Advertisement

Automated nystagmus detection: Accuracy of slow-phase and quick-phase algorithms to determine the presence of nystagmus

  • Ariel A. Winnick
    Affiliations
    Soroka University Hospital and Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel

    Department of Neurology, University of South Alabama, Mobile, AL, USA
    Search for articles by this author
  • Chih-Chung Chen
    Affiliations
    Dizziness and Balance Disorder Center, Taipei Medical University–Shuang Ho Hospital, New Taipei City, Taiwan

    Taipei Neuroscience Institute, Taipei Medical University, New Taipei City, Taiwan

    Department of Neurology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan
    Search for articles by this author
  • Tzu-Pu Chang
    Correspondence
    Corresponding author at: Department of Neurology/Neuro-medical Scientific Center, Taichung Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, No. 88, Sec. 1, Fengxing Rd., Tanzi Dist., Taichung City 427, Taiwan.
    Affiliations
    Department of Neurology/Neuro-medical Scientific Center, Taichung Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Taichung, Taiwan

    Department of Neurology, School of Medicine, Tzu Chi University, Hualien, Taiwan
    Search for articles by this author
  • Yu-Hung Kuo
    Affiliations
    Department of Research, Taichung Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, Taichung, Taiwan
    Search for articles by this author
  • Ching-Fu Wang
    Affiliations
    Department of Biomedical Engineering, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan

    Biomedical Engineering Research and Development Center, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan

    Neurobit Technologies Co., Ltd., Taipei, Taiwan
    Search for articles by this author
  • Chin-Hsun Huang
    Affiliations
    Neurobit Technologies Co., Ltd., Taipei, Taiwan
    Search for articles by this author
  • Chun-Chen Yang
    Affiliations
    Neurobit Technologies Co., Ltd., Taipei, Taiwan
    Search for articles by this author
Published:August 27, 2022DOI:https://doi.org/10.1016/j.jns.2022.120392

      Highlights

      • Automated nystagmus detection is an important first step toward automated diagnosis of vestibular disorders.
      • The automated nystagmus detection by current algorithms is accurate with real-world clinical data.
      • But the low positive predictive value (PPV) in the clinical settings with low nystagmus prevalence limits its utility.
      • Combination of multiple parameters of different algorithms may further improve the accuracy of nystagmus detection.

      Abstract

      Purpose

      To verify the accuracy of automated nystagmus detection algorithms.

      Method

      Video-oculography (VOG) plots were analyzed from consecutive patients with dizziness presenting to a neurology clinic. Data were recorded for 30 s in upright position with fixation block. For automated nystagmus detection, slow-phase algorithm parameters included mean and median slow-phase velocity (SPV), and slow-phase duration ratio. Quick-phase algorithm parameters included saccadic difference and saccadic ratio. For verification, two independent blinded assessors reviewed VOG traces and videos and coded presence or absence of nystagmus. Assessor consensus was used as reference standard. Accuracy of slow-phase and quick-phase algorithm parameters were compared, and ROC analysis was performed.

      Results

      Among 524 analyzed VOG traces, 99 were verified as nystagmus present and 425 were verified as nystagmus absent. Prevalence of nystagmus in the sample population was 18.9%. In ROC analysis, areas under the curve of individual algorithm parameters were 0.791–0.896. With optimal thresholds for determining presence or absence of nystagmus, algorithm sensitivity (70.7–87.9%), specificity (71.8–84.0%), and negative predictive value (91.7–96.4%) were ideal, but positive predictive value (38.8–53.4%) was not ideal. Combining algorithm parameters using logistic regression models mildly improved detection accuracy.

      Conclusion

      Both slow-phase and fast-phase algorithms were accurate for detecting nystagmus. Due to low positive predictive value, the utility of independent automated nystagmus detection systems is limited in clinical settings with low prevalence of nystagmus. Combining parameters using logistic regression models appears to improve detection accuracy, indicating that machine learning may potentially optimize the accuracy of future automated nystagmus detection systems.

      Keywords

      Abbreviations:

      VOG (video-oculography), SPV (slow-phase velocity), ROC (receiver operating characteristic), AUC (area under curve), VOR (vestibulo-ocular reflex), PPV (positive predictive value), NPV (negative predictive value)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Journal of the Neurological Sciences
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Leigh J.R.
        • Zee D.S.
        The Neurology of Eye Movements.
        5 ed. Oxford University Press, 2015
        • Kattah J.C.
        • Talkad A.V.
        • Wang D.Z.
        • Hsieh Y.H.
        • Newman-Toker D.E.
        HINTS to diagnose stroke in the acute vestibular syndrome: three-step bedside oculomotor examination more sensitive than early MRI diffusion-weighted imaging.
        Stroke. 2009; 40: 3504-3510
        • Eckert A.M.
        • Gizzi M.
        Video-oculography as part of the ENG battery.
        Br. J. Audiol. 1998; 32: 411-416
        • Choi J.H.
        • Park M.G.
        • Choi S.Y.
        • Park K.P.
        • Baik S.K.
        • Kim J.S.
        • Choi K.D.
        Acute transient vestibular syndrome: prevalence of stroke and efficacy of bedside evaluation.
        Stroke. 2017; 48: 556-562
        • Newman-Toker D.E.
        • Saber Tehrani A.S.
        • Mantokoudis G.
        • Pula J.H.
        • Guede C.I.
        • Kerber K.A.
        • Blitz A.
        • Ying S.H.
        • Hsieh Y.H.
        • Rothman R.E.
        • Hanley D.F.
        • Zee D.S.
        • Kattah J.C.
        Quantitative video-oculography to help diagnose stroke in acute vertigo and dizziness: toward an ECG for the eyes.
        Stroke. 2013; 44: 1158-1161
        • Young A.S.
        • Lechner C.
        • Bradshaw A.P.
        • MacDougall H.G.
        • Black D.A.
        • Halmagyi G.M.
        • Welgampola M.S.
        Capturing acute vertigo: a vestibular event monitor.
        Neurology. 2019; 92: e2743-e2753
        • Gold D.
        • Peterson S.
        • McClenney A.
        Diagnostic Impact of a Device-Enabled Remote “Tele-Dizzy” Consultation Service Diagnostic Error in Medicine, 12th Annual Conference, Washington, D.C..
        2019
        • Radinsky I.
        • Galiana H.L.
        Improved algorithm for classification of ocular nystagmus.
        Conf. Proc. IEEE Eng. Med. Biol. Soc. 2006; 2004: 534-537
        • Wall 3rd, C.
        • Black F.O.
        Algorithms for the clinical analysis of nystagmus eye movements.
        IEEE Trans. Biomed. Eng. 1981; 28: 638-646
        • Honrubia V.
        • Katz R.D.
        • Strelioff D.
        • Ward P.H.
        Computer analysis of induced vestibular nystagmus. Rotatory stimulation of normal cats.
        Ann. Otol. Rhinol. Laryngol. 1971; 53: 7-25
        • Mantokoudis G.
        • Wyss T.
        • Zamaro E.
        • Korda A.
        • Wagner F.
        • Sauter T.C.
        • Kerkeni H.
        • Kalla R.
        • Morrison M.
        • Caversaccio M.D.
        Stroke prediction based on the spontaneous nystagmus suppression test in dizzy patients: a diagnostic accuracy study.
        Neurology. 2021; 97: e42-e51
        • Erkelens A.J.
        • Sloot O.B.
        Initial directions and landing positions of binocular saccades.
        Vis. Res. 1995; 35: 3297-3303
        • Otero-Millan J.
        • Troncoso X.G.
        • Macknik S.L.
        • Serrano-Pedraza I.
        • Martinez-Conde S.
        Saccades and microsaccades during visual fixation, exploration, and search: foundations for a common saccadic generator.
        J. Vis. 2008; 8: 1-18
        • Punuganti S.
        • Otero-Millan J.
        Detection of Saccades and Quick-Phases in Eye Movement Recordings with Nystagmus, 2020 Symposium on Eye Tracking Research and Applications, Stuttgart, Germany.
        2020
        • Dunn M.J.
        • Harris C.M.
        • Ennis F.A.
        • Margrain T.H.
        • Woodhouse J.M.
        • McIlreavy L.
        • Erichsen J.T.
        An automated segmentation approach to calibrating infantile nystagmus waveforms.
        Behav. Res. Methods. 2019; 51: 2074-2084
        • Pander T.
        • Czabanski R.
        • Przybyla T.
        • Pojda-Wilczek D.
        An automatic saccadic eye movement detection in an optokinetic nystagmus signal.
        Biomed Tech (Berl). 2014; 59: 529-543
        • Pander T.
        • Czabanski R.
        • Przybyla T.
        • Jezewski J.
        • Pojda-Wilczek D.
        • Wrobel J.
        • Horoba K.
        • Bernys M.
        A new method of saccadic eye movement detection for optokinetic nystagmus analysis.
        Ann. Int. Conf. IEEE Eng. Med. Biol. Soc. 2012; 2012: 3464-3467
        • Bremova T.
        • Krafczyk S.
        • Bardins S.
        • Reinke J.
        • Strupp M.
        Vestibular function in patients with Niemann-pick type C disease.
        J. Neurol. 2016; 263: 2260-2270
        • Kanari K.
        • Kikuchi-Ito M.
        Estimation of the degree of autism spectrum disorder by the slow phase of optokinetic nystagmus in typical adults.
        Heliyon. 2021; 7e07751
        • Shalabi L.A.
        • Shaaban Z.
        • Kasasbeh B.
        Data mining: a preprocessing engine.
        J. Comput. Sci. 2006; 2: 735-739
        • Slama A.B.
        • Machraoui A.N.
        • Sayadi M.
        Pupil tracking using active contour model for videonystagmography, applications[C].
        in: Image Processing, Applications and Systems Conference. IEEE, 2015: 1-5
        • Hastie T.
        • Tibshirani R.
        • Friedman J.
        The Elements of Statistical Learning.
        2 ed. Springer-Verlag, 2009
        • Porte H.S.
        Slow horizontal eye movement at human sleep onset.
        J. Sleep Res. 2004; 13: 239-249
        • Mantokoudis G.
        • Saber Tehrani A.S.
        • Kattah J.C.
        • Eibenberger K.
        • Guede C.I.
        • Zee D.S.
        • Newman-Toker D.E.
        Quantifying the vestibulo-ocular reflex with video-oculography: nature and frequency of artifacts.
        Audiol. Neurootol. 2015; 20: 39-50
        • Herishanu Y.O.
        • Sharpe J.A.
        Normal square wave jerks.
        Invest. Ophthalmol. Vis. Sci. 1981; 20: 268-272
        • Abadi R.V.
        • Gowen E.
        Characteristics of saccadic intrusions.
        Vis. Res. 2004; 44: 2675-2690
        • Bellet M.E.
        • Bellet J.
        • Nienborg H.
        • Hafed Z.M.
        • Berens P.
        Human-level saccade detection performance using deep neural networks.
        J. Neurophysiol. 2019; 121: 646-661
        • Otero-Millan J.
        • Castro J.L.
        • Macknik S.L.
        • Martinez-Conde S.
        Unsupervised clustering method to detect microsaccades.
        J. Vis. 2014; 14
        • Phillips J.S.
        • Newman J.L.
        • Cox S.J.
        An investigation into the diagnostic accuracy, reliability, acceptability and safety of a novel device for continuous ambulatory vestibular assessment (CAVA).
        Sci. Rep. 2019; 9: 10452