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

An Artificial Intelligence-Based Detection of Comorbid Depression, Anxiety, and Substance Use Disorder in Korean Counseling Dialogues Using an Explainable Hierarchical Attention Network with Shapley Additive Explanations.

Diagnostics (Basel, Switzerland)·2026
Same author

Digital Gait Biomarkers for Parkinson's Disease: Subject-Wise Validated Explainable AI Framework Using Vertical Ground Reaction Force Signals.

Bioengineering (Basel, Switzerland)·2026
Same author

Limitations of MMSE in Cognitive Assessment: Revealing Latent Risk via Structural Brain Atrophy.

Life (Basel, Switzerland)·2026
Same author

Indole-3-propionic Acid Is an Endogenous Agonist of TAS2R38.

Journal of agricultural and food chemistry·2026
Same author

Uncovering a Glaucoma-Linked Lysophosphatidic Acid-MAPK/AP-1 Fibrosis Axis in Human Trabecular Meshwork Cells and Its Modulation by <i>Diospyros kaki</i> Leaf Extract.

International journal of molecular sciences·2026
Same author

Implementation of a Stress Biomarker and Development of a Deep Neural Network-Based Multi-Mental State Classification Model.

Bioengineering (Basel, Switzerland)·2025

Related Experiment Video

Updated: May 5, 2026

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

16.7K

Research on Threshold Optimization and Variability-Based Digital Biomarker Approaches Through MMSE-Lifelog Multimodal

Yeeun Park1, Jin-Hyoung Jeong2

  • 1Department of Electronic and Communication Engineering, Catholic Kwandong University, Gangneung-si 25601, Republic of Korea.

Healthcare (Basel, Switzerland)
|May 4, 2026
PubMed
Summary

This study introduces a new screening method for cognitive impairment by combining Mini-Mental State Examination (MMSE) scores with wearable data. Optimizing thresholds improves accuracy for detecting cognitive decline.

Keywords:
digital biomarkermild cognitive impairmentthreshold optimization

More Related Videos

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

3.8K
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

7.0K

Related Experiment Videos

Last Updated: May 5, 2026

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
10:28

Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease

Published on: July 24, 2019

16.7K
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

3.8K
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

7.0K

Area of Science:

  • Neuroscience
  • Gerontology
  • Biomedical Engineering

Background:

  • Early detection of cognitive impairment is crucial for effective intervention.
  • Conventional cognitive tests like the Mini-Mental State Examination (MMSE) may have suboptimal fixed thresholds for real-world screening.
  • Integrating diverse data sources can enhance screening accuracy.

Purpose of the Study:

  • To develop a multimodal screening framework for cognitive impairment.
  • To integrate item-level MMSE scores with wearable-derived sleep and physical activity data.
  • To optimize decision thresholds for improved screening performance.

Main Methods:

  • A dataset of 174 adults was analyzed, categorized into cognitively normal (CN) and impaired groups.
  • A CatBoost classification model was trained using five-fold cross-validation.
  • Optimal decision thresholds were determined by maximizing balanced accuracy on out-of-fold predictions.

Main Results:

  • The optimized threshold (0.49) yielded an accuracy of 0.818 and balanced accuracy of 0.728.
  • Recall for CN was 0.885, and for the impaired group was 0.571, with an AUC of 0.676.
  • Variability-related sleep and activity features were consistently important across model training folds.

Conclusions:

  • Threshold optimization and multimodal data integration can enhance the interpretability of cognitive impairment screening.
  • Lifelog data, particularly variability metrics, may offer complementary insights to traditional cognitive assessments.
  • Further validation in larger, longitudinal studies is needed to confirm the role of lifelog features.