Hierarchical biomarker thresholding: a model-agnostic framework for stability

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Debeaupuis, O.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918214927122432
author Debeaupuis, O.
author_facet Debeaupuis, O.
contents Many biomarker pipelines require patient-level decisions aggregated from instance-level (cell/patch) scores. Thresholds tuned on pooled instances often fail across sites due to hierarchical dependence, prevalence shift, and score-scale mismatch. We present a selection-honest framework for hierarchical thresholding that makes patient-level decisions reproducible and more defensible. At its core is a risk decomposition theorem for selection-honest thresholds. The theorem separates contributions from (i) internal fit and patient-level generalization, (ii) operating-point shift reflecting prevalence and shape changes, and (iii) a stability term that penalizes sensitivity to threshold perturbations. The stability component is computable via patient-block bootstraps mapped through a monotone modulus of risk. This framework is model-agnostic, reconciles heterogeneous decision rules on a quantile scale, and yields monotone-invariant ensembles and reportable diagnostics (e.g. flip-rate, operating-point shift).
format Preprint
id arxiv_https___arxiv_org_abs_2511_18030
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hierarchical biomarker thresholding: a model-agnostic framework for stability
Debeaupuis, O.
Methodology
Artificial Intelligence
Statistics Theory
Many biomarker pipelines require patient-level decisions aggregated from instance-level (cell/patch) scores. Thresholds tuned on pooled instances often fail across sites due to hierarchical dependence, prevalence shift, and score-scale mismatch. We present a selection-honest framework for hierarchical thresholding that makes patient-level decisions reproducible and more defensible. At its core is a risk decomposition theorem for selection-honest thresholds. The theorem separates contributions from (i) internal fit and patient-level generalization, (ii) operating-point shift reflecting prevalence and shape changes, and (iii) a stability term that penalizes sensitivity to threshold perturbations. The stability component is computable via patient-block bootstraps mapped through a monotone modulus of risk. This framework is model-agnostic, reconciles heterogeneous decision rules on a quantile scale, and yields monotone-invariant ensembles and reportable diagnostics (e.g. flip-rate, operating-point shift).
title Hierarchical biomarker thresholding: a model-agnostic framework for stability
topic Methodology
Artificial Intelligence
Statistics Theory
url https://arxiv.org/abs/2511.18030