Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence
The Journal of Clinical Psychiatry · 28.05.2025 · 86 (3)
DOI: 10.4088/jcp.25m15792 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Journal of Clinical Psychiatry, online erschienen am 28.05.2025. Verfasst von Anthony A Sterns und 9 weiteren Autor:innen. Beteiligte Einrichtung: iRxReminder, Cleveland, Ohio. Hauptthemen laut MEDLINE: Tardive Dyskinesia, Antipsychotic Agents, Video Recording, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref). Gefördert von: NIMH NIH HHS.
Abstract (Originalsprache)
Tardive dyskinesia (TD) is a late-onset adverse effect of dopamine receptor-blocking medications, characterized by involuntary movements primarily affecting the mouth, though other body parts may be involved. Severity of TD varies from mild to debilitating and is usually irreversible. Despite the existence of treatments such as VMAT2 inhibitors, TD remains underdiagnosed, with 40,000 patients treated of an estimated 2.6 million affected US individuals. This study demonstrates a novel, efficient, and reliable method to detect and bring TD to psychiatrists' attention using video-based artificial intelligence. Individuals taking antipsychotic medications were enrolled in Study 1 (n = 46) between March and November 2018, in Study 2 (n = 136) between May 2023 and May 2024, and in Study 3 (n = 174) between July 2023 and May 2024. Participants completed video assessments. A vision transformer machine-learning architecture was evaluated by calculating the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity compared with a reference standard of the trained raters' evaluation of TD on the Abnormal Involuntary Movement Scale. The algorithm reached an AUC of 0.89 in the combined validation cohort across Studies 1, 2, and 3. The model demonstrated strong and reliable levels of agreement, outperforming human raters. Our algorithm reliably detected suspected TD, reaching higher sensitivity and specificity than trained raters using the standard assessment. The algorithm can be used to monitor patients taking antipsychotic medications, allowing scarce resources to assess identified patients for a conclusive diagnosis by psychiatrists.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- iRxReminder, Cleveland, Ohio.
- Scripps Gerontology Center, Miami University, Oxford, Ohio.
- Department of Information Management Systems, Ambassador Crawford College of Business and Entrepreneurship, Kent, Ohio.
- Corresponding Author: Anthony A. Sterns, PhD, iRxReminder, 1800 63rd St, Cleveland, OH 44103 (asterns@irxreminder.com).
- Department of Psychological Sciences, Kent State University, Kent, Ohio.
- Videra Health, Orem, Utah.
Förderung
- NIMH NIH HHS
Zitieren
APA
Sterns, A. A., Hughes, J. W., Grimm, B., Larsen, L., Ma, F., Ranjan, R., MacMillan, C., Talbot, B. H., Friedman, J. H., & Muir, O. S. (2025). Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence. The Journal of Clinical Psychiatry, 86(3). https://doi.org/10.4088/jcp.25m15792
Vancouver
Sterns AA, Hughes JW, Grimm B, Larsen L, Ma F, Ranjan R, et al. Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence. The Journal of Clinical Psychiatry. 2025;86(3). doi:10.4088/jcp.25m15792
BibTeX
@article{Sterns2025,
author = {Sterns, Anthony A and Hughes, Joel W and Grimm, Bradley and Larsen, Loren and Ma, Fred and Ranjan, Rakesh and MacMillan, Carlene and Talbot, Bretton H and Friedman, Joseph H and Muir, Owen S},
title = {Detecting Tardive Dyskinesia Using Video-Based Artificial Intelligence},
journal = {The Journal of Clinical Psychiatry},
year = {2025},
volume = {86},
number = {3},
doi = {10.4088/jcp.25m15792}
}
EUVIMED