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

Response to: Baroreflex Prognosis Requires Timing and Rhythm Context.

QJM : monthly journal of the Association of Physicians·2026

Same author

Zfand5 terminates TLR3/4 signaling and necroptosis by targeting TRIF to the proteasome for degradation.

Cell death & disease·2026

Same author

Baroreceptor Sensitivity as an Independent Predictor for Functional Outcomes in Acute Ischemic Stroke.

QJM : monthly journal of the Association of Physicians·2026

Same author

Response to comments on "Predictive machine learning algorithms for depression and anxiety disorders in six cancer types: a comprehensive multi-center population-based study".

Journal of the Formosan Medical Association = Taiwan yi zhi·2026

Same author

Influence of interhospital transfer on endovascular thrombectomy outcome in acute ischemic stroke patients: an analysis of the TREAT-AIS registry.

Frontiers in neurology·2026

Same author

ASO Visual Abstract: Comparative Outcomes and Cost-Effectiveness of Robotic Versus Laparoscopic Partial Nephrectomy: A Nationwide Population-Based Analysis in Taiwan.

Annals of surgical oncology·2026

Same journal

Explainable machine learning-based preliminary screening for viral encephalitis by blood routine analysis.

Frontiers in neurology·2026

Same journal

Global landscape of registered clinical trials of stem cell therapy for spinal cord injury: a cross-sectional analysis.

Frontiers in neurology·2026

Same journal

Experimental verification and PK/PD modeling of selective drug absorption via acupoint administration in rabbit model of rheumatoid arthritis.

Frontiers in neurology·2026

Same journal

Plasma metabolomic signatures of the no-reflow phenomenon in stroke patients following thrombectomy.

Frontiers in neurology·2026

Same journal

Parametric color-coding-derived microvascular transit time may predict infarction and reveals microcirculatory benefits of Tenecteplase in acute ischemic stroke.

Frontiers in neurology·2026

Same journal

The application of fNIRS-sEMG in the study of muscle-brain coupling.

Frontiers in neurology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 4, 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

Predicting 30-Day Readmission for Stroke Using Machine Learning Algorithms: A Prospective Cohort Study.

Yu-Ching Chen^1,2, Jo-Hsuan Chung¹, Yu-Jo Yeh¹

¹Department of Healthcare Administration and Medical Informatics, Kaohsiung Medical University, Kaohsiung, Taiwan.

Frontiers in Neurology

|July 21, 2022

Summary

This summary is machine-generated.

Artificial neural network (ANN) models accurately predict 30-day stroke readmissions, outperforming other machine learning and Cox regression models. Key predictors include post-acute care, nasogastric tube insertion, and stroke type.

Keywords:

30-day readmission artificial neural network feature importance analysis post-acute care stroke

More Related Videos

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Published on: February 22, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Related Experiment Videos

Last Updated: Sep 4, 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

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Published on: February 22, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Area of Science:

Medical Informatics
Health Services Research
Clinical Prediction Modeling

Background:

30-day readmission after stroke is a critical outcome measure.
Machine learning (ML) applications for predicting stroke readmissions are underexplored.
Identifying accurate predictors is essential for effective patient management.

Purpose of the Study:

To identify significant predictors of 30-day stroke readmission.
To compare the predictive accuracy of various ML models and Cox regression.
To evaluate the performance of artificial neural network (ANN), K nearest neighbor (KNN), random forest (RF), support vector machine (SVM), naive Bayes classifier (NBC), and Cox regression (COX) models.

Main Methods:

Prospective cohort study of 1,476 stroke patients across six hospitals (March 2014 - September 2019).
Development dataset (n=1,033), internal validation dataset (n=443), and external validation dataset (n=167) were utilized.
Feature importance analysis was conducted to identify significant input variables.

Main Results:

The ANN model demonstrated significantly superior performance (P < 0.001) in predicting 30-day stroke readmission compared to all other models.
Post-acute care (PAC), nasogastric tube insertion, and stroke type were identified as the most significant predictors by the ANN model (P < 0.05).

Conclusions:

An ANN model provides accurate estimation of 30-day stroke readmission risk.
Identifying key risk factors like PAC can enhance patient education and management strategies.
This approach improves the precision and efficacy of care for stroke survivors.