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

Deep learning-based arterial waveform analysis for predicting postoperative cerebrovascular events in pediatric patients with Moyamoya disease.

PloS one·2026
Same author

Physician behavior for "invisible" treatment; Korean herbal medicine doctor's treatment covered by auto insurance.

PloS one·2026
Same author

The Central Role of Neuronal Cell Death in Alzheimer's Disease Pathobiology.

Biomedicines·2026
Same author

Validity and Reliability of the InGrip<sup>®</sup> Load-Cell Handgrip Dynamometer Compared With the Takei Handgrip Dynamometer in Healthy Adults and Patients With Stroke.

Journal of Korean medical science·2026
Same author

Deep Learning outperforms physicians in myopathy and neuropathy classification based on Needle Electromyography Signal.

PloS one·2026
Same author

Aromatic interactions surrounding the Asp-X-Glu motif stabilize the active site of HYAL1 and PH20.

Biochimica et biophysica acta. Proteins and proteomics·2026

Related Experiment Video

Updated: Aug 27, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.4K

A machine learning approach for predicting suicidal ideation in post stroke patients.

Seung Il Song1, Hyeon Taek Hong2, Changwoo Lee3

  • 1Department Occupational Therapy, Gumi University, Yaeun-ro 37, Gumi, 39213, South Korea.

Scientific Reports
|September 23, 2022
PubMed
Summary

Identifying stroke patients at high risk of suicide ideation (SI) is crucial. Machine learning models, particularly CatBoost, accurately predict SI using clinical data, improving objective risk assessment for stroke survivors.

More Related Videos

A Middle Cerebral Artery Occlusion Technique for Inducing Post-stroke Depression in Rats
04:38

A Middle Cerebral Artery Occlusion Technique for Inducing Post-stroke Depression in Rats

Published on: May 22, 2019

10.4K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.6K

Related Experiment Videos

Last Updated: Aug 27, 2025

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment
05:19

Author Spotlight: Therapeutic Benefit of Closed-Loop Deep Brain Stimulation in Depression Treatment

Published on: July 7, 2023

2.4K
A Middle Cerebral Artery Occlusion Technique for Inducing Post-stroke Depression in Rats
04:38

A Middle Cerebral Artery Occlusion Technique for Inducing Post-stroke Depression in Rats

Published on: May 22, 2019

10.4K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

7.6K

Area of Science:

  • Neuroscience
  • Psychiatry
  • Data Science

Background:

  • Current suicide ideation (SI) identification in stroke patients relies on subjective self-report questionnaires.
  • This subjective approach lacks objectivity and may fail to identify at-risk individuals effectively.

Purpose of the Study:

  • To develop and validate a machine learning-based suicide ideation (SI) prediction model for stroke patients.
  • To identify key clinical predictors of SI in this population.
  • To compare the performance of different machine learning models for SI prediction.

Main Methods:

  • Retrospective analysis of clinical data from 385 stroke patients (October 2012 - March 2014).
  • Traditional statistical analysis to select significant demographic and functional variables (age, onset, type, socioeconomic status, education, ADL, emotion).
  • Application and comparison of three boosting models: XGBoost, CatBoost, and LightGBM (LGBM).

Main Results:

  • The CatBoost model demonstrated superior performance with an accuracy of 0.900.
  • Key predictors of SI included depression, anxiety, self-efficacy, and rehabilitation motivation.
  • Depression and anxiety showed a positive correlation with SI, while self-efficacy and motivation showed an inverse relationship.

Conclusions:

  • Machine learning models, especially CatBoost, offer an objective and effective approach to predicting SI in stroke patients.
  • Identifying psychological factors like depression, anxiety, and self-efficacy is vital for SI prevention in stroke survivors.
  • These models can assist healthcare professionals in identifying high-risk patients for timely SI prevention interventions.