Article

The Deferral Frontier: Reliability-Gated Selective Prediction for Clinical AI

2026-06-02

Abstract excerpt

<title>Abstract</title> <p>Selective prediction in clinical AI conventionally defers low-confidence predictions to human clinicians. But confidence captures only one dimension of prediction quality, and the patients it flags may not be the ones who most need human review. We propose reliability-gated selective prediction, where a composite of five dimensions—confidence, data sufficiency, cohort similarity, tempor...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 73b5b0a1-1f8c-59d7-bedd-eadb13184ff6
DOI: 10.21203/rs.3.rs-9887494/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

The Deferral Frontier: Reliability-Gated Selective Prediction for Clinical AIDOI 10.21203/rs.3.rs-9887494/v1Read

A Simulation-Based Validation Framework for Uncertainty-Aware Clinical Triage: Conformal Prediction and Ensemble Learning Applied to a Synthetic ICU Benchmark CohortSemantic proximity Read

Operationalizing Trustworthy AI: A Scalable Framework for Granular Error Analysis and Bias Mitigation in Healthcare ModelsSemantic proximity Read

CardioTrust: Trustworthy Retrieval Augmented Clinical Decision Support for Personalized Cardiovascular Disease PredictionSemantic proximity Read

Retrieval-aligned Tabular Foundation Models Enable Robust Clinical Risk Prediction in Electronic Health Records Under Real-world ConstraintsSemantic proximity Read

Clinical Risk-Weighted Evaluation of ICU Mortality Prediction Models on MIMIC-IVSemantic proximity Read

Development and External Validation of a High-Precision Model for Predicting ICU Admission from Emergency Department TriageSemantic proximity Read

Predicting Annotation Yield in Artificial Intelligence-Ranked Electronic Health Record Cohorts: A Regression-Based Framework for Efficient Manual ReviewSemantic proximity Read

Trustworthy LLM-Embedding Clinical Prediction: Calibrating Confidence and Transparency for Foundation Model-Based Disease Risk ScoresSemantic proximity Read

A Foundation Model for Intensive Care: Unlocking Generalization across Tasks and Domains at ScaleSemantic proximity Read

Cultryx: Precision Diagnostic Stewardship for Blood Cultures Using Machine LearningSemantic proximity Read

Generalisability of AI-based scoring systems in the ICU: a systematic review and meta-analysisSemantic proximity Read

Does Model Compression Amplify Clinical Bias? A Subgroup Fairness Audit of Quantized ICU Risk Models on MIMIC-IVSemantic proximity Read