Article

Clinician-Informed Feature Engineering Improves Machine Learning Assignment of Molecular Endotypes in the Intensive Care Unit

2026-04-07

Abstract excerpt

<h4>Objective</h4> To develop a workflow that transforms electronic health record data into machine learning-ready features for molecular endotype assignment and to evaluate whether clinician-informed feature engineering improves model performance and interpretability. <h4>Materials and Methods</h4> We developed parallel clinician-informed and clinician-agnostic feature engineering pipelines to prepare raw EHR d...

Topics

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

Identifiers and source

Literature Corpus work: 211e79e3-33c3-521d-b895-8522ce7fd197
DOI: 10.64898/2026.04.06.26350248

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Clinician-Informed Feature Engineering Improves Machine Learning Assignment of Molecular Endotypes in the Intensive Care UnitDOI 10.64898/2026.04.06.26350248Read

Calibrated and Interpretable Machine Learning for ICU Mortality Prediction Using First 24-Hour Clinical DataSemantic proximity Read

Application of concise machine learning to construct accurate and interpretable EHR computable phenotypesSemantic proximity Read

Predicting Respiratory Decompensation in Mechanically Ventilated Adult ICU PatientsSemantic proximity Read

Machine Learning Classifier Models Can Identify Acute Respiratory Distress Syndrome Phenotypes Using Readily Available Clinical Data.Semantic proximity Read

GPT-4o and the Quest for Machine Learning Interpretability in ICU Mortality PredictionSemantic proximity Read

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

Machine learning for predicting clinical outcomes in emergency department patients with acute respiratory infections: A scoping reviewSemantic proximity Read

Hybrid phenotype-guided modeling across algorithm-feature regimes with application to ICU mortality prediction for Acinetobacter baumannii.Semantic proximity Read

Risk assessment of acute respiratory failure requiring advanced respiratory support using machine learningSemantic proximity Read

Clinical utility of automatic phenotype annotation in unstructured clinical notes: intensive care unit use.Semantic proximity Read

Leveraging Expert Knowledge and Causal Structure Learning to Build Parsimonious Models of Acute Brain Dysfunction in the Pediatric Intensive Care Unit (PICU)Semantic proximity Read

Electronic medical record phenotyping using the anchor and learn framework.Semantic proximity Read