Advertisement

Automated General Movement Assessment for Perinatal Stroke Screening in Infants

  • Yan Gao
  • Yang Long
  • Yu Guan
  • Anna Basu
  • Jessica Baggaley
  • Thomas PlötzEmail author
Chapter
  • 664 Downloads
Part of the Computer Communications and Networks book series (CCN)

Abstract

Perinatal stroke (PS) is a serious condition that often leads to life-long disability, in particular cerebral palsy (CP). Early detection and early intervention could improve motor outcome. In clinical settings, Prechtl’s general movement assessment (GMA) can be used to classify infant movements using a Gestalt approach, identifying infants at high risk of abnormal motor development. Training and maintenance of assessment skills are essential and expensive for the correct use of GMA, yet many practitioners lack these skills, preventing larger-scale screening and leading to significant risks of missing affected infants. We present an automated approach to GMA, based on body-worn accelerometers and a novel sensor data analysis method—discriminative pattern discovery (DPD)—that is designed to cope with scenarios where only coarse annotations of data are available for model training. We demonstrate the effectiveness of our approach in a study with 34 newborns (21 typically developing infants and 13 PS infants with abnormal movements). Our method is able to correctly recognise the trials with abnormal movements with at least the accuracy that is required by newly trained human annotators (75%), which is encouraging towards our ultimate goal of an automated screening system that can be used population-wide.

Keywords

Human activity recognition Health Wearables Machine learning Prechtl’s general movements assessment Perinatal stroke 

Notes

Acknowledgments

This work was supported jointly by Medical Research Council (MRC, UK) Innovation Fellowship (MR/S003916/1), Engineering and Physical Sciences Research Council (EPSRC, UK) Project DERC: Digital Economy Research Centre (EP/M023001/1) and National Institute of Health Research (NIHR, UK) Career Development Fellowship (CDF-2013-06-001)(AB). The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health and Social Care (DHSC, UK).

References

  1. 1.
    Johnson A (2002) Prevalence and characteristics of children with cerebral palsy in Europe. Dev Med Child Neurol 44(9):633–640CrossRefGoogle Scholar
  2. 2.
    Nelson KB (2007) Perinatal ischemic stroke. Stroke 38(2 Suppl):742–745CrossRefGoogle Scholar
  3. 3.
    Basu AP et al (2018) Feasibility trial of an early therapy in perinatal stroke (eTIPS). BMC Neurol 18(1):102CrossRefGoogle Scholar
  4. 4.
    Basu AP et al (2017) Participatory design in the development of an early therapy intervention for perinatal stroke. BMC Pediatr 17(1):33MathSciNetCrossRefGoogle Scholar
  5. 5.
    Basu AP (2014) Early intervention after perinatal stroke: opportunities and challenges. Dev Med Child Neurol 56(6):516–521CrossRefGoogle Scholar
  6. 6.
    Edwards AD et al (2018) Effect of MRI on preterm infants and their families: a randomised trial with nested diagnostic and economic evaluation. Arch Dis Child Fetal Neonatal Ed 103(1):F15–F21CrossRefGoogle Scholar
  7. 7.
    Cowan F et al (2005) Does cranial ultrasound imaging identify arterial cerebral infarction in term neonates? Arch Dis Child Fetal Neonatal Ed 90(3):F252–F256CrossRefGoogle Scholar
  8. 8.
    Einspieler C, Prechtl HF (2005) Prechtl’s assessment of general movements: a diagnostic tool for the functional assessment of the young nervous system. Ment Retard Dev Disabil Res Rev 11(1):61–67CrossRefGoogle Scholar
  9. 9.
    Kwong AKL et al (2018) Predictive validity of spontaneous early infant movement for later cerebral palsy: a systematic review. Dev Med Child Neurol 60(5):480–489CrossRefGoogle Scholar
  10. 10.
    Avci A et al (2010) Activity recognition using inertial sensing for healthcare, wellbeing and sports applications: a survey. In: 23th international conference on architecture of computing systems, 2010Google Scholar
  11. 11.
    Hammerla NY et al (2015) PD disease state assessment in naturalistic environments using deep learning. In: Proceedings of the twenty-ninth AAAI conference on artificial intelligence, 2015. AAAI Press, Austin, Texas, pp 1742–1748Google Scholar
  12. 12.
    Hoey J et al (2011) Rapid specification and automated generation of prompting systems to assist people with dementia. J Pervasive Mob Comput 7(3):299–318CrossRefGoogle Scholar
  13. 13.
    Kranz M et al (2013) The mobile fitness coach: towards individualized skill assessment using personalized mobile devices. J Pervasive Mob Comput 9(2):203–215CrossRefGoogle Scholar
  14. 14.
    Plötz T, Moynihan P, Pham C, Olivier P (2011) Activity recognition and healthier food preparation. In: Chen NCL, Biswas J, Hoey J (eds) Activity recognition in pervasive intelligent environments. Atlantis Press, Atlantis Ambient and Pervasive IntelligenceCrossRefGoogle Scholar
  15. 15.
    Bulling A, Blanke U, Schiele B (2014) A tutorial on human activity recognition using body-worn inertial sensors. J ACM Comput Surv 46(3):1–33CrossRefGoogle Scholar
  16. 16.
    Guan Y, Ploetz T (2017) Ensembles of deep LSTM learners for activity recognition using wearables. J Proc ACM Interact Mob Wearable Ubiquitous Technol 1(2):1–28MathSciNetCrossRefGoogle Scholar
  17. 17.
    Hammerla NY et al (2016) Deep, convolutional, and recurrent models for human activity recognition using wearables. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, 2016. AAAI Press, New York, New York, USA, pp 1533–1540Google Scholar
  18. 18.
    Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115CrossRefGoogle Scholar
  19. 19.
    Yang JB et al (2015) Deep convolutional neural networks on multichannel time series for human activity recognition. In: Proceedings of the 24th international conference on artificial intelligence, 2015. AAAI Press, Buenos Aires, Argentina, pp 3995–4001Google Scholar
  20. 20.
    Zeng M et al (2014) Convolutional neural networks for human activity recognition using mobile sensors. In: 6th International conference on mobile computing, applications and servicesGoogle Scholar
  21. 21.
    Salerno S et al (2018) Is MRI imaging in pediatric age totally safe? A critical reprisal. Radiol Med 123(9):695–702CrossRefGoogle Scholar
  22. 22.
    Marcroft C et al (2014) Movement recognition technology as a method of assessing spontaneous general movements in high risk infants. Front Neurol 5:284Google Scholar
  23. 23.
    Gravem D et al (2012) Assessment of infant movement with a compact wireless accelerometer system. J Med Dev 6:2Google Scholar
  24. 24.
    Heinze F et al (2010) Movement analysis by accelerometry of newborns and infants for the early detection of movement disorders due to infantile cerebral palsy. Med Biol Eng Comput 48(8):765–772CrossRefGoogle Scholar
  25. 25.
    Singh M, Patterson DJ (2010) Involuntary gesture recognition for predicting cerebral palsy in high-risk infants. In: International symposium on wearable computers (ISWC), 2010Google Scholar
  26. 26.
    Fan M et al (2012) Augmenting gesture recognition with erlang-cox models to identify neurological disorders in premature babies. In: Proceedings of the 2012 ACM conference on ubiquitous computing (UbiComp)Google Scholar
  27. 27.
    Ploetz T, Hammerla NY, Olivier P (2011) Feature learning for activity recognition in ubiquitous computing. In: Proceedings of the twenty-second international joint conference on artificial intelligence, vol 2. AAAI Press, Barcelona, Catalonia, Spain, pp 1729–1734Google Scholar
  28. 28.
    Bachlin M et al (2010) Wearable assistant for Parkinson’s disease patients with the freezing of gait symptom. IEEE Trans Inf Technol Biomed 14(2):436–446CrossRefGoogle Scholar
  29. 29.
    Khan A et al (2015) Beyond activity recognition: skill assessment from accelerometer data. In: Proceedings of the 2015 ACM international joint conference on pervasive and ubiquitous computing, 2015. ACM, Osaka, Japan, pp 1155–1166Google Scholar
  30. 30.
    Ladha C et al (2013) ClimbAX: skill assessment for climbing enthusiasts. In: Proceedings of the 2013 ACM international joint conference on pervasive and ubiquitous computing, 2013. ACM, Zurich, Switzerland, pp 235–244Google Scholar
  31. 31.
    Abowd GD (2012) What next, ubicomp? celebrating an intellectual disappearing act. In: Proceedings of the 2012 ACM conference on ubiquitous computing, 2012. ACM, Pittsburgh, Pennsylvania, pp 31–40Google Scholar
  32. 32.
    Chen L et al (2012) Sensor-based activity recognition. IEEE Trans Syst Man Cybern Part C (Appl Rev) 42(6):790–808CrossRefGoogle Scholar
  33. 33.
    Plötz T, Guan Y (2018) Deep learning for human activity recognition in mobile computing. Computer 51(5):50–59CrossRefGoogle Scholar
  34. 34.
    Li H et al (2018) On specialized window lengths and detector based human activity recognition. In: Proceedings of the 2018 ACM international symposium on wearable computers, 2018. ACM, Singapore, Singapore, pp 68–71Google Scholar
  35. 35.
    Figo D et al (2010) Preprocessing techniques for context recognition from accelerometer data. Pers Ubiquit Comput 14(7):645–662CrossRefGoogle Scholar
  36. 36.
    Hammerla NY et al (2013) On preserving statistical characteristics of accelerometry data using their empirical cumulative distribution. In: Proceedings of the 2013 international symposium on wearable computers, 2013. ACM, Zurich, Switzerland, pp 65–68Google Scholar
  37. 37.
    Kwon H et al (2018) Adding structural characteristics to distribution-based accelerometer representations for activity recognition using wearables. In: Proceedings of the 2018 ACM international symposium on wearable computers, 2018. ACM, Singapore, Singapore, pp 72–75Google Scholar
  38. 38.
    Ploetz T et al (2012) Automatic synchronization of wearable sensors and video-cameras for ground truth annotation —a practical approach. In: 2012 16th international symposium on wearable computersGoogle Scholar
  39. 39.
    Hsu WY et al (2012) Effects of repetitive transcranial magnetic stimulation on motor functions in patients with stroke: a meta-analysis. Stroke 43(7):1849–1857CrossRefGoogle Scholar
  40. 40.
    Ferrari F et al (2002) Cramped synchronized general movements in preterm infants as an early marker for cerebral palsy. Arch Pediatr Adolesc Med 156(5):460–467CrossRefGoogle Scholar
  41. 41.
    Dietterich TG et al (1997) Solving the multiple instance problem with axis-parallel rectangles. % J Artif Intell 89(1–2):31–71CrossRefGoogle Scholar
  42. 42.
    Weidmann N, Frank E, Pfahringer B (2003) A two-level learning method for generalized multi-instance problems. In: Proceedings of the 14th European conference on machine learning, 2003. Springer, Cavtat-Dubrovnik, Croatia, pp 468–479CrossRefGoogle Scholar
  43. 43.
    Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, HobokenzbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Yan Gao
    • 1
  • Yang Long
    • 1
  • Yu Guan
    • 1
  • Anna Basu
    • 2
  • Jessica Baggaley
    • 3
  • Thomas Plötz
    • 4
    Email author
  1. 1.Open Lab, School of Computing, Newcastle UniversityNewcastle upon TyneUK
  2. 2.Institute of Health and Society, Newcastle UniversityNewcastle upon TyneUK
  3. 3.Institute of Neuroscience, Newcastle UniversityNewcastle upon TyneUK
  4. 4.School of Interactive ComputingGeorgia Institute of TechnologyAtlantaUSA

Personalised recommendations