Skip to main content
SpringerLink
Log in

Neuroevolutionary intelligent system to aid diagnosis of motor impairments in children

  • Published:
Applied Intelligence Aims and scope Submit manuscript

Abstract

An early detection of motor impairments in children is essential to improve self-care. Nevertheless, it may not be straightforward to conduct all required assessments physically in a clinic. Previous efforts in providing such a classification leveraged Machine Learning (ML)-based techniques on centralised data collected from activities of daily living (ADL); however, they used black-box optimisation methods and classification approaches that are not generalisable, hindering their application and impact in a clinical setting from an applied intelligence perspective. Thus, this study developed, applied, and validated a novel two-step neuroevolutionary optimisation approach to achieve earlier convergence in a user-centred and explainable manner, by applying early stopping based on three cross-entropy loss functions (for training, validation, and test) and optimise hyperparameters concurrently to ensure generalisation of the predictive performance by design. This method was applied to a neural network-based decision support system for aiding detection of motor impairments using three publicly available datasets on 190 children with motor impairments, including 483 socio-demographic and clinical self-care-related features in total. Such biomarkers were based on “The International Classification of Functioning, Disability, and Health for Children and Youth” (ICF-CY) and retrieved from the University California Irvine ML database, which were leveraged for the initial model training, validation, and testing. Moreover, to increase users’ confidence and drive adoption of the proposed applied intelligence-based tool, two additional publicly available datasets were used for validating the proposed two-step neuroevolutionary approach; such data include 34 and 39 socio-demographic and self-care-related clinical characteristics features as indicators of the functional independence of 50 further children with motor disability from a hospital in the city of Salvador, State of Bahia in Brazil. A novel, explainable and generalisable two-step neuroevolutionary approach guided early stopping based on three cross-entropy loss functions and optimised hyperparameters concurrently to improve generalisation in a neural network-based classifier. The ability of the proposed hybrid decision support system to detect motor impairments in the paediatric subjects considered was evaluated as compared to the best-performing ML-based classification systems on the same benchmark datasets to date. Whilst leveraging a transparent optimisation approach, results demonstrate its superior generalisation, quantified via the classification accuracy and the area under the receiver operating characteristic curve, being almost 6% higher than the most accurate and reliable ML-based system on the same benchmark dataset from published studies, thus supporting its potential for aiding classification of self-care problems in children with physical and motor disability in a clinical setting.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

Similar content being viewed by others

Data availability

Two demographic features (years of age and sex (1 = male; 0 = female)) and two-hundred and four outcomes on self-care exercises based on ‘The International Classification of Functioning, Disability, and Health for Children and Youth’ ICF-CY on seventy (N = 70) children with motor impairments (29 males, 41 females; age: 12.26 ± 3.6 years) from the University of California Irvine (UCI) ML database were leveraged [12].

Moreover, two additional publicly available datasets [32, 33] were used for validating the proposed two-step neuroevolutionary approach; such data include 34 [33] and 39 [32] socio-demographic and self-care-related clinical characteristics features as indicators of the functional independence of 50 (26 and 24 respectively) further children with motor disability from a hospital in the city of Salvador, State of Bahia in Brazil.

References

  1. Aslam A (2013) The state of the world's children 2013: children with disabilities. United Nations Children's Fund (UNICEF)

  2. Baeza-Velasco C, Sinibaldi L, Castori M (2018) Attention-deficit/hyperactivity disorder, joint hypermobility-related disorders and pain: expanding body-mind connections to the developmental age. ADHD Atten Deficit Hyperactivity Dis 10(3):163–175

    Article  Google Scholar 

  3. Florea R, Florea R (2016) Individual and organizational implications of work-related stress. Econ Transdisciplinarity Cogn 19(1):28

    Google Scholar 

  4. Arbour KP, Latimer AE, Martin KA, Ginis, and Mary E. Jung. (2007) Moving beyond the stigma: the impression formation benefits of exercise for individuals with a physical disability. Adapt Phys Act Q 24(2):144–159

    Google Scholar 

  5. Scarpa S (2011) “The body in the mind. Role of sports practice in the self-description of one's body in adolescents and young people with motor disabilities”. Padua Research [Ph.D. thesis]

  6. Lawrence B (1991) Self-concept formation and physical handicap: some educational implications for integration. Disabil Handicap Soc 6(2):139–146

    Article  Google Scholar 

  7. Chawathe SS (2018) "Classifying self-care activities of children and youths with disabilities." In: 2018 9th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp. 922–928. IEEE

  8. Choudhury A (2019) "classification of functioning, disability, and health: ICF-CY self care (SCADI dataset) using predictive analytics." In: Choudhury A, classification of functioning, disability, and health: ICF-CY self care. (SCADI DATASET) using predictive analytics. In: Proceedings of the 2019 IISE annual conference. Edited by HE Romeijn AS, R. Thomas. Orlando: IISE

  9. Keleş MK, Kılıç Ü (2018) "Artificial bee colony algorithm for feature selection on scadi dataset." In: 2018 3rd International Conference on Computer Science and Engineering (UBMK), pp. 463–466. IEEE

  10. Putatunda S (2018) “Care2Vec: A Deep learning approach for the classification of self-care problems in physically disabled children”. arXiv preprint arXiv:1812.00715

  11. Souza PVC, dos Reis AG, Marques GRR, Guimaraes AJ, Araujo VJS, Araujo VS, Rezende TS, Batista LO, da Silva GA (2019) "Using hybrid systems in the construction of expert systems in the identification of cognitive and motor problems in children and young people." In: 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), pp. 1–6. IEEE

  12. Zarchi MS, Fatemi Bushehri SMM, Dehghanizadeh M (2018) SCADI: a standard dataset for self-care problems classification of children with physical and motor disability. Int J Med Inform 114:81–87

    Article  Google Scholar 

  13. Bushehri SMMF, Zarchi MS (2019) An expert model for self-care problems classification using probabilistic neural network and feature selection approach. Appl Soft Comput 82:105545

    Article  Google Scholar 

  14. Faris H, Aljarah I, Mirjalili S (2018) Improved monarch butterfly optimization for unconstrained global search and neural network training. Appl Intell 48(2):445–464

    Article  Google Scholar 

  15. Henderson CE et al (2000) Predicting aflatoxin contamination in peanuts: a genetic algorithm/neural network approach. Appl Intell 12(3):183–192

    Article  Google Scholar 

  16. Tsai J-T, Chou J-H, Liu T-K (2006) Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm. IEEE Trans Neural Netw 17(1):69–80

    Article  Google Scholar 

  17. Tong DL, Schierz AC (2011) Hybrid genetic algorithm-neural network: feature extraction for unpreprocessed microarray data. Artif Intell Med 53(1):47–56

    Article  Google Scholar 

  18. Malek H, Ebadzadeh MM, Rahmati M (2012) Three new fuzzy neural networks learning algorithms based on clustering, training error and genetic algorithm. Appl Intell 37(2):280–289

    Article  Google Scholar 

  19. Parisi L (2020) "m-arcsinh: An Efficient and Reliable Function for SVM and MLP in scikit-learn." arXiv preprint arXiv:2009.07530

  20. Parisi L, Ma R, RaviChandran N, Lanzillotta M (2020d) "hyper-sinh: An Accurate and Reliable Function from Shallow to Deep Learning in TensorFlow and Keras." arXiv preprint arXiv:2011.07661

  21. Parisi L, Ma R, Zaernia A, Youseffi M (2021a) M-ark-support vector machine for early detection of Parkinson’s disease from speech signals. Int J Math Comput Simul 15:34–41

  22. Parisi L, Ma R, Zaernia A, Youseffi M (2021b) Ηyper-sinhconvolutional neural network for early detection of Parkinson’s disease from spiral drawings. WSEAS Trans Comput Res 9:1–7

  23. Parisi L, Neagu D, Ma R, Campean F (2020c) "QReLU and m-QReLU: Two novel quantum activation functions to aid medical diagnostics." arXiv preprint arXiv:2010.08031

  24. Parisi L, Neagu D, Ma R, Campean F (2022) Quantum ReLU activation for convolutional neural networks to improve diagnosis of Parkinson’s disease and COVID-19. Expert Syst Appl:115892

  25. Parisi L (2019) “Machine learning-based feature selection and optimisation for clinical decision support systems. Optimal data-driven feature selection methods for binary and multi-class classification problems: towards a minimum viable solution for predicting early diagnosis and prognosis”. University of Bradford, UK, [Ph.D. thesis]

  26. Parisi L, Ravichandran N (2017) "Genetic algorithms and artificial neural networks for Optimising user control in hand prosthetic devices." In: AUT Mathematical Sciences Symposium, p. 16

  27. Parisi L, RaviChandran N (2020a) Evolutionary feature transformation to improve prognostic prediction of hepatitis. Knowl-Based Syst 200:106012

    Article  Google Scholar 

  28. Parisi L, RaviChandran N (2020b) Evolutionary Denoising-based machine learning for detecting knee disorders. Neural Process Lett 52(3):2565–2581

    Article  Google Scholar 

  29. Parisi L, RaviChandran N, Manaog ML (2018a) Decision support system to improve postoperative discharge: a novel multi-class classification approach. Knowl-Based Syst 152:1–10

    Article  Google Scholar 

  30. Parisi L, RaviChandran N (2018a) "Genetic algorithms and unsupervised machine learning for predicting robotic manipulation failures for force-sensitive tasks." In: 2018 4th International Conference on Control, Automation and Robotics (ICCAR), pp. 22–25. IEEE

  31. Parisi L, RaviChandran N (2018b) “Evolutionary Algorithms for Margin Maximisation of Support Vector Machine”. ANZAMP Meeting 2018 - Sixth Annual Meeting of The Australian and New Zealand Association of Mathematical Physics 1(1), 32

  32. Figueirêdo BBR d S, Magalhães PAF, de Andrade LB, Bezerra P, do Carmo-Menezes Bezerra Duarte M (2018) Level of independence, functional capacity and respiratory muscle strength of patients with mucopolysaccharidosis type VI in the Northeast of Brazil. Rev Bras Saúde Materno Infantil 18(1):83–92

    Article  Google Scholar 

  33. Lopes PS, Filho DPS, Matos MAA (2019) Functional independence of pediatric patients with mucopolysaccharidoses. Acta Ortop Bras 27(4):212–215

    Article  Google Scholar 

  34. Parisi L, RaviChandran N, Manaog ML (2018) Feature-driven machine learning to improve early diagnosis of Parkinson's disease. Expert Syst Appl 110:182–190

    Article  Google Scholar 

  35. Parisi L, Ravichandran N, Lanzillotta M (2020a) "Artificial intelligence for clinical gait diagnostics of knee osteoarthritis: an evidence-based review and analysis." TechrXiv

  36. Parisi L, RaviChandran N, Manaog ML (2020b) A novel hybrid algorithm for aiding prediction of prognosis in patients with hepatitis. Neural Comput & Applic 32(8):3839–3852

    Article  Google Scholar 

  37. Parisi L, RaviChandran N, Lanzillotta M (2020e) "Supervised machine learning for aiding diagnosis of knee osteoarthritis: a systematic review and Meta-analysis." TechrXiv

  38. Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2(4):303–314

    Article  MathSciNet  Google Scholar 

  39. Parisi L (2014a) Exploiting kinetic and kinematic data to plot cyclograms for managing the rehabilitation process of BKAs by applying neural networks. Int J Biomed Biol Eng 8(10):664–668

    Google Scholar 

  40. Parisi L (2014b) Neural networks for distinguishing the performance of two hip joint implants on the basis of hip implant side and ground reaction force. Int J Medical Heal Pharm Biomed Eng 8(10):659–663

    Google Scholar 

  41. Parisi L (2015) “A novel validation of the Cardiff classifier as decision-making support tool for diagnosing knee osteoarthritis and monitoring the extent of Total knee replacement surgery outcomes”. Cardiff University, UK, [BEng Hons thesis]

  42. Parisi L, Biggs PR, Whatling GM, C Avril Holt. (2015) "A novel comparison of artificial intelligence methods for diagnosing knee osteoarthritis." In: XXV Congress of the International Society of Biomechanics, pp. 1227–1229

  43. Parisi L, Manaog ML (2017a) "The importance of selecting appropriate k-fold cross-validation and training algorithms in improving postoperative discharge decision-making via artificial intelligence." In: 2017 AUT Mathematical Sciences Symposium, vol. 1, no. 1, p. 16

  44. Parisi L, Manaog ML (2017b) "A minimum viable machine learning-based speech processing solution for facilitating early diagnosis of Parkinson’s disease." In: MATLAB Conference

  45. Friedl MA, Brodley CE (1997) Decision tree classification of land cover from remotely sensed data. Remote Sens Environ 61(3):399–409

    Article  Google Scholar 

  46. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

    MATH  Google Scholar 

  47. Parisi L, Manaog ML (2016) "Preliminary validation of the Lagrangian support vector machine learning classifier as clinical decision-making support tool to aid prediction of prognosis in patients with hepatitis." In: The 16th International Conference on Biomedical Engineering, National University of Singapore (NUS)

  48. Prasad AM, Iverson LR, Liaw A (2006) Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 9(2):181–199

    Article  Google Scholar 

  49. Ng AY, Jordan MI (2002) "On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes." In: Advances in Neural Information Processing Systems, pp. 841–848

  50. Seada H, Deb K (2015) "U-NSGA-III: a unified evolutionary optimization procedure for single, multiple, and many objectives: proof-of-principle results." In: International Conference on Evolutionary Multi-criterion Optimization, pp. 34–49. Springer: Cham

  51. Barton G, Lisboa P, Lees A, Attfield S (2007) Gait quality assessment using self-organising artificial neural networks. Gait Posture 25(3):374–379

    Article  Google Scholar 

  52. Grunkemeier GL, Jin R (2001) Receiver operating characteristic curve analysis of clinical risk models. Ann Thorac Surg 72(2):323–326

    Article  Google Scholar 

Download references

Acknowledgments

The authors would like to thank the University of Auckland Rehabilitate Technologies Association (UARTA) and the University of Bradford for the opportunity to develop this collaborative work. No ethical approval was needed to perform this research, since the data leveraged in it are publicly available, as referenced in the text. Furthermore, there are no competing interests to declare, and this research was not supported by any funding.

Funding

This study was not supported by any funding.

Author information

Authors and Affiliations

  1. Department of Counselling Psychology, Institute of Systemic Psychotherapy “Centro Studi Eteropoiesi”, Corso Francia 98, 10143, Turin, Italy

    Matteo Lanzillotta

  2. University of Auckland Rehabilitative Technologies Association (UARTA), University of Auckland, 11 Symonds Street, Auckland, 1010, New Zealand

    Matteo Lanzillotta, Renfei Ma, Narrendar RaviChandran & Luca Parisi

  3. Warshel Institute for Computational Biology, The Chinese University of Hong Kong (CUHK-SZ), Shenzhen, China

    Renfei Ma

  4. Department of Psychomotricity and Pedagogy, Brignone Clinic, Via Rita Levi Montalcini, 3, 10098, Rivoli, Turin, Italy

    Marcella Accardi

  5. Department of Biomedical and Electronics Engineering, Faculty of Engineering and Informatics, University of Bradford, Bradford, BD7 1DP, UK

    Amir Zaernia & Mansour Youseffi

  6. Faculty of Business and Law (Artificial Intelligence Specialism), Coventry University, Priory St, Coventry, CV1 5FB, UK

    Luca Parisi

  7. Parkinson’s UK, 215 Vauxhall Bridge Rd, Pimlico, London, SW1V 1EJ, UK

    Luca Parisi

Authors
  1. Matteo Lanzillotta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Renfei Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Marcella Accardi
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Narrendar RaviChandran
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Amir Zaernia
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Mansour Youseffi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Luca Parisi
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors took part in the design of this study, in performing and validating the experiments reported in this manuscript, as well as in interpreting the results obtained from them. Moreover, all authors contributed to write this manuscript and approved it for submission to the Journal of Applied Intelligence.

Corresponding author

Correspondence to Luca Parisi.

Ethics declarations

Conflict of interest

None.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lanzillotta, M., Ma, R., Accardi, M. et al. Neuroevolutionary intelligent system to aid diagnosis of motor impairments in children. Appl Intell 52, 10757–10767 (2022). https://doi.org/10.1007/s10489-021-03126-3

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10489-021-03126-3

Keywords

Search

Navigation