Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Large language models are powerful electronic health record encoders.

NPJ digital medicine·2026

Same author

Effectiveness of Interruptive Clinical Decision Support Alerts on Intravenous vs. Oral Acetaminophen Prescribing.

Applied clinical informatics·2026

Same author

Assessing the effects of fluids and antibiotics in an acute murine model of sepsis: study protocol for the National Preclinical Sepsis Platform-01 (NPSP-01) Study.

F1000Research·2026

Same author

Sample-Specific Debiasing for Better Image-Text Models.

Proceedings of machine learning research·2026

Same author

Protocol for multi-organ isolation of murine leukocytes for flow cytometry.

STAR protocols·2026

Same author

Using Multiple Instance Learning to Build Multimodal Representations.

Information processing in medical imaging : proceedings of the ... conference·2025

Search research articles

Related Experiment Video

Updated: Mar 22, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Electronic medical record phenotyping using the anchor and learn framework.

Yoni Halpern¹, Steven Horng², Youngduck Choi³

¹Department of Computer Science, New York University, New York, NY, USA dsontag@cs.nyu.edu.

Journal of the American Medical Informatics Association : JAMIA

|April 24, 2016

Summary

This summary is machine-generated.

Learning with anchors efficiently creates patient phenotypes from electronic medical records (EMRs) for real-time clinical decision support. This method requires minimal manual input and yields interpretable, fast-to-build phenotypes comparable to traditional approaches.

Keywords:

clinical decision support systems electronic health records knowledge representation machine learning natural language processing

More Related Videos

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

Related Experiment Videos

Last Updated: Mar 22, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Identification and Classification of Position-specific GABAA Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Identification and Classification of Position-specific GABA_A Receptor Subunit Missense Variants for Their Role In Hippocampal Pyramidal Neurons

Published on: June 6, 2025

Area of Science:

Health Informatics
Clinical Decision Support
Machine Learning in Healthcare

Background:

Electronic medical records (EMRs) contain rich patient data crucial for personalized care.
As medicine advances, patient phenotypes derived from EMRs are vital for real-time clinical decision support systems.
Learning with anchors offers an efficient method for developing statistically driven phenotypes with reduced manual effort.

Purpose of the Study:

To develop a phenotype library using both structured and unstructured EMR data for real-time clinical decision support.
To evaluate the performance of developed phenotype classifiers using retrospective EMR data.

Main Methods:

Developed a phenotype library incorporating 42 publicly available definitions.
Utilized structured and unstructured data from EMRs.
Evaluated eight phenotype classifiers on emergency department patient data against gold standard labels.

Main Results:

Phenotype classifiers achieved high Area Under the ROC Curve (AUC) values, with most exceeding 0.85 at triage and 0.90 at disposition.
AUC values for infection, cancer, septic shock, and pneumonia were particularly high, reaching up to 0.97.
The developed phenotypes are interpretable and rapid to construct.

Conclusions:

Learning with anchors enables the creation of interpretable and efficient phenotype definitions.
This approach performs comparably to methods requiring extensive manual labeling.
It is a promising method for building a public repository of phenotype definitions for health IT applications, including real-time decision support.