Intelligent wearable allows out-of-the-lab tracking of developing motor abilities in infants
Manu Airaksinen, Anastasia Gallen, Anna Kivi, Pavithra Vijayakrishnan, Taru Häyrinen, Elina Ilén, Okko Räsänen, Leena M Haataja, Sampsa Vanhatalo, Manu Airaksinen, Anastasia Gallen, Anna Kivi, Pavithra Vijayakrishnan, Taru Häyrinen, Elina Ilén, Okko Räsänen, Leena M Haataja, Sampsa Vanhatalo
Abstract
Background: Early neurodevelopmental care needs better, effective and objective solutions for assessing infants' motor abilities. Novel wearable technology opens possibilities for characterizing spontaneous movement behavior. This work seeks to construct and validate a generalizable, scalable, and effective method to measure infants' spontaneous motor abilities across all motor milestones from lying supine to fluent walking.
Methods: A multi-sensor infant wearable was constructed, and 59 infants (age 5-19 months) were recorded during their spontaneous play. A novel gross motor description scheme was used for human visual classification of postures and movements at a second-level time resolution. A deep learning -based classifier was then trained to mimic human annotations, and aggregated recording-level outputs were used to provide posture- and movement-specific developmental trajectories, which enabled more holistic assessments of motor maturity.
Results: Recordings were technically successful in all infants, and the algorithmic analysis showed human-equivalent-level accuracy in quantifying the observed postures and movements. The aggregated recordings were used to train an algorithm for predicting a novel neurodevelopmental measure, Baba Infant Motor Score (BIMS). This index estimates maturity of infants' motor abilities, and it correlates very strongly (Pearson's r = 0.89, p < 1e-20) to the chronological age of the infant.
Conclusions: The results show that out-of-hospital assessment of infants' motor ability is possible using a multi-sensor wearable. The algorithmic analysis provides metrics of motility that are transparent, objective, intuitively interpretable, and they link strongly to infants' age. Such a solution could be automated and scaled to a global extent, holding promise for functional benchmarking in individualized patient care or early intervention trials.
Keywords: Biomarkers; Paediatric research.
Conflict of interest statement
Competing interestsThe authors declare the following competing interests: E.I. is the founder and shareholder of Planno Ltd, which consults in technical textile design and manufacturing. The remaining authors declare no competing interests.
© The Author(s) 2022.
Figures
References
- Olusanya BO, et al. The conundrum of a global tool for early childhood development to monitor SDG indicator 4.2.1. Lancet Global Health. 2021;9:e586–e587. doi: 10.1016/S2214-109X(21)00030-9.
- Rosenberg SA, Zhang D, Robinson CC. Prevalence of developmental delays and participation in early intervention services for young children. Pediatrics. 2008;121:1503–1509. doi: 10.1542/peds.2007-1680.
- Bax M, et al. Proposed definition and classification of cerebral palsy, April 2005. Dev. Med. Child Neurol. 2005;47:571–576. doi: 10.1017/S001216220500112X.
- Rancken, E. J., Metsäranta, M. P. H., Gissler, M., Rahkonen, L. K. & Haataja, L. M. Endogenous erythropoietin at birth is associated with neurodevelopmental morbidity in early childhood. Pediatric Res.10.1038/s41390-021-01679-0 (2021).
- Serenius F, et al. Neurodevelopmental outcomes among extremely preterm infants 6.5 years after active perinatal care in Sweden. JAMA Pediatr. 2016;170:954–963. doi: 10.1001/jamapediatrics.2016.1210.
- Hadders-Algra, M. Early Diagnostics and early intervention in neurodevelopmental disorders—Age-dependent challenges and opportunities. J. Clin. Med.10, 861 (2021).
- Iverson JM. Developmental variability and developmental cascades: lessons from motor and language development in infancy. Curr Dir Psychol Sci. 2021;30:228–235. doi: 10.1177/0963721421993822.
- Bornstein MH, Hahn C-S, Suwalsky JTD. Physically developed and exploratory young infants contribute to their own long-term academic achievement. Psychol Sci. 2013;24:1906–1917. doi: 10.1177/0956797613479974.
- LeBarton ES, Iverson JM. Associations between gross motor and communicative development in at-risk infants. Infant Behav. Dev. 2016;44:59–67. doi: 10.1016/j.infbeh.2016.05.003.
- Romeo DM, et al. Hammersmith Infant Neurological Examination for infants born preterm: predicting outcomes other than cerebral palsy. Dev. Med. Child Neurol. 2021;63:939–946. doi: 10.1111/dmcn.14768.
- Uusitalo K, et al. Hammersmith infant neurological examination and long-term cognitive outcome in children born very preterm. Dev. Med. Child Neurol. 2021;63:947–953. doi: 10.1111/dmcn.14873.
- Adolph KE, Hoch JE. Motor development: embodied, embedded, enculturated, and enabling. Annu. Rev. Psychol. 2019;70:141–164. doi: 10.1146/annurev-psych-010418-102836.
- Lancaster GA, et al. Creation of the WHO indicators of infant and young child development (IYCD): metadata synthesis across 10 countries. BMJ Global Health. 2018;3:e000747. doi: 10.1136/bmjgh-2018-000747.
- Hadders-Algra M, Tacke U, Pietz J, Rupp A, Philippi H. Reliability and predictive validity of the Standardized Infant NeuroDevelopmental Assessment neurological scale. Dev. Med. Child Neurol. 2019;61:654–660. doi: 10.1111/dmcn.14045.
- De Kegel A, et al. New reference values must be established for the Alberta Infant Motor Scales for accurate identification of infants at risk for motor developmental delay in Flanders. Child Care, Health Dev. 2013;39:260–267. doi: 10.1111/j.1365-2214.2012.01384.x.
- Adolph KE, Hoch JE, Cole WG. Development (of walking): 15 suggestions. Trends Cogn. Sci. 2018;22:699–711. doi: 10.1016/j.tics.2018.05.010.
- Dusing SC. Postural variability and sensorimotor development in infancy. Dev. Med. Child Neurol. 2016;58:17–21. doi: 10.1111/dmcn.13045.
- Haataja L, et al. Optimality score for the neurologic examination of the infant at 12 and 18 months of age. J. Pediatr. 1999;135:153–161. doi: 10.1016/S0022-3476(99)70016-8.
- Hecker, E., Baer, G. D., Stark, C., Herkenrath, P. & Hadders-Algra, M. Inter- and intrarater reliability of the infant motor profile in 3- to 18-month-old infants. Pediatr. Phys. Ther.28, 217–22 (2016).
- Hadders-Algra M, Heineman KR, Bos AF, Middelburg KJ. The assessment of minor neurological dysfunction in infancy using the Touwen Infant Neurological Examination: strengths and limitations. Dev. Med. Child Neurol. 2010;52:87–92. doi: 10.1111/j.1469-8749.2009.03305.x.
- Boggs D, et al. Rating early child development outcome measurement tools for routine health programme use. Arch. Dis. Child. 2019;104:S22. doi: 10.1136/archdischild-2018-315431.
- Airaksinen M, et al. Automatic posture and movement tracking of infants with wearable movement sensors. Sci. Rep. 2020;10:169. doi: 10.1038/s41598-019-56862-5.
- Wilson, R. B., Vangala, S., Elashoff, D., Safari, T. & Smith, B. A. Using wearable sensor technology to measure motion complexity in infants at high familial risk for autism spectrum disorder. Sensors21, 616 (2021).
- Straczkiewicz M, James P, Onnela J-P. A systematic review of smartphone-based human activity recognition methods for health research. npj Digit. Med. 2021;4:148. doi: 10.1038/s41746-021-00514-4.
- Schachner A, Carey S. Reasoning about ‘irrational’ actions: When intentional movements cannot be explained, the movements themselves are seen as the goal. Cognition. 2013;129:309–327. doi: 10.1016/j.cognition.2013.07.006.
- Oord, A. van den, Li, Y. & Vinyals, O. Representation learning with contrastive predictive coding. Preprint at arXiv:1807.03748 [cs, stat] (2019).
- Piper, M. C. & Darrah, J. Motor Assessment of the Developing Infant (Saunders, 1994).
- van Iersel PAM, la Bastide-van Gemert S, Wu Y-C, Hadders-Algra M. Alberta Infant Motor Scale: cross-cultural analysis of gross motor development in Dutch and Canadian infants and introduction of Dutch norms. Early Hum. Dev. 2020;151:105239. doi: 10.1016/j.earlhumdev.2020.105239.
- Diedenhofen B, Musch J. cocor: a comprehensive solution for the statistical comparison of correlations. PLoS ONE. 2015;10:e0121945. doi: 10.1371/journal.pone.0121945.
- Airaksinen, M. MATLAB analysis scripts used in the article ‘Intelligent wearable allows out-of-the-lab tracking of developing motor abilities in infants’. Zenodo10.5281/zenodo.6417486 (2022).
- Landis JR, Koch GG. The measurement of observer agreement for categorical data. Biometrics. 1977;33:159–174. doi: 10.2307/2529310.
- Massey SL, et al. Interrater and intrarater agreement in neonatal electroencephalogram background scoring. J. Clin. Neurophysiol. 2019;36:1–8. doi: 10.1097/WNP.0000000000000534.
- Pouppirt NR, et al. The general movements assessment in neonates with hypoxic ischemic encephalopathy. J. Child Neurol. 2021;36:601–609. doi: 10.1177/0883073820981515.
- Banville H, Chehab O, Hyvärinen A, Engemann D-A, Gramfort A. Uncovering the structure of clinical EEG signals with self-supervised learning. J. Neural. Eng. 2021;18:046020. doi: 10.1088/1741-2552/abca18.
- van der Maaten L, Hinton G. Visualizing data using t-SNE. J. Mach. Learn. Res. 2008;9:2579–2605.
- Hadders-Algra M. Early human motor development: from variation to the ability to vary and adapt. Neurosci. Biobehav. Rev. 2018;90:411–427. doi: 10.1016/j.neubiorev.2018.05.009.
- Miller LE, Perkins KA, Dai YG, Fein DA. Comparison of parent report and direct assessment of child skills in toddlers. Res. Autism Spectr. Disord. 2017;41–42:57–65. doi: 10.1016/j.rasd.2017.08.002.
- van Wassenaer-Leemhuis A. Parental report of early cognitive development: benefits, and next steps. Lancet Child Adolesc. Health. 2019;3:666–668. doi: 10.1016/S2352-4642(19)30190-7.
- Adolph KE, et al. How do you learn to walk? Thousands of steps and dozens of falls per day. Psychol. Sci. 2012;23:1387–1394. doi: 10.1177/0956797612446346.
- Sgandurra G, et al. A randomized clinical trial in preterm infants on the effects of a home-based early intervention with the ‘CareToy System’. PLoS ONE. 2017;12:e0173521. doi: 10.1371/journal.pone.0173521.
- Tataranno ML, Vijlbrief DC, Dudink J, Benders MJNL. Precision medicine in neonates: a tailored approach to neonatal brain injury. Front. Pediatr. 2021;9:418. doi: 10.3389/fped.2021.634092.
- Beltrán, M. I., Dudink, J., de Jong, T. M., Benders, M. J. N. L. & van den Hoogen, A. Sensory-based interventions in the NICU: systematic review of effects on preterm brain development. Pediatr. Res.10.1038/s41390-021-01718-w (2021).
- Greenspan B, Cunha AB, Lobo MA. Design and validation of a smart garment to measure positioning practices of parents with young infants. Infant Behav. Dev. 2021;62:101530. doi: 10.1016/j.infbeh.2021.101530.
- Jeong H, et al. Miniaturized wireless, skin-integrated sensor networks for quantifying full-body movement behaviors and vital signs in infants. Proc Natl Acad Sci USA. 2021;118:e2104925118. doi: 10.1073/pnas.2104925118.
- Mirelman A, et al. Detecting sensitive mobility features for Parkinson’s disease stages via machine learning. Mov. Disord. 2021;36:2144–2155. doi: 10.1002/mds.28631.
- Velázquez-Pérez L, et al. Prodromal spinocerebellar ataxia type 2 subjects have quantifiable gait and postural sway deficits. Mov. Disord. 2021;36:471–480. doi: 10.1002/mds.28343.
- Dunn J, Runge R, Snyder M. Wearables and the medical revolution. Per. Med. 2018;15:429–448. doi: 10.2217/pme-2018-0044.
- Jun, K. & Choi, S. Unsupervised end-to-end deep model for newborn and infant activity recognition. Sensors20, 6467 (2020).
- Kwon, S., Zavos, P., Nickele, K., Sugianto, A. & Albert, M. V. Hip and wrist-worn accelerometer data analysis for toddler activities. Int. J. Environ. Res. Public Health16, 2598 (2019).
- Touwen BCL. Variability and stereotypy of spontaneous motility as a predictor of neurological development of preterm infants. Dev. Med. Child Neurol. 1990;32:501–508. doi: 10.1111/j.1469-8749.1990.tb16975.x.
- Hadders-Algra M. Typical and atypical development of reaching and postural control in infancy. Dev. Med. Child Neurol. 2013;55:5–8. doi: 10.1111/dmcn.12298.
- Raghuram K, et al. Automated movement recognition to predict motor impairment in high-risk infants: a systematic review of diagnostic test accuracy and meta-analysis. Dev. Med. Child Neurol. 2021;63:637–648. doi: 10.1111/dmcn.14800.
- Einspieler C, Prayer D, Marschik PB. Fetal movements: the origin of human behaviour. Dev. Med. Child Neurol. 2021;63:1142–1148. doi: 10.1111/dmcn.14918.
- Severson KA, et al. Discovery of Parkinson’s disease states and disease progression modelling: a longitudinal data study using machine learning. The Lancet Digital Health. 2021;3:e555–e564. doi: 10.1016/S2589-7500(21)00101-1.
- Oren O, Gersh BJ, Bhatt DL. Artificial intelligence in medical imaging: switching from radiographic pathological data to clinically meaningful endpoints. The Lancet Digital Health. 2020;2:e486–e488. doi: 10.1016/S2589-7500(20)30160-6.
- Futoma J, Simons M, Panch T, Doshi-Velez F, Celi LA. The myth of generalisability in clinical research and machine learning in health care. The Lancet Digital Health. 2020;2:e489–e492. doi: 10.1016/S2589-7500(20)30186-2.
- Valavani E, et al. Language function following preterm birth: prediction using machine learning. Pediatr. Res. 2021 doi: 10.1038/s41390-021-01779-x.
- Prosser LA, Lauer RT, VanSant AF, Barbe MF, Lee SCK. Variability and symmetry of gait in early walkers with and without bilateral cerebral palsy. Gait Posture. 2010;31:522–526. doi: 10.1016/j.gaitpost.2010.03.001.
- Ryll UC, et al. Early prediction of unilateral cerebral palsy in infants with asymmetric perinatal brain injury – Model development and internal validation. Eur. J. Paediatr. Neurol. 2019;23:621–628. doi: 10.1016/j.ejpn.2019.04.004.
- Hewitt, L., Kerr, E., Stanley, R. M. & Okely, A. D. Tummy time and infant health outcomes: a systematic review. Pediatrics145, e20192168 (2020).
- Centers for Disease Control and Prevention. WHO growth standards are recommended for use in the U.S. for infants and children 0 to 2 years of age. (2010).
- Stevenson NJ, et al. Automated cot-side tracking of functional brain age in preterm infants. Ann. Clin. Transl. Neurol. 2020;7:891–902. doi: 10.1002/acn3.51043.
- Pillay K, Dereymaeker A, Jansen K, Naulaers G, De Vos M. Applying a data-driven approach to quantify EEG maturational deviations in preterms with normal and abnormal neurodevelopmental outcomes. Sci. Rep. 2020;10:7288. doi: 10.1038/s41598-020-64211-0.
- Dubowitz LMS, Dubowitz V, Goldberg C. Clinical assessment of gestational age in the newborn infant. J. Pediatr. 1970;77:1–10. doi: 10.1016/S0022-3476(70)80038-5.
- Shimony JS, et al. Comparison of cortical folding measures for evaluation of developing human brain. NeuroImage. 2016;125:780–790. doi: 10.1016/j.neuroimage.2015.11.001.
- Baecker L, Garcia-Dias R, Vieira S, Scarpazza C, Mechelli A. Machine learning for brain age prediction: Introduction to methods and clinical applications. EBioMedicine. 2021;72:103600. doi: 10.1016/j.ebiom.2021.103600.
- Touwen BCL, Hempel MS, Westra LC. The development of crawling between 18 months and four years. Dev. Med. Child Neurol. 1992;34:410–416. doi: 10.1111/j.1469-8749.1992.tb11453.x.
- Lee CS, Lee AY. Clinical applications of continual learning machine learning. The Lancet Digital Health. 2020;2:e279–e281. doi: 10.1016/S2589-7500(20)30102-3.
- Muñoz-Organero, M., Powell, L., Heller, B., Harpin, V. & Parker, J. Automatic extraction and detection of characteristic movement patterns in children with ADHD based on a convolutional neural network (CNN) and acceleration images. Sensors18, 3924 (2018).
- Debache, I., Jeantet, L., Chevallier, D., Bergouignan, A. & Sueur, C. A Lean and performant hierarchical model for human activity recognition using body-mounted sensors. Sensors20, 3090 (2020).
- Ghassabian, A. et al. Gross motor milestones and subsequent development. Pediatrics138, e20154372 (2016).
- Camerota M, Willoughby MT. Prenatal risk predicts preschooler executive function: a cascade model. Child Dev. 2020;91:e682–e700. doi: 10.1111/cdev.13271.
- Yoshii, K., Michihata, N., Hirasawa, K., Nagata, S. & Morisaki, N. Secular trends in early motor development between 1980 and 2010 in Japan. Arch Dis Child10.1136/archdischild-2021-322087 (2021).
- Abrishami MS, et al. Identification of developmental delay in infants using wearable sensors: full-day leg movement statistical feature analysis. IEEE J. Transl. Eng. Health Med. 2019;7:1–7. doi: 10.1109/JTEHM.2019.2893223.
- Franchak, J. M., Scott, V. & Luo, C. A. Contactless method for measuring full-day, naturalistic motor behavior using wearable inertial sensors. Front. Psychol.12, 701343 (2021).
- Franchak JM. Changing opportunities for learning in everyday life: infant body position over the first year. Infancy. 2019;24:187–209. doi: 10.1111/infa.12272.
- Tveten KM, et al. Intra- and inter-rater reliability of the infant motor profile in infants in primary health care. null. 2020;40:571–581.
- Muehlematter UJ, Daniore P, Vokinger KN. Approval of artificial intelligence and machine learning-based medical devices in the USA and Europe (2015–20): a comparative analysis. The Lancet Digital Health. 2021;3:e195–e203. doi: 10.1016/S2589-7500(20)30292-2.
- Vokinger KN, Feuerriegel S, Kesselheim AS. Continual learning in medical devices: FDA’s action plan and beyond. The Lancet Digital Health. 2021;3:e337–e338. doi: 10.1016/S2589-7500(21)00076-5.
Source: PubMed