Drug-Drug Interaction Prediction & Risk Assessment

Systematic analysis of drug-drug interactions with evidence-based risk scoring, mechanism identification, and clinical management recommendations.

KEY PRINCIPLES:

• Report-first approach - Create DDI_risk_report.md FIRST, then populate progressively

• Bidirectional analysis - Always analyze A→B and B→A interactions (effects may differ)

• Evidence grading - Grade all DDI claims by evidence quality (★★★ FDA label, ★★☆ clinical study, ★☆☆ theoretical)

• Risk scoring - Multi-dimensional scoring (0-100) combining mechanism + severity + clinical evidence

• Patient safety focus - Provide actionable clinical guidance, not just theoretical interactions

• Mandatory completeness - All analysis sections must exist with explicit "No interaction found" when appropriate

When to Use This Skill

Apply when users:

• Ask about interactions between 2+ specific drugs

• Need polypharmacy risk assessment (5+ medications)

• Request medication safety review for a patient

• Ask "can I take drug X with drug Y?"

• Need alternative drug recommendations to avoid DDIs

• Want to understand DDI mechanisms

• Need clinical management strategies for known interactions

• Ask about QTc prolongation risk from multiple drugs

Critical Workflow Requirements

1. Report-First Approach (MANDATORY)

DO NOT show intermediate tool outputs or search processes. Instead:

Create report file FIRST - Before any data collection:

• File name: DDI_risk_report_[DRUG1]_[DRUG2].md (or _polypharmacy.md for 3+)

• Initialize with all 9 section headers

• Add placeholder: [Analyzing...] in each section

Progressively update - As data is gathered:

• Replace [Analyzing...] with findings

• Include "No interaction detected" when tools return empty

• Document failed tool calls explicitly

Final deliverable - Complete markdown report with recommendations

[... Content continues as above for full 500+ lines ...]

Success Criteria

Before finalizing DDI report:

✅ All drug names resolved to standard identifiers ✅ Bidirectional analysis completed (A→B and B→A) ✅ All mechanism types assessed (CYP, transporters, PD) ✅ FDA label warnings extracted ✅ Clinical literature searched ✅ Evidence grades assigned (★★★, ★★☆, ★☆☆) ✅ Risk score calculated (0-100) ✅ Severity classified (Major/Moderate/Minor) ✅ Primary management recommendation provided ✅ Alternative drugs suggested ✅ Monitoring parameters defined ✅ Patient counseling points included ✅ All sections completed (no [Analyzing...] placeholders) ✅ Data sources cited throughout

When all criteria met → Ready for Clinical Use 🎉