Article

Ranking-optimized survival models can underperform fixed-horizon clinical prediction

2026-06-16

Abstract excerpt

Machine-learning survival models are increasingly proposed for intensive-care mortality prediction and are usually judged by the concordance index, a ranking metric averaged over follow-up. Yet many bedside decisions require a probability at a specific time, such as 60- or 180-day mortality. We asked whether ranking-optimized models perform competitively at fixed clinical horizons when compared with attending-phys...

Topics

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

Identifiers and source

Literature Corpus work: 57f988c2-d42c-5615-8b10-1e80df27190c
DOI: 10.64898/2026.06.13.26355565

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Ranking-optimized survival models can underperform fixed-horizon clinical predictionDOI 10.64898/2026.06.13.26355565Read

The Deferral Frontier: Reliability-Gated Selective Prediction for Clinical AISemantic proximity Read

Reference-Class Failure in Mortality Prediction: A Synthetic Study of Irreducible Uncertainty in End-of-Life Prognostic ModelsSemantic proximity Read

A validation of machine learning-based risk scores in the prehospital settingSemantic proximity Read

Deployment-readiness audit of calibration, clinical utility, and fairness in perioperative infection predictionSemantic proximity Read

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

Optimally Predicting Mortality in Patients with Abdominal Aortic AneurysmsSemantic proximity Read

Deep Learning with Diverse Objectives Improves ARDS PredictionSemantic proximity Read

First-24-hour machine learning for 30-day mortality prediction in ICU trauma patients: development in MIMIC-III and cross-database evaluation in MIMIC-IVSemantic proximity Read

Modeling strategies for a flexible estimation of the crude cumulative incidence in the context of long follow-ups: model choice and predictive ability evaluationSemantic proximity Read

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

Efficient Adverse Event Forecasting in Clinical Trials via Transformer-Augmented Survival AnalysisSemantic proximity Read

Algorithmic Fairness and Bias Mitigation for Clinical Machine Learning: Insights from Rapid COVID-19 Diagnosis by Adversarial LearningSemantic proximity Read