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

Variability in epilepsy polygenic risk prediction across Taiwanese population and clinical cohorts.

Epilepsia·2026

Same author

Machine learning prediction of long-term postoperative pneumonia risk: a retrospective cohort study.

BMC medical informatics and decision making·2026

Same author

Site-Specific Olfactory Cleft Opacification Predicts Olfactory Function and Olfactory Training Outcome in Persistent Postinfection Olfactory Dysfunction.

International forum of allergy & rhinology·2026

Same author

Modified Berlin Score for predicting sleep apnea in patients with acute ischemic stroke.

BMC neurology·2026

Same author

EV-D68 exploits clathrin-mediated endocytosis and compensatory macropinocytosis for cellular entry.

Journal of virology·2026

Same author

Speech analysis for differentiating bipolar disorder and major depressive disorder during euthymic states.

Annals of general psychiatry·2026

Same journal

Multimodal Contrastive Spatiotemporal Self-Organizing Neural Networks for In-Home Activity Learning of Mild Cognitive Impairment.

IEEE journal of biomedical and health informatics·2026

Same journal

Integrating Multi-View Residue Graph and Protein Language Model for Cell-Penetrating Peptide Prediction via Global-Local Graph Aggregation and Cross-Attentive Fusion.

IEEE journal of biomedical and health informatics·2026

Same journal

An Ultra-Lightweight Cross-scale Attention Mamba Network for Accurate Skin Lesion Segmentation.

IEEE journal of biomedical and health informatics·2026

Same journal

Explanation-Guided Reconstruction of Missing Clinical Features for Survival Prediction in Pancreatic Cancer.

IEEE journal of biomedical and health informatics·2026

Same journal

stDGCN: A dual-augmentation graph convolutional network for identifying spatial domains with attention mechanism.

IEEE journal of biomedical and health informatics·2026

Same journal

Patient-specific Biomechanical Investigation of Percutaneous Pulmonary Valves: Towards the Integration of Routinely Acquired Clinical Data and Fluid-structure Interaction Simulations.

IEEE journal of biomedical and health informatics·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 26, 2025

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

EMR-Based Phenotyping of Ischemic Stroke Using Supervised Machine Learning and Text Mining Techniques.

Sheng-Feng Sung, Chia-Yi Lin, Ya-Han Hu

IEEE Journal of Biomedical and Health Informatics

|March 7, 2020

Summary

This summary is machine-generated.

Automated phenotyping of ischemic stroke subtypes using electronic medical records (EMRs) improves accuracy. Combining structured and unstructured EMR data with machine learning enhances stroke classification for better research and patient prognostication.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Dec 26, 2025

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

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Neurology
Medical Informatics
Machine Learning in Healthcare

Background:

Ischemic stroke is a leading cause of adult death and disability globally.
Accurate phenotyping of ischemic stroke is crucial for research and prognostication due to its heterogeneous nature.
Manual phenotyping of large patient cohorts from electronic medical records (EMRs) is labor-intensive and challenging.

Purpose of the Study:

To evaluate automated strategies for phenotyping ischemic stroke into Oxfordshire Community Stroke Project subtypes.
To assess the utility of structured and unstructured data from EMRs for stroke phenotyping.
To compare the performance of various machine learning algorithms for classifying ischemic stroke subtypes.

Main Methods:

Utilized structured data from the National Institutes of Health Stroke Scale and unstructured clinical narratives from 4640 adult ischemic stroke patients.
Preprocessed clinical narratives using MetaMap to extract medical concepts and create feature vectors.
Employed supervised machine learning algorithms for classification, exploring multi-class and binary decomposition strategies.

Main Results:

Integrating textual information from EMRs with structured data significantly improved ischemic stroke phenotyping.
Decomposing the multi-class phenotyping problem into binary classification tasks enhanced classifier performance.
Machine learning models demonstrated effectiveness in automating stroke subtype classification.

Conclusions:

Automated phenotyping of ischemic stroke using combined structured and unstructured EMR data is feasible and effective.
Leveraging clinical narratives through natural language processing enhances the accuracy of stroke subtype classification.
The proposed automated approach offers a scalable solution for phenotyping large ischemic stroke populations.