Develops a decision-analytic variable selection algorithm based on net benefit for clinical prediction models.
This paper introduces a novel approach to variable selection that considers the cost of misclassifications and the harm of measuring variables, unlike traditional statistical approaches.
Before reading this…
Applications
To understand this paper, make sure you know these concepts first:
Objective: Variable selection for clinical prediction models is commonly done on statistical grounds related to model fit. Statistical approaches ignore the cost of misclassifications and the harm of measuring a variable. We aim to develop a decision-analytic variable selection algorithm based on net benefit. Materials and Methods: The proposed algorithm selects the set of predictors by exhaustively comparing the net benefit of all combinations using cross validation, with an extension based on backward elimination for settings with many predictors. Variables are selected if the increased net benefit from better predictiveness exceeds the net benefit reduction from the harm of variable measurement. Harm includes financial expense, time, resource allocation, and patient burden. We illustrate the algorithm through a simulated example and three real case studies. We compare its performance to traditional backward elimination and LASSO. Results: Across the case studies, parsimonious models were generated that optimized clinical utility with minimal impact on discrimination and calibration. Penalizing predictors based on their cost ensured that expensive or burdensome variables were only selected if they offer sufficient clinical utility. The algorithm was implemented in the R package NBvarsel. Discussion: Decision-analytic variable selection allows prediction models to maximize patient benefit while minimizing unnecessary clinical burden and costs. Conclusion: Clinical utility should not be an afterthought reserved only for implementation. By integrating a harm-adjusted net benefit metric directly into the variable selection process, NBvarsel allows researchers to select only the variables that sufficiently improve clinical utility.
Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical R…
Proposes a reinforcement learning framework for precision recall controllable au…
Bridging the Post-discharge Gap: A Traceable Multi-agent Framework for Safe and Continuous Care
Healink is a memory-enhanced multi-agent framework that supports AI-assisted pos…
Glyph: An Interpretability Engine for AI-Driven Scientific Discovery in Clinical Data
This paper introduces Glyph, a framework that extracts features from clinical da…
Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explaina…
This paper adapts a decision foundation model for disease classification from pa…
A prospective randomized study of patient-centered AI for clinical visit preparation
A large language model-based chatbot improved patient visit preparation and sati…
Optimizing Physical Neural Networks through Device Variable Selection
This paper improves the efficiency and accuracy of physical neural networks by l…
Null-Calibrated Conformal Selection via Target-Membership Scores
This paper proposes a new approach to conformal selection that uses target-membe…
PHAST-Net: Attention-Guided, Physics-Informed Network for Unified Estimation of Ideal Time-Frequency…
PHAST-Net is an attention-guided, physics-informed network for unified estimatio…