Does this skill support Time-to-Event (TTE) trials?

Yes, it includes specific patterns for event count optimization and grid searching over event counts for survival analysis and TTE designs.

What is the Joint Optimal Region in this context?

The Joint Optimal Region is a design strategy that finds a range of parameters, such as sample size, that perform optimally across multiple potential clinical scenarios simultaneously, ensuring design robustness.

How does this skill help with sample size determination?

It provides a standardized binary search algorithm to find the minimum sample size needed to meet a specific target power based on effect size and alpha constraints, automating the iterative simulation process.

What R frameworks are used in these patterns?

The patterns are designed around the Clinical Scenario Evaluation (CSE) framework, providing reusable R snippets for data modeling, analysis models, and evaluation criteria.

Can I optimize for multiple endpoints simultaneously?

Yes, the skill includes patterns for tradeoff-based optimization, allowing you to balance power between primary and secondary endpoints using weighted criteria or constrained optimization.

Power Optimization Patterns for Clinical Trials

Name: Power Optimization Patterns for Clinical Trials
Author: choxos

bychoxos

0•

データサイエンスとML

Optimizes clinical trial designs through advanced sample size determination, event count tuning, and multi-objective tradeoff analysis.

This Claude Code Skill provides specialized patterns for biostatisticians and researchers to optimize clinical trial parameters. It offers a structured framework for finding optimal sample sizes, event counts for time-to-event (TTE) trials, and balancing competing objectives using additive criteria or constrained optimization. By implementing robust sensitivity analysis and multiplicity optimization, it helps ensure that clinical designs are powered appropriately across various scenarios while maintaining statistical rigor and cost-efficiency.

主な機能

01Automated sample size determination using binary search algorithms

02Event count optimization for Time-to-Event (TTE) trial designs

03Multiplicity adjustment optimization for complex primary and secondary endpoints

04Qualitative and quantitative sensitivity analysis for design robustness

050 GitHub stars

06Tradeoff-based optimization using weighted additive criteria

ユースケース

01Balancing primary and secondary endpoint power through weight allocation optimization

02Conducting sensitivity analysis to evaluate trial design performance across optimistic and conservative scenarios

03Determining the minimum sample size required to reach a specific statistical power target

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add choxos/biostatagent power-optimization-patterns

For use in Claude.ai and ChatGPT

主な機能

01Automated sample size determination using binary search algorithms

02Event count optimization for Time-to-Event (TTE) trial designs

03Multiplicity adjustment optimization for complex primary and secondary endpoints

04Qualitative and quantitative sensitivity analysis for design robustness

050 GitHub stars

06Tradeoff-based optimization using weighted additive criteria

ユースケース

01Balancing primary and secondary endpoint power through weight allocation optimization

02Conducting sensitivity analysis to evaluate trial design performance across optimistic and conservative scenarios

03Determining the minimum sample size required to reach a specific statistical power target