Classification of mild and severe adolescent idiopathic scoliosis (AIS) from healthy subjects via a supervised learning model based on electromyogram and ground reaction force data during gait

• Autorzy: Sikidar Arnab , Vidyasagar Koyyana Eshwar Chandra , Gupta Manish , Garg Bhavuk , Kalyanasundaram Dinesh

Identyfikatory

DOI

10.1016/j.bbe.2022.06.006

• Języki publikacji: EN

Abstrakty

EN

At early stages, adolescent idiopathic scoliosis (AIS) is quite hard to be distinguished from healthy (HC) subjects by the naked eye. AIS demands multiple corrective surgeries when detected later, thereby causing significant physical and psychological trauma as no mathematical models exist for the classification of mild AIS (MS) (20° < Cobb’s angle < 40°) from HC, we propose a k-nearest neighbour (kNN) method based model. In this work, we collected both the EMG and GRF data from nine severe AIS (SS), three MS and four female HC during gait. Delayed muscle activation in Erector spinatus Iliocostalis, Gluteus Medius and Gastrocnemius lateralis was observed in SS compared to HC. However, no such distinction was noticed between MS and HC motivating for a mathematical model. Eighteen time-domain and nine frequency-domain features were computed from the EMG data of 14 lower extremity muscles, while five time-domain features were calculated from GRF data during gait. Out of all the features computed for each subject, the principal component analysis (PCA) yielded 15 principal components that coupled both time and frequency domains (TFD). Further, the kNN model classified SS, MS and HC from each other by these 15 TFD features. The model was trained and validated using 32 and 21 EMG and GRF data datasets during gait, respectively. The classification and validation accuracy of 90.6% and 85.7% were obtained among SS, MS and HC. The proposed model is capable of early detection of AIS and can be used by medical professionals to plan treatments and corrective measures.

Słowa kluczowe

EN

adolescence idiopathic scoliosis; electromyogram; lower extremity; K-nearest neighbour; principal component analysis

PL

skolioza idiopatyczna; elektromiogram; kończyna dolna; analiza składowych głównych

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2022
• Tom: Vol. 42, no. 3
• Strony: 870--887
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr.

Twórcy

autor

Sikidar Arnab

• Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India

autor

Vidyasagar Koyyana Eshwar Chandra

• Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi, India
• Department of Biomedical Engineering, College of Engineering, Osmania University, Hyderabad, India

autor

Gupta Manish

• Department of Orthopedics, All India Institute of Medical Sciences, New Delhi, India

autor

Garg Bhavuk

• Department of Orthopedics, All India Institute of Medical Sciences, New Delhi, India

autor

Kalyanasundaram Dinesh

• Centre for Biomedical Engineering, Indian Institute of Technology Delhi, New Delhi 110016, India
• Department of Biomedical Engineering, All India Institute of Medical Sciences, New Delhi, India

Bibliografia

• [1] Di Pauli T, von Treuheim DT, Li C, Mikhail D, Cataldo DR, Cooperman BG, et al. Reliable skeletal maturity assessment for an AIS patient cohort: external validation of the proximal humerus ossification system (PHOS) and relevant learning methodology. Spine Deform 2020;8:613–20. https://doi.org/10.1007/s43390-020-00105-5.
• [2] Pesenti S, Pomero V, Prost S, Severyns M, Authier G, Roscigni L, et al. Curve location influences spinal balance in coronal and sagittal planes but not transversal trunk motion in adolescents with idiopathic scoliosis: a prospective observational study. Eur Spine J 2020;29:1972–80. https://doi.org/10.1007/s00586-020-06361-3.
• [3] Haddas R, Kosztowski T, Mar D, Boah A, Lieberman IH. Balance effort, Cone of Economy, and dynamic compensatory mechanisms in common degenerative spinal pathologies. Gait Posture 2021;89:67–73. https://doi.org/10.1016/j.gaitpost.2021.04.038.
• [4] Sampiev MT, Zagorodniy NV, Lysenko IS, Dubinin IP, CHemurzieva KHM. Two-stage treatment of idiopathic scoliosis using the LSZ growing system with a 10-year followup: a case report. J Surg Case Reports 2022:1–3. https://doi.org/10.1093/jscr/rjac087.
• [5] Machino M, Kawakami N, Ohara T, Saito T, Tauchi R. Factors affecting postoperative pulmonary function deterioration in adolescent idiopathic scoliosis: A prospective study using 3-dimensional image reconstruction by biplanar stereoradiography. J Clin Neurosci 2022;98:182–8. https://doi.org/10.1016/j.jocn.2022.02.014.
• [6] Zhu TB, Wang YS, Xie JM, Zhang Y, Zhao Z, Li T, et al. Development and initial validation of classification for severe spinal deformity based on X-ray features. Eur Spine J 2022;31:79–87. https://doi.org/10.1007/s00586-021-07028-3.
• [7] Belli G, Toselli S, Latessa PM, Mauro M. Evaluation of self-perceived body image in adolescents with mild idiopathic scoliosis. Eur J Invest Heal Psychol Educ 2022;12:319–33. https://doi.org/10.3390/ejihpe12030023.
• [8] Tajdari M, Pawar A, Li H, Tajdari F, Maqsood A, Cleary E, et al. Image-based modelling for Adolescent Idiopathic Scoliosis: Mechanistic machine learning analysis and prediction. Comput Methods Appl Mech Eng 2021;374:113590. https://doi.org/10.1016/j.cma.2020.113590.
• [9] Sung PS, Park MS. Compensatory ground reaction forces during scoliotic gait in subjects with and without right adolescent idiopathic scoliosis. Symmetry (Basel) 2021;13:2372. https://doi.org/10.3390/sym13122372.
• [10] Vergari C, Skalli W, Abelin-Genevois K, Bernard JC, Hu Z, Cheng JCY, et al. Effect of curve location on the severity index for adolescent idiopathic scoliosis: a longitudinal cohort study. Eur Radiol 2021;31:8488–97. https://doi.org/10.1007/s00330-021-07944-4.
• [11] Haddas R, Ju KL, Belanger T, Lieberman IH. The use of gait analysis in the assessment of patients afflicted with spinal disorders. Eur Spine J 2018;27:1712–23. https://doi.org/10.1007/s00586-018-5569-1.
• [12] Yoo Y-J, Park J-G, Jo L, Hwang Y, Yoon M-J, Kim J-S, et al. Factors influencing the progression and direction of scoliosis in children with neurological disorders. Children 2022;9(1):81.
• [13] Popov I, Lisitsa N, Baloshin Y, Dudin M, Bober S. Variational model of scoliosis. Theor Appl Mech 2018;45:167–75. https://doi.org/10.2298/TAM170818012P.
• [14] Yılmaz H, Zateri C, Kusvuran Ozkan A, Kayalar G, Berk H. Prevalence of adolescent idiopathic scoliosis in Turkey: an epidemiological study. Spine J 2020;20:947–55. https://doi.org/10.1016/j.spinee.2020.01.008.
• [15] Motyer GS, Kiely PJ, Fitzgerald A. Adolescents’ Experiences of Idiopathic Scoliosis in the Presurgical Period: A Qualitative Study. J Pediatr Psychol 2022;47:225–35. https://doi.org/10.1093/jpepsy/jsab095.
• [16] Hatzilazaridis I, Hatzitaki V, Antoniadou N, Samoladas E. Postural and muscle responses to galvanic vestibular stimulation reveal a vestibular deficit in adolescents with idiopathic scoliosis. Eur J Neurosci 2019;50(10):3614–26. https://doi.org/10.1111/ejn.14525.
• [17] Haddas R, Lieberman IH, Kakar RS. A Comparison of muscular activity during gait between walking sticks and a walker in patients with adult degenerative scoliosis. Spine Deform 2019;7:454–66. https://doi.org/10.1016/j.jspd.2018.09.067.
• [18] Roy S, Grünwald ATD, Alves-Pinto A, Lampe R. Automatic analysis method of 3D images in patients with scoliosis by quantifying asymmetry in transverse contours. Biocybern Biomed Eng 2020;40:1486–98. https://doi.org/10.1016/j.bbe.2020.09.001.
• [19] Gao C-C, Chern J-S, Chang C-J, Lai P-L, Lung C-W, Tulchin-Francis K. Center of pressure progression patterns during level walking in adolescents with idiopathic scoliosis. PLoS ONE 2019;14(4):e0212161. https://doi.org/10.1371/journal.pone.0212161.
• [20] Al-Mohrej OA, Aldakhil SS, Al-Rabiah MA, Al-Rabiah AM. Surgical treatment of adolescent idiopathic scoliosis: complications. Ann Med Surg 2020;52:19–23. https://doi.org/10.1016/j.amsu.2020.02.004.
• [21] Le Berre M, Pradeau C, Brouillard A, Coget M, Massot C, Catanzariti JF. Do adolescents with idiopathic scoliosis have an erroneous perception of the gravitational vertical? Spine Deform 2019;7:71–9. https://doi.org/10.1016/j.jspd.2018.05.004.
• [22] Tahirbegolli B, Obertinca R, Bytyqi A, Kryeziu B, Hyseni B, Taganoviq B, et al. Factors affecting the prevalence of idiopathic scoliosis among children aged 8–15 years in Prishtina, Kosovo. Sci Rep 2021;11:1–7. https://doi.org/10.1038/s41598-021-96398-1.
• [23] Zhu F, Hong Q, Guo X, Wang D, Chen J, Zhu Q, Zhang C, Chen W, Zhang M. A comparison of foot posture and walking performance in patients with mild, moderate, and severe adolescent idiopathic scoliosis. PLoS One 2021;16:e0251592. https://doi.org/10.1371/journal.pone.0251592.
• [24] Peng J. Evaluation of the effectiveness of artificial neural network based on correcting scoliosis and improving spinal health in university students. J Healthc Eng 2022;2022:1–9. https://doi.org/10.1155/2022/2092034.
• [25] Sklensky J, Urbasek K, Svehlik M, Svozilova V, Kocanda J, Prymek M, et al. The relationship of hip loading asymmetry and radiological parameters of the spine in Lenke type 1 idiopathic scoliosis. Gait Posture 2022;94:160–5. https://doi.org/10.1016/j.gaitpost.2022.03.005.
• [26] Khorrami Chokami A, Gasparini M, Merletti R. Identification of periodic bursts in surface EMG: Applications to the erector spinae muscles of sitting violin players. Biomed Signal Process Control 2021;65:102369. https://doi.org/10.1016/j.bspc.2020.102369.
• [27] Garg B, Gupta M, Mehta N, Malhotra R. Influence of etiology and onset of deformity on spatiotemporal, kinematic, kinetic, and electromyography gait variables in patients with scoliosis-a prospective, comparative study. Spine (Phila Pa 1976) 2021;46:374–82. https://doi.org/10.1097/BRS.0000000000003796.
• [28] Remeseiro B, Bolon-Canedo V. A review of feature selection methods in medical applications. Comput Biol Med 2019;112:103375. https://doi.org/10.1016/j.compbiomed.2019.103375.
• [29] Elsais WM, Preece SJ, Jones RK, Herrington L. Between-day repeatability of lower limb EMG measurement during running and walking. J Electromyogr Kinesiol 2020;55:102473. https://doi.org/10.1016/j.jelekin.2020.102473.
• [30] Bains MK, Gait analysis in adolescents with idiopathic scoliosis: A systematic review. 2015.
• [31] Haris M, Chakraborty P, Rao BV. EMG signal based finger movement recognition for prosthetic hand control. In: Commun. Control Intell. Syst.. IEEE; 2015. p. 194–8. https://doi.org/10.1109/CCIntelS.2015.7437907.
• [32] Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl 2012;39:7420–31. https://doi.org/10.1016/j.eswa.2012.01.102.
• [33] Wu KW, Wang TM, Hu CC, Hong SW, Lee PA, Lu TW. Postural adjustments in adolescent idiopathic thoracic scoliosis during walking. Gait Posture 2019;68:423–9. https://doi.org/10.1016/j.gaitpost.2018.12.024.
• [34] Jafarnezhadgero AA, Fatollahi A, Amirzadeh N, Siahkouhian M, Granacher U, Mirkov D. Ground reaction forces and muscle activity while walking on sand versus stable ground in individuals with pronated feet compared with healthy controls. PLoS ONE 2019;14(9):e0223219. https://doi.org/10.1371/journal.pone.0223219.
• [35] Zhou X, Li X, Wu Q, Liang J, Guo H, Jin M, et al. Three-dimensional corrective exercise therapy for idiopathic scoliosis: study protocol for a prospective non-randomized trial. BMC Musculoskelet Disord 2022;23:1–9. https://doi.org/10.1186/s12891-022-05057-7.
• [36] Cheung M-C, Yip J, Lai JSK, de Mauroy JC. Biofeedback posture training for adolescents with mild scoliosis. Biomed Res Int 2022;2022:1–8. https://doi.org/10.1155/2022/5918698.
• [37] Loughenbury PR, Tsirikos AI. Current concepts in the treatment of neuromuscular scoliosis: clinical assessment, treatment options, and surgical outcomes. Bone Jt Open 2022;3:85–92. https://doi.org/10.1302/2633-1462.31.bjo-2021-0178.r1.
• [38] Park J, So W-Y. The effect of the schroth rehabilitation exercise program on spinal and feet alignment in adolescent patients with idiopathic scoliosis: A pilot study. Healthc2022;10(2):398.
• [39] Marin L, Lovecchio N, Pedrotti L, Manzoni F, Febbi M, Albanese I, et al. Acute effects of self-correction on spine deviation and balance in adolescent girls with idiopathic scoliosis. Sensors 2022;22:1–9. https://doi.org/10.3390/s22051883.
• [40] B S, M R, S A, C F. Identification of the most relevant intervertebral effort indicators during gait of adolescents with idiopathic scoliosis. Comput Methods Biomech Biomed Eng 2020;23(10):664–74. https://doi.org/10.1080/10255842.2020.1758075.
• [41] Wick J, Le H, Lafage R, Gupta M, Hart R, Mundis Gregory J, et al., Assessment of adult spinal deformity complication timing and impact on two-year outcomes using a comprehensive adult spinal deformity classification system, Spine (Phila. Pa. 1976). 2021. Doi: 10.1097/BRS.0000000000004289.
• [42] Holewijn RM, Kingma I, de Kleuver M, Schimmel JJP, Keijsers NLW. Spinal fusion limits upper body range of motion during gait without inducing compensatory mechanisms in adolescent idiopathic scoliosis patients. Gait Posture 2017;57:1–6. https://doi.org/10.1016/j.gaitpost.2017.05.017.
• [43] Pesenti S, Prost S, Pomero V, Authier G, Severyns M, Roscigni L, et al. Early dynamic changes within the spine following posterior fusion using hybrid instrumentation in adolescents with idiopathic scoliosis: a gait analysis study. Arch Orthop TraumaSurg 2021. https://doi.org/10.1007/s00402-021-03956-3.
• [44] Kokabu T, Kanai S, Kawakami N, Uno K, Kotani T, Suzuki T, et al. An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection. Spine J 2021;21:980–7. https://doi.org/10.1016/j.spinee.2021.01.022.
• [45] Wu C, Meng G, Lian J, Xu J, Gao M, Huang C, et al. A multistage ensemble network system to diagnose adolescent idiopathic scoliosis. Eur Radiol 2022. https://doi.org/10.1007/s00330-022-08692-9.
• [46] Caesarendra W, Rahmaniar W, Mathew J, Thien A. Automated Cobb angle measurement for adolescent idiopathic scoliosis using convolutional neural network. Diagnostics 2022;12:396.
• [47] Li J, Li S, Yang Z, Wu T, Hu Y. An automatic scoliosis diagnosis platform based on deep learning approach. ACM Int Conf Proceeding Ser 2022:215–23. https://doi.org/10.1145/3512353.3512385.
• [48] Holewijn R, Kingma I, de Kleuver M, Schimmel J, Keijsers N, Near preoperative shoulder and trunk range of motion during gait after surgical correction of adolescent idiopathic scoliosis, Glob Spine J. 2016;6. Doi: 10.1055/s-0036-1582682.
• [49] Syczewska M, Kocel K, Święcicka A, Graff K, Krawczyk M, Wąsiewicz P, et al. Selection of gait parameters for modified Gillette Gait Index using Hellwig Correlation Based Filter method, random forest method, and correlation methods. Biocybern Biomed Eng 2020;40:1267–76. https://doi.org/10.1016/j.bbe.2020.07.002.