Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

Surgical Outcomes of Perioperative Toripalimab in Stage III Resectable Non-Small Cell Lung Cancer: Post Hoc Analysis of the Neotorch Randomized Clinical Trial.

JAMA surgery·2026
Same author

A web-based two-stage prediction model for postoperative pulmonary complications using preoperative and intraoperative data.

Journal of anesthesia and translational medicine·2026
Same author

Predictive accuracy of a perioperative hemodynamic indices-based prediction model for moderate-to-severe acute kidney injury after orthotopic heart transplantation.

Surgery·2026
Same author

An Interpretable PK-Informed Hybrid Model for Voriconazole Exposure Prediction: Roles of CYP2C19 Genotype and Inflammation.

Drug design, development and therapy·2026
Same author

Identification of plasma exosomal VPS41 chr7:38764322A>I editing as a diagnostic biomarker in lung cancer via a pan-cancer screen.

Respiratory research·2026
Same author

Development and validation of an interpretable machine learning model for predicting in-hospital hypoglycemia in adults with type 1 diabetes mellitus: a multicenter retrospective study.

Frontiers in endocrinology·2026

Related Experiment Video

Updated: Oct 13, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

1.8K

Using machine learning to predict atrial fibrillation diagnosed after ischemic stroke.

Xiaohan Zheng1, Fusang Wang1, Juan Zhang2

  • 1School of Basic Medicine and Clinical Pharmacy, China Pharmaceutical University, Nanjing, China; Department of Clinical Pharmacology, Nanjing First Hospital, Nanjing Medical University, Nanjing, China.

International Journal of Cardiology
|November 14, 2021
PubMed
Summary

A deep neural network model effectively identifies acute ischemic stroke patients at high risk for poststroke atrial fibrillation, improving cardiac monitoring selection compared to traditional scores.

Keywords:
Atrial fibrillationIschemic strokeMachine learningPredict

More Related Videos

The WATCHMAN Left Atrial Appendage Closure Device for Atrial Fibrillation
23:33

The WATCHMAN Left Atrial Appendage Closure Device for Atrial Fibrillation

Published on: February 28, 2012

83.9K
Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
28:13

Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation

Published on: February 26, 2013

33.6K

Related Experiment Videos

Last Updated: Oct 13, 2025

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

1.8K
The WATCHMAN Left Atrial Appendage Closure Device for Atrial Fibrillation
23:33

The WATCHMAN Left Atrial Appendage Closure Device for Atrial Fibrillation

Published on: February 28, 2012

83.9K
Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation
28:13

Catheter Ablation in Combination With Left Atrial Appendage Closure for Atrial Fibrillation

Published on: February 26, 2013

33.6K

Area of Science:

  • Neurology
  • Cardiology
  • Artificial Intelligence

Background:

  • Identifying acute ischemic stroke (AIS) patients needing prolonged cardiac monitoring for poststroke atrial fibrillation (AF) remains difficult.
  • Traditional risk scores and logistic regression have limitations in predicting AF risk accurately.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for predicting poststroke AF in AIS patients.
  • To compare the performance of the ML model against established risk scores and logistic regression.

Main Methods:

  • Utilized data from 3929 AIS patients (July 2012-September 2020).
  • Employed LASSO regression for feature selection and built five ML models, including deep neural network (DNN).
  • Interpreted the optimal model using SHAP and partial dependence plots (PDP), comparing against CHADS₂, CHA₂DS₂-VASc, AS5F, HAVOC scores, and classic logistic regression.

Main Results:

  • The DNN model demonstrated the best performance among the five ML models.
  • DNN significantly outperformed traditional risk scores and classic logistic regression in predicting poststroke AF.
  • Key predictors identified by SHAP/PDP include age, cardioembolic stroke, large-artery atherosclerosis stroke, and NIHSS score.

Conclusions:

  • The DNN model offers superior predictive performance for poststroke AF compared to existing methods.
  • This ML model can reliably identify high-risk AIS patients for targeted prolonged cardiac monitoring.