Article

PORT: Generative EHR Pretraining for Pediatric Intraoperative Risk Prediction

2026-08-12

Abstract excerpt

<title>Abstract</title> <p>Pediatric intraoperative deterioration (IoD) is a rare, high-consequence event with no validated pre-operative risk model. We developed PORT (Pediatric Operative Risk Transformer), a decoder-only transformer pretrained on perioperative electronic health record (EHR) timelines and adapted with low-rank adaptation, to predict IoD from pre-operative data. We studied a single-center retrosp...

Topics

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

Identifiers and source

Literature Corpus work: 1c64a6dc-2c9c-507e-9744-98ead3f4fbf0
DOI: 10.21203/rs.3.rs-10609619/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

PORT: Generative EHR Pretraining for Pediatric Intraoperative Risk PredictionDOI 10.21203/rs.3.rs-10609619/v1Read

Application of Foundation Models in Emergency and Critical Care: A Scoping ReviewSemantic proximity Read

GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary Bypass<sup>2</sup>Semantic proximity Read

GenAI Exceeds Clinical Experts in Predicting Acute Kidney Injury following Paediatric Cardiopulmonary BypassSemantic proximity Read

Enformer: An encoder-decoder generative model to enhance prediction of disease outcomes using electronic health recordsSemantic proximity Read

EDBERT: Predicting Emergency Department Disposition Using A BERT-Based ArchitectureSemantic proximity Read

EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution ShiftSemantic proximity Read

Predicting Hospital Admissions Using Pretrained EHR Embeddings: External Evaluation and Insights on Local Vocabulary AdaptationSemantic proximity Read

Deep Representation Learning for Risk Prediction in Electronic Health Records Using Self-Supervised MethodsSemantic proximity Read

Developing Deep Learning Continuous Risk Models for Early Adverse Event Prediction in Electronic Health Records: an AKI Case StudySemantic proximity Read

Cadence: A Benchmark Evaluation of the Narrative Velocity Framework for Next Clinical Event Prediction in MIMIC-IVSemantic proximity Read

Evaluation of a Generative Medical Event Foundation Model for Predicting Post-Discharge Trajectories in Emergency Department Abdominal PainSemantic proximity Read

ExCaPT: Explainable Cancer Prediction with Transformer-based modelsSemantic proximity Read