Article

What the Doctor Didn’t Order: Informative Missingness as a Clinical Signal in ICU Prediction Models

2026-06-15

Abstract excerpt

<h4>Objective: </h4> Clinical prediction models treat missing data as noise to be imputed. In intensive care, missingness is not random—whether a physician orders a serum lactate or places an arterial line reflects diagnostic reasoning, workflow protocols, and institutional practice. We quantified how much predictive information resides only in the pattern of which measurements were obtained, entirely independent...

Topics

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

Identifiers and source

Literature Corpus work: 679f19f4-c566-5618-9b2c-37970ce29d6f
DOI: 10.20944/preprints202606.1130.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

What the Doctor Didn’t Order: Informative Missingness as a Clinical Signal in ICU Prediction ModelsDOI 10.20944/preprints202606.1130.v1Read

Laboratory test-ordering patterns carry an early prognostic signal in electronic health recordsSemantic proximity Read

Observation-process features are associated with larger domain shift in sepsis mortality prediction: a cross-database evaluation using MIMIC-IV and eICU-CRDSemantic proximity Read

Falsification Testing of Sepsis Prediction Models: Evaluating Independent Biological Signal After Controlling for Care-Process IntensitySemantic proximity Read

Machine learning outperforms state-of-the-art continuous vital sign monitoringSemantic proximity Read

XU-NetI: Simple U-Shaped Encoder-Decoder Network for Accurate Imputation of Multivariate Missing DataSemantic proximity Read

Demonstrating the Consequences of Learning Missingness Patterns in Early Warning Systems for Preventative Health Care: A Novel Simulation and SolutionSemantic proximity Read

Auditing missingness and input-outcome circularity in unsupervised clinical phenotyping: an empirical case study in hospitalized traumatic brain injurySemantic proximity Read

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

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

Prediction of postoperative infections by strategic data imputation and explainable machine learningSemantic proximity Read

The Causal Artificial Intelligence Clinician for early haemodynamic management of septic shock in ICUSemantic proximity Read