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

Real-world evidence of SAINT® effectiveness in a heterogenous clinical population with psychiatric and medical comorbidities: A multicenter, open-label, community-based study.

Journal of mood and anxiety disorders·2026
Same author

Cross-Dataset Evaluation of an Automated Video-Based Model for Detecting Tardive Dyskinesia Using the Clinician's Tardive Inventory: Validation Study.

JMIR mental health·2026
Same author

Development of a Novel Self-Report Tool to Aid in the Assessment of Women's Pregnancy-Related Self-Efficacy: The Pregnancy Care Confidence Scale (PCCS).

The Journal of perinatal & neonatal nursing·2026
Same author

Psychometric evaluation of the DSM-5-TR-Level 1 Cross-Cutting Symptom Measure: transdiagnostic factor analysis in a real-world psychiatric outpatient sample.

Frontiers in psychiatry·2026
Same author

Reply to "Beyond the 'overdiagnosis' narrative: understanding adult ADHD through DSM-5".

The American journal of managed care·2026
Same author

Multimodal machine learning for video based single question mental health assessment.

NPJ digital medicine·2025

Related Experiment Video

Updated: Mar 14, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.6K

Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence.

Anthony A Sterns1,2,3,4, Joel W Hughes5, Bradley Grimm6

  • 1iRxReminder, Cleveland, Ohio.

The Journal of Clinical Psychiatry
|June 9, 2025
PubMed
Summary

An AI tool effectively detects tardive dyskinesia (TD), a movement disorder caused by antipsychotic medications. This technology offers higher accuracy than human raters, aiding in early diagnosis and patient monitoring.

More Related Videos

Induction and Assessment of Levodopa-induced Dyskinesias in a Rat Model of Parkinson's Disease
05:51

Induction and Assessment of Levodopa-induced Dyskinesias in a Rat Model of Parkinson's Disease

Published on: October 14, 2021

4.6K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.9K

Related Experiment Videos

Last Updated: Mar 14, 2026

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.6K
Induction and Assessment of Levodopa-induced Dyskinesias in a Rat Model of Parkinson's Disease
05:51

Induction and Assessment of Levodopa-induced Dyskinesias in a Rat Model of Parkinson's Disease

Published on: October 14, 2021

4.6K
Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans
10:51

Frame-by-Frame Video Analysis of Idiosyncratic Reach-to-Grasp Movements in Humans

Published on: January 15, 2018

8.9K

Area of Science:

  • Neurology
  • Artificial Intelligence
  • Psychiatry

Background:

  • Tardive dyskinesia (TD) is a serious side effect of dopamine receptor-blocking drugs, causing involuntary movements.
  • TD is often underdiagnosed, affecting millions despite available treatments.
  • Current diagnostic methods rely on subjective assessments by trained raters.

Purpose of the Study:

  • To develop and validate an efficient, reliable AI-powered method for detecting tardive dyskinesia.
  • To improve the early identification and attention to TD in patients on antipsychotic medications.

Main Methods:

  • Video assessments of individuals taking antipsychotic medications were analyzed.
  • A vision transformer machine-learning model was employed.
  • Performance was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, and specificity against expert ratings on the Abnormal Involuntary Movement Scale.

Main Results:

  • The AI algorithm achieved an AUC of 0.89 in a combined validation cohort.
  • The model demonstrated strong agreement and outperformed human raters in accuracy.
  • High sensitivity and specificity were observed in detecting suspected TD.

Conclusions:

  • The developed algorithm reliably detects potential tardive dyskinesia with superior accuracy to human assessment.
  • This AI tool can aid in monitoring patients on antipsychotics, optimizing psychiatric resources for diagnosis.
  • The technology facilitates earlier identification and management of TD.