New algorithm optimizes clinical prediction models by factoring in variable costs

Researchers have developed a new algorithm for selecting variables in clinical prediction models that incorporates the costs and harms associated with measuring each variable. This decision-analytic approach, implemented in the R package NBvarsel, aims to optimize clinical utility by ensuring that the added benefit of a variable's predictiveness outweighs the reduction in net benefit from its measurement. The method was tested on simulated and real-world case studies, demonstrating its ability to generate parsimonious models that enhance clinical utility while minimizing unnecessary burden and costs. AI

IMPACT This research could lead to more efficient and cost-effective clinical prediction models by reducing unnecessary data collection.

RANK_REASON The cluster contains a research paper detailing a new methodology for variable selection in prediction models. [lever_c_demoted from research: ic=1 ai=0.4]

Read on arXiv stat.ML →

• lasso
• NBvarsel
• R

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →