skip to main content
research-article

Analyzing Head Pose in Remotely Collected Videos of People with Parkinson’s Disease

Authors Info & Claims
Published:14 September 2021Publication History
Skip Abstract Section

Abstract

We developed an intelligent web interface that guides users to perform several Parkinson’s disease (PD) motion assessment tests in front of their webcam. After gathering data from 329 participants (N = 199 with PD, N = 130 without PD), we developed a methodology for measuring head motion randomness based on the frequency distribution of the motion. We found PD is associated with significantly higher randomness in side-to-side head motion as measured by the variance and number of large frequency components compared to the age-matched non-PD control group (p = 0.001, d = 0.13). Additionally, in participants taking levodopa (N = 151), the most common drug to treat Parkinson’s, the degree of random side-to-side head motion was found to follow an exponential-decay activity model following the time of the last dose taken (r = −0.404, p = 6e-5). A logistic regression model for classifying PD vs. non-PD groups identified that higher frequency components are more associated with PD. Our findings could potentially be useful toward objectively quantifying differences in head motions that may be due to either PD or PD medications.

Skip Supplemental Material Section

Supplemental Material

References

  1. Parkinson’s Foundation. 2018. Statistics. (2018). Retrieved February 15, 2018 from http://parkinson.org/Understanding-Parkinsons/Causes-and-Statistics/Statistics.Google ScholarGoogle Scholar
  2. CDC. 2016. National Center for Health Statistics: Parkinson’s Disease Mortality by State. (2016). Retrieved Aug 13, 2020 from https://www.cdc.gov/nchs/pressroom/sosmap/parkinsons_disease_mortality/parkinsons_disease.htm.Google ScholarGoogle Scholar
  3. Movement Disorder Society Task Force. 2003. The unified Parkinson’s disease rating scale (UPDRS): Status and recommendations. Movement Disorders 18, 7 (July 2003), 738–750. DOI:http://dx.doi.org/10.1002/mds.10473Google ScholarGoogle Scholar
  4. John G. Nutl and Jack H. Fellman. 1984. Pharmacokinetics of levodopa. Clinical Neuropharmacology 7, 1 (1984), 35–50.Google ScholarGoogle Scholar
  5. Lalit M. Ambani and Melvin H. Van Woert. 1973. Start hesitation—a side effect of long-term levodopa therapy. New England Journal of Medicine 288, 21 (1973), 1113–1115.Google ScholarGoogle Scholar
  6. Joseph Jankovic. 2002. Levodopa strengths and weaknesses. Neurology 58, Suppl. 1 (2002), S19–S32.Google ScholarGoogle Scholar
  7. Melvin D. Yahr, Roger C. Duvoisin, Myrna J. Schear, Robert E. Barrett, and Margaret M. Hoehn. 1969. Treatment of parkinsonism with levodopa. Archives of Neurology 21, 4 (1969), 343–354.Google ScholarGoogle ScholarCross RefCross Ref
  8. Guha Balakrishnan, Fredo Durand, and John Guttag. 2013. Detecting pulse from head motions in video. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3430–3437. Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. Ming-Zher Poh, Daniel J. McDuff, and Rosalind W. Picard. 2010. Non-contact, automated cardiac pulse measurements using video imaging and blind source separation.Optics Express 18, 10 (2010), 10762–10774.Google ScholarGoogle Scholar
  10. Anouk Van de Vel, Kris Cuppens, Bert Bonroy, Milica Milosevic, Katrien Jansen, Sabine Van Huffel, Bart Vanrumste, Lieven Lagae, and Berten Ceulemans. 2013. Non-EEG seizure-detection systems and potential SUDEP prevention: State of the art. Seizure 22, 5 (2013), 345–355.Google ScholarGoogle ScholarCross RefCross Ref
  11. K. Song Tan, Reza Saatchi, Heather Elphick, and Derek Burke. 2010. Real-time vision based respiration monitoring system. In 2010 7th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP 2010). IEEE, 770–774.Google ScholarGoogle Scholar
  12. Kris Cuppens, Lieven Lagae, Berten Ceulemans, Sabine Van Huffel, and Bart Vanrumste. 2010. Automatic video detection of body movement during sleep based on optical flow in pediatric patients with epilepsy. Medical & Biological Engineering & Computing 48, 9 (2010), 923–931.Google ScholarGoogle Scholar
  13. M. Pediaditis, M. Tsiknakis, P. Vorgia, D. Kafetzopoulos, V. Danilatou, and D. Fotiadis. 2010. Vision-based human motion analysis in epilepsy-methods and challenges. In Proceedings of the 10th IEEE International Conference on Information Technology and Applications in Biomedicine. IEEE, 1–5.Google ScholarGoogle Scholar
  14. Hodjat Rahmati, Ole Morten Aamo, Øyvind Stavdahl, Ralf Dragon, and Lars Adde. 2014. Video-based early cerebral palsy prediction using motion segmentation. In 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 3779–3783.Google ScholarGoogle Scholar
  15. Pew Research Center. 2018. Internet/Broadband Fact Sheet. (5 Feb. 2018). http://www.pewinternet.org/fact-sheet/internet-broadband/.Google ScholarGoogle Scholar
  16. E. Ray Dorsey, Vinayak Venkataraman, Matthew J. Grana, Michael T. Bull, Benjamin P. George, Cynthia M. Boyd, Christopher A. Beck, Balaraman Rajan, Abraham Seidmann, and Kevin M. Biglan. 2013. Randomized controlled clinical trial of “virtual house calls” for Parkinson disease. JAMA Neurology 70, 5 (2013), 565–570.Google ScholarGoogle ScholarCross RefCross Ref
  17. Athanasios Tsanas, Max A. Little, Patrick E. McSharry, and Lorraine O. Ramig. 2010. Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests. IEEE Transactions on Biomedical Engineering 57, 4 (2010), 884–893.Google ScholarGoogle ScholarCross RefCross Ref
  18. Raina Langevin, Mohammad Rafayet Ali, Taylan Sen, Christopher Snyder, Taylor Myers, E. Ray Dorsey, and Mohammed Ehsan Hoque. 2019. The PARK framework for automated analysis of pParkinson’s disease characteristics. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3, 2 (June 2019), Article 54, 22 pages. DOI:http://dx.doi.org/10.1145/3328925 Google ScholarGoogle ScholarDigital LibraryDigital Library
  19. Michael H, Cole, Peter A. Silburn, Joanne M. Wood, Charles J. Worringham, and Graham K. Kerr. 2010. Falls in Parkinson’s disease: Kinematic evidence for impaired head and trunk control. Movement Disorders 25, 14 (2010), 2369–2378.Google ScholarGoogle Scholar
  20. Erika Franzén, Caroline Paquette, Victor S. Gurfinkel, Paul J. Cordo, John G. Nutt, and Fay B. Horak. 2009. Reduced performance in balance, walking and turning tasks is associated with increased neck tone in Parkinson’s disease. Experimental Neurology 219, 2 (2009), 430–438.Google ScholarGoogle Scholar
  21. Mohammad Rafayet Ali, Javier Hernandez, E. Ray Dorsey, Ehsan Hoque, and Daniel McDuff. Spatio-temporal attention and magnification for classification of Parkinson’s disease from videos collected via the internet. In 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020). IEEE Computer Society, 53–60.Google ScholarGoogle Scholar
  22. E. Dorsey, Larsson Omberg, Emma Waddell, Jamie L. Adams, Roy Adams, Mohammad Rafayet Ali, Katherine Amodeo, Abigail Arky, Erika F. Augustine, Karthik Dinesh, et al. 2020. Deep phenotyping of parkinson’s disease. Journal of Parkinson’s Disease, preprint (2020), 1–19.Google ScholarGoogle Scholar
  23. Dennis L. Kasper, Eugene Braunwald, Anthony S. Fauci, Stephen L. Hauser, Dan L. Longo, J. Larry Jameson, et al. 2005. Harrison’s Manual of Medicine.Google ScholarGoogle Scholar
  24. Kelvin L. Chou. 2017. Diagnosis and differential diagnosis of Parkinson disease. Rhode Island Medical Journal 87, 5 (2017), 135.Google ScholarGoogle Scholar
  25. C. W. Olanow and W. G. Tatton. 1999. Etiology and pathogenesis of Parkinson’s disease. Annual Review of Neuroscience 22, 1 (1999), 123–144.Google ScholarGoogle ScholarCross RefCross Ref
  26. Joseph Jankovic. 2008. Parkinson’s disease: Clinical features and diagnosis. Journal of Neurology, Neurosurgery & Psychiatry 79, 4 (2008), 368–376.Google ScholarGoogle ScholarCross RefCross Ref
  27. Chauncey Spears. 2019. 10 Early Signs of Parkinson’s Disease. (2019). https://parkinson.org/understanding-parkinsons/10-early-warning-signs.Google ScholarGoogle Scholar
  28. Olivier Rascol, David J. Brooks, Amos D. Korczyn, Peter P. De Deyn, Carl E. Clarke, and Anthony E. Lang. 2000. A five-year study of the incidence of dyskinesia in patients with early Parkinson’s disease who were treated with ropinirole or levodopa. New England Journal of Medicine 342, 20 (2000), 1484–1491.Google ScholarGoogle ScholarCross RefCross Ref
  29. Kavita R. Gandhi and Abdolreza Saadabadi. 2018. Levodopa (l-dopa). In StatPearls [Internet]. StatPearls Publishing.Google ScholarGoogle Scholar
  30. John G. Nutt, William R. Woodward, John P. Hammerstad, Julie H. Carter, and John L. Anderson. 1984. The on–off phenomenon in Parkinson’s disease: Relation to levodopa absorption and transport. New England Journal of Medicine 310, 8 (1984), 483–488.Google ScholarGoogle ScholarCross RefCross Ref
  31. Krista G. Sibley. Video-based analyses of Parkinson’s disease severity: A brief review. Journal of Parkinson’s Disease (2021), DOI:10.3233/JPD-202402Google ScholarGoogle Scholar
  32. Birgit Frauscher, Viola Gschliesser, Elisabeth Brandauer, Hanno Ulmer, Cecilia M. Peralta, Jörg Müller, Werner Poewe, and Birgit Högl. 2007. Video analysis of motor events in REM sleep behavior disorder. Movement Disorders: Official Journal of the Movement Disorder Society 22, 10 (2007), 1464–1470.Google ScholarGoogle Scholar
  33. Silvia Marino, Edoardo Sessa, Giuseppe Di Lorenzo, Pietro Lanzafame, Gabriella Scullica, Alessia Bramanti, Francesco La Rosa, Giancarlo Iannizzotto, Placido Bramanti, and Paolo Di Bella. 2007. Quantitative analysis of pursuit ocular movements in parkinson’s disease by using a video-based eye tracking system. European Neurology 58, 4 (2007), 193–197.Google ScholarGoogle Scholar
  34. Natasa K. Orphanidou, Abir Hussain, Robert Keight, Paulo Lishoa, Jade Hind, and Haya Al-Askar. 2018. Predicting freezing of gait in parkinsons disease patients using machine learning. In 2018 IEEE Congress on Evolutionary Computation (CEC’18). 1–8. DOI:http://dx.doi.org/10.1109/CEC.2018.8477909Google ScholarGoogle Scholar
  35. Samarjit Das, Breogan Amoedo, Fernando De la Torre, and Jessica Hodgins. 2012. Detecting Parkinsons’ symptoms in uncontrolled home environments: A multiple instance learning approach. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, 3688–3691.Google ScholarGoogle Scholar
  36. Steven T. Moore, Hamish G. MacDougall, and William G. Ondo. 2008. Ambulatory monitoring of freezing of gait in Parkinson’s disease. Journal of Neuroscience Methods 167, 2 (2008), 340–348.Google ScholarGoogle ScholarCross RefCross Ref
  37. A. J. Manson, P. Brown, J. D. O’Sullivan, P. Asselman, D. Buckwell, and A. J. Lees. 2000. An ambulatory dyskinesia monitor. Journal of Neurology, Neurosurgery & Psychiatry 68, 2 (2000), 196–201.Google ScholarGoogle ScholarCross RefCross Ref
  38. Ilias Thomas, Filip Bergquist, Radu Constantinescu, Dag Nyholm, Marina Senek, and Mevludin Memedi. 2017. Using measurements from wearable sensors for automatic scoring of Parkinson’s disease motor states. In 21st International Congress of Parkinson’s Disease and Movement Disorders, Vol. 32. John Wiley & Sons.Google ScholarGoogle Scholar
  39. E. Ray Dorsey, Alistair M. Glidden, Melissa R. Holloway, Gretchen L. Birbeck, and Lee H. Schwamm. 2018. Teleneurology and mobile technologies: The future of neurological care. Nature Reviews Neurology 14, 5 (2018), 285.Google ScholarGoogle ScholarCross RefCross Ref
  40. Abdulwahab Sahyoun, Karim Chehab, Osama Al-Madani, Fadi Aloul, and Assim Sagahyroon. 2016. ParkNosis: Diagnosing Parkinson’s disease using mobile phones. In IEEE 18th International Conference on e-Health Networking, Applications and Services. 387–392. DOI:http://dx.doi.org/10.1109/HealthCom.2016.7749491Google ScholarGoogle Scholar
  41. Alexandros T. Tzallas, Markos G. Tsipouras, Georgios Rigas, Dimitrios G. Tsalikakis, Evaggelos C. Karvounis, Maria Chondrogiorgi, Fotis Psomadellis, Jorge Cancela, Matteo Pastorino, María Teresa Arredondo Waldmeyer, Spiros Konitsiotis, and Dimitrios I. Fotiadis. 2014. PERFORM: A system for monitoring, assessment and management of patients with Parkinson’s disease. Sensors (Basel) 14, 11 (Nov. 2014), 21329–21357. DOI:http://dx.doi.org/10.3390/s141121329Google ScholarGoogle Scholar
  42. Brian M. Bot, Christine Suver, Elias Chaibub Neto, Michael Kellen, Arno Klein, Christopher Bare, Megan Doerr, Abhishek Pratap, John Wilbanks, E. Ray Dorsey, et al. 2016. The mPower study, Parkinson disease mobile data collected using researchkit. Scientific Data 3, 1 (2016), 1–9.Google ScholarGoogle Scholar
  43. Andong Zhan, Max A. Little, Denzil A. Harris, Solomon O. Abiola, E. Dorsey, Suchi Saria, and Andreas Terzis. 2016. High frequency remote monitoring of Parkinson’s disease via smartphone: Platform overview and medication response detection. Retrieved Aug 13, 2020 on https://arxiv.org/pdf/1601.00960.pdf.Google ScholarGoogle Scholar
  44. Oliver Chén, Florian Lipsmeier, Huy Phan, John Prince, Kirsten Taylor, Christian Gossens, Michael Lindemann, and Maarten De Vos. 2020. Building a machine-learning framework to remotely assess Parkinson’s disease using smartphones. IEEE Transactions on Biomedical Engineering 67, 12 (2020), 3491–3500.Google ScholarGoogle Scholar
  45. Tadas Baltrusaitis, Amir Zadeh, Yao Chong Lim, and Louis-Philippe Morency. 2018. Openface 2.0: Facial behavior analysis toolkit. In 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). IEEE, 59–66.Google ScholarGoogle ScholarDigital LibraryDigital Library
  46. W. Morven Gentleman and Gordon Sande. 1966. Fast Fourier transforms: for fun and profit. In Proceedings of the November 7-10, 1966, Fall Joint Computer Conference. ACM, 563–578. Google ScholarGoogle ScholarDigital LibraryDigital Library
  47. Henry B. Mann and Donald R. Whitney. 1947. On a test of whether one of two random variables is stochastically larger than the other. The Annals of Mathematical Statistics (1947), 50–60.Google ScholarGoogle Scholar
  48. Norman Cliff. 1993. Dominance statistics: Ordinal analyses to answer ordinal questions.Psychological Bulletin 114, 3 (1993), 494.Google ScholarGoogle Scholar
  49. Karl Pearson. 1909. Determination of the coefficient of correlation. Science 30, 757 (1909), 23–25.Google ScholarGoogle ScholarCross RefCross Ref
  50. Cornelis Joost Van Rijsbergen. 1977. A theoretical basis for the use of co-occurrence data in information retrieval. Journal of Documentation 33, 2 (1977), 106–119.Google ScholarGoogle ScholarCross RefCross Ref
  51. Robert J. Cabin and Randall J. Mitchell. 2000. To bonferroni or not to bonferroni: When and how are the questions. Bulletin of the Ecological Society of America 81, 3 (2000), 246–248.Google ScholarGoogle Scholar
  52. Michael P. Caligiuri and James B. Lohr. 1993. Worsening of postural tremor in patients with levodopa-induced dyskinesia: A quantitative analysis.Clinical Neuropharmacology 16, 3 (1993), 244–250.Google ScholarGoogle Scholar
  53. Michael H. Li, Tiago A. Mestre, Susan H. Fox, and Babak Taati. 2018. Vision-based assessment of parkinsonism and levodopa-induced dyskinesia with pose estimation. Journal of Neuroengineering and Rehabilitation 15, 1 (2018), 97.Google ScholarGoogle ScholarCross RefCross Ref
  54. Anne-Marie A. Wills, Adriana Pérez, Jue Wang, Xiao Su, John Morgan, Suja S. Rajan, Maureen A. Leehey, Gregory M. Pontone, Kelvin L. Chou, Chizoba Umeh, et al. 2016. Association between change in body mass index, unified Parkinson’s disease rating scale scores, and survival among persons with Parkinson disease: Secondary analysis of longitudinal data from NINDS exploratory trials in Parkinson disease long-term study 1. JAMA Neurology 73, 3 (2016), 321–328.Google ScholarGoogle Scholar
  55. C. G. Bachmann, A. Zapf, E. Brunner, and C. Trenkwalder. 2009. Dopaminergic treatment is associated with decreased body weight in patients with Parkinson’s disease and dyskinesias. European Journal of Neurology 16, 8 (2009), 895–901.Google ScholarGoogle Scholar
  56. Mario Zappia, Lucia Crescibene, Gennarina Arabia, Giuseppe Nicoletti, Angelo Bagalà, Loredana Bastone, Manuela Caracciolo, Simona Bonavita, Alfonso Di Costanzo, Massimo Scornaienchi, et al. 2002. Body weight influences pharmacokinetics of levodopa in Parkinson’s disease. Clinical Neuropharmacology 25, 2 (2002), 79–82.Google ScholarGoogle Scholar

Index Terms

  1. Analyzing Head Pose in Remotely Collected Videos of People with Parkinson’s Disease

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    • Published in

      cover image ACM Transactions on Computing for Healthcare
      ACM Transactions on Computing for Healthcare  Volume 2, Issue 4
      October 2021
      199 pages
      ISSN:2691-1957
      EISSN:2637-8051
      DOI:10.1145/3476827
      Issue’s Table of Contents

      Copyright © 2021 ACM

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 14 September 2021
      • Accepted: 1 March 2021
      • Revised: 1 January 2021
      • Received: 1 August 2020
      Published in health Volume 2, Issue 4

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
      • Research
      • Refereed

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format .

    View HTML Format
    About Cookies On This Site

    We use cookies to ensure that we give you the best experience on our website.

    Learn more

    Got it!