Article

Contrastive Transformer-Driven Discovery of Temporal Hemodynamic Subphenotypes in Cardiac Surgery Patients

2026-03-30

Abstract excerpt

Cardiac surgery patients experience rapidly evolving hemodynamics in early post-operative period requiring intensive support. Identifying hemodynamic subphenotypes from these data can inform personalized management. Using 24-hour high-resolution physiologic and treatment data from 6,630 MIMIC-IV and 1,963 SICdb patients, we trained a transformer encoder with a reconstruction-contrastive objective to derive patient...

Topics

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

Identifiers and source

Literature Corpus work: f9fc25b4-9139-5936-b946-daa456687322
DOI: 10.64898/2026.03.27.26349519

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Contrastive Transformer-Driven Discovery of Temporal Hemodynamic Subphenotypes in Cardiac Surgery PatientsDOI 10.64898/2026.03.27.26349519Read

Cardiovascular and Autonomic Phenotypes Reveal Distinct Mechanisms of Sepsis Decompensation via Deep LearningSemantic proximity Read

Physiology-Informed Digital Twin-AI Framework Predicts Pacing Therapy Response in HFpEFSemantic proximity Read

Identifying acute illness phenotypes via deep temporal interpolation and clustering network on physiologic signaturesSemantic proximity Read

Early heart-rate trajectory phenotypes predict short-term mortality in critically ill patients: a dynamic time-warping cluster analysis.Semantic proximity Read

Deep Learning Identifies Novel Subphenotypes of Multiple Organ Dysfunction Syndrome in Critical CareSemantic proximity Read

Identifying Cardiogenic Shock Sub-Phenotypes with Machine Learning: A Multicenter Study Combining Clinical and Echocardiographic DataSemantic proximity Read

Unsupervised Cluster-Augmented Mortality Prediction in MIMIC-IV Using Tabular ICU Time-Series Aggregation and Gradient Boosted LearningSemantic proximity Read

Development and Prospective Validation of Predictive Model for Early Hemodynamic Deterioration in Critical Care: A Multicenter StudySemantic proximity Read

Identifying acute illness phenotypes via deep temporal interpolation and clustering network on physiologic signatures.Semantic proximity Read

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

Leveraging Explainable Temporal-Modelling Machine Learning to Identify Distinct Multimorbidity Trajectory Profiles in Acute Myocardial InfarctionSemantic proximity Read

Representation-first transformer semantic phenotyping reveals hidden burden heterogeneity in adult congenital heart diseaseSemantic proximity Read