
• clinical_pathway_template.tex - TikZ decision algorithm flowcharts for treatment sequencing
• biomarker_report_template.tex - Molecular subtype classification and genomic profile reports
• evidence_synthesis_template.tex - Systematic evidence review and meta-analysis summaries

Template Features:

• 0.5in margins for compact presentation
• Color-coded recommendation boxes
• Professional tables for demographics, biomarkers, outcomes
• Built-in support for Kaplan-Meier curves, waterfall plots, forest plots
• GRADE evidence grading tables
• Confidentiality headers for pharmaceutical documents

Scripts

See the scripts/ directory for analysis and visualization tools:

• generate_survival_analysis.py - Kaplan-Meier curve generation with log-rank tests, hazard ratios, 95% CI
• create_waterfall_plot.py - Best response visualization for cohort analyses
• create_forest_plot.py - Subgroup analysis visualization with confidence intervals
• create_cohort_tables.py - Demographics, biomarker frequency, and outcomes tables
• build_decision_tree.py - TikZ flowchart generation for treatment algorithms
• biomarker_classifier.py - Patient stratification algorithms by molecular subtype
• calculate_statistics.py - Hazard ratios, Cox regression, log-rank tests, Fisher's exact
• validate_cds_document.py - Quality and compliance checks (HIPAA, statistical reporting standards)
• grade_evidence.py - Automated GRADE assessment helper for treatment recommendations