EUVIMEDEUVIMED entdecken
Crossref

Automated vertigo diagnosis using video-oculography and artificial intelligence for clinic-based triage: Preliminary results

Yi-Jing Lai, Ching-Fu Wang, Chun-Chen Yang, Chin-Hsun Huang, Chih-Chung Chen, Ting-Yi Lee, Hsun-Hua Lee, I-Hsien Chen, Tzu-Pu Chang

Neurological Sciences · 2026

DOI: 10.1007/s10072-025-08781-9 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neurological Sciences, 2026. Verfasst von Yi-Jing Lai und 8 weiteren Autor:innen. Beteiligte Einrichtung: Neurobit Technologies Co., Ltd., 2F., No. 320, Sec. 4, Zhongxiao E. Rd., Da'an Dist., Taipei, 106, Taiwan. Hauptthemen laut MEDLINE: Vertigo, Triage, Artificial Intelligence, Diagnosis, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Gefördert von: Neurobit Technologies Co., Ltd, Buddhist Tzu Chi Medical Foundation, Taipei Medical University.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Distinguishing dangerous from benign vertigo remains a diagnostic challenge. Our study aimed to develop and evaluate a machine learning model to differentiate between dangerous and benign vertigo in the outpatient setting across two medical institutions that used different equipment, testing methods, and protocols. METHODS: Patients in the dizziness clinics of Shuang Ho Hospital (SHH) and Taichung Tzu Chi Hospital (TTCH) were classified into "benign vertigo" and "dangerous vertigo" groups. The data of video-oculography (VOG) and video head impulse test were combined and preprocessed by applying the min-max scaler and the synthetic minority oversampling technique. The optimized Random Forest (RF)-Adaptive Boosting (AdaBoost) model was employed for classification. The SHapley Additive exPlanations method provided feature importance. Model performance was evaluated using a random 70/30 stratified split across sites, and 95% confidence intervals (CIs) were computed using stratified bootstrapping. RESULTS: A total of 294 patients were enrolled, including 184 (171 with benign vertigo and 13 with dangerous vertigo) in SHH and 110 (63 with benign vertigo and 47 with dangerous vertigo) in TTCH. The optimized RF-AdaBoost model was used to identify dangerous vertigo. The accuracy was 97% (95% CI: 92 - 100%), the sensitivity was 92% (95% CI: 75 - 100%), the specificity was 97% (95% CI: 93 - 100%), and the AUC was 0.95 (95% CI: 0.86 - 1.00). CONCLUSION: Our VOG-based machine learning model for differentiating dangerous from benign vertigo demonstrated good accuracy and showed potential for use across different equipment, testing methods, and institutional protocols.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

VertigoTriageArtificial IntelligenceDiagnosis, Computer-AssistedHumansFemaleMaleMiddle AgedAdultAgedVideo RecordingHead Impulse TestMachine Learning

Stichwörter der Autor:innen

Machine learningOptimized random forest with adaptive boostingSynthetic minority oversampling techniqueVertigoVideo-oculography

Autor:innen und Institutionen

  • Neurobit Technologies Co., Ltd., 2F., No. 320, Sec. 4, Zhongxiao E. Rd., Da'an Dist., Taipei, 106, Taiwan.
  • School of Biomedical Engineering, College of Biomedical Engineering, Taipei Medical University, Taipei, Taiwan.
  • Neurobit Technologies Co., Ltd., 2F., No. 320, Sec. 4, Zhongxiao E. Rd., Da'an Dist., Taipei, 106, Taiwan. travisyang@neurobittech.com.
  • Department of Neurology, Taipei Medical University-Shuang Ho Hospital, New Taipei City, Taiwan.
  • Dizziness and Balance Disorder Center, Taipei Medical University-Shuang Ho Hospital, New Taipei City, Taiwan.
  • Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.

Förderung

  • Neurobit Technologies Co., Ltd
  • Buddhist Tzu Chi Medical Foundation
  • Taipei Medical University

Zitieren

APA

Lai, Y. J., Wang, C. F., Yang, C. C., Huang, C. H., Chen, C. C., Lee, T. Y., Lee, H. H., Chen, I. H., & Chang, T. P. (2026). Automated vertigo diagnosis using video-oculography and artificial intelligence for clinic-based triage: Preliminary results. Neurological Sciences. https://doi.org/10.1007/s10072-025-08781-9

Vancouver

Lai YJ, Wang CF, Yang CC, Huang CH, Chen CC, Lee TY, et al. Automated vertigo diagnosis using video-oculography and artificial intelligence for clinic-based triage: Preliminary results. Neurological Sciences. 2026. doi:10.1007/s10072-025-08781-9

BibTeX
@article{Lai2026,
  author = {Lai, Yi-Jing and Wang, Ching-Fu and Yang, Chun-Chen and Huang, Chin-Hsun and Chen, Chih-Chung and Lee, Ting-Yi and Lee, Hsun-Hua and Chen, I-Hsien and Chang, Tzu-Pu},
  title = {Automated vertigo diagnosis using video-oculography and artificial intelligence for clinic-based triage: Preliminary results},
  journal = {Neurological Sciences},
  year = {2026},
  doi = {10.1007/s10072-025-08781-9}
}
Kostenlos starten →