1
|
Lan Z, Lempereur M, Gueret G, Houx L, Cacioppo M, Pons C, Mensah J, Rémy-Néris O, Aïssa-El-Bey A, Rousseau F, Brochard S. Towards a diagnostic tool for neurological gait disorders in childhood combining 3D gait kinematics and deep learning. Comput Biol Med 2024; 171:108095. [PMID: 38350399 DOI: 10.1016/j.compbiomed.2024.108095] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Revised: 01/31/2024] [Accepted: 02/01/2024] [Indexed: 02/15/2024]
Abstract
Gait abnormalities are frequent in children and can be caused by different pathologies, such as cerebral palsy, neuromuscular disease, toe walker syndrome, etc. Analysis of the "gait pattern" (i.e., the way the person walks) using 3D analysis provides highly relevant clinical information. This information is used to guide therapeutic choices; however, it is underused in diagnostic processes, probably because of the lack of standardization of data collection methods. Therefore, 3D gait analysis is currently used as an assessment rather than a diagnostic tool. In this work, we aimed to determine if deep learning could be combined with 3D gait analysis data to diagnose gait disorders in children. We tested the diagnostic accuracy of deep learning methods combined with 3D gait analysis data from 371 children (148 with unilateral cerebral palsy, 60 with neuromuscular disease, 19 toe walkers, 60 with bilateral cerebral palsy, 25 stroke, and 59 typically developing children), with a total of 6400 gait cycles. We evaluated the accuracy, sensitivity, specificity, F1 score, Area Under the Curve (AUC) score, and confusion matrix of the predictions by ResNet, LSTM, and InceptionTime deep learning architectures for time series data. The deep learning-based models had good to excellent diagnostic accuracy (ranging from 0.77 to 0.99) for discrimination between healthy and pathological gait, discrimination between different etiologies of pathological gait (binary and multi-classification); and determining stroke onset time. LSTM performed best overall. This study revealed that the gait pattern contains specific, pathology-related information. These results open the way for an extension of 3D gait analysis from evaluation to diagnosis. Furthermore, the method we propose is a data-driven diagnostic model that can be trained and used without human intervention or expert knowledge. Furthermore, the method could be used to distinguish gait-related pathologies and their onset times beyond those studied in this research.
Collapse
Affiliation(s)
- Zhengyang Lan
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; IMT Atlantique, LaTIM U1101 INSERM, Brest, France
| | - Mathieu Lempereur
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France.
| | - Gwenael Gueret
- CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France
| | - Laetitia Houx
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France; Fondation Ildys, Brest, France
| | - Marine Cacioppo
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France
| | - Christelle Pons
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France; Fondation Ildys, Brest, France
| | - Johanne Mensah
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France; Fondation Ildys, Brest, France
| | - Olivier Rémy-Néris
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France
| | | | - François Rousseau
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; IMT Atlantique, LaTIM U1101 INSERM, Brest, France
| | - Sylvain Brochard
- Laboratoire de Traitement de l'Information Médicale INSERM U1101, Brest, France; Université de Bretagne Occidentale, Brest, France; CHU de Brest, Hôpital Morvan, service de médecine physique et de réadaptation, Brest, France; Fondation Ildys, Brest, France
| |
Collapse
|
2
|
de Jonge S, Potters WV, Verhamme C. Artificial intelligence for automatic classification of needle EMG signals: A scoping review. Clin Neurophysiol 2024; 159:41-55. [PMID: 38246117 DOI: 10.1016/j.clinph.2023.12.134] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2023] [Revised: 12/01/2023] [Accepted: 12/16/2023] [Indexed: 01/23/2024]
Abstract
OBJECTIVE This scoping review provides an overview of artificial intelligence (AI), including machine and deep learning techniques, in the interpretation of clinical needle electromyography (nEMG) signals. METHODS A comprehensive search of Medline, Embase and Web of Science was conducted to find peer-reviewed journal articles. All papers published after 2010 were included. The methodological quality of the included studies was assessed with CLAIM (checklist for artificial intelligence in medical imaging). RESULTS 51 studies were identified that fulfilled the inclusion criteria. 61% used open-source EMGlab data set to develop models to classify nEMG signal in healthy, amyotrophic lateral sclerosis (ALS) and myopathy (25 subjects). Only two articles developed models to classify signals recorded at rest. Most articles reported high performance accuracies, but many were subject to bias and overtraining. CONCLUSIONS Current AI-models of nEMG signals are not sufficient for clinical implementation. Suggestions for future research include emphasizing the need for an optimal training and validation approach using large datasets of clinical nEMG data from a diverse patient population. SIGNIFICANCE The outcomes of this study and the suggestions made aim to contribute to developing AI-models that can effectively handle signal quality variability and are suitable for daily clinical practice in interpreting nEMG signals.
Collapse
Affiliation(s)
- S de Jonge
- Department of Neurology and Clinical Neurophysiology, Amsterdam Neuroscience, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands
| | - W V Potters
- Department of Neurology and Clinical Neurophysiology, Amsterdam Neuroscience, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands; TrianecT, Padualaan 8, Utrecht, The Netherlands
| | - C Verhamme
- Department of Neurology and Clinical Neurophysiology, Amsterdam Neuroscience, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, Amsterdam, The Netherlands.
| |
Collapse
|
3
|
Gomez-Correa M, Ballesteros M, Salgado I, Cruz-Ortiz D. Forearm sEMG data from young healthy humans during the execution of hand movements. Sci Data 2023; 10:310. [PMID: 37210582 DOI: 10.1038/s41597-023-02223-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2022] [Accepted: 05/10/2023] [Indexed: 05/22/2023] Open
Abstract
This work provides a complete dataset containing surface electromyography (sEMG) signals acquired from the forearm with a sampling frequency of 1000 Hz. The dataset is named WyoFlex sEMG Hand Gesture and recorded the data of 28 participants between 18 and 37 years old without neuromuscular diseases or cardiovascular problems. The test protocol consisted of sEMG signals acquisition corresponding to ten wrist and grasping movements (extension, flexion, ulnar deviation, radial deviation, hook grip, power grip, spherical grip, precision grip, lateral grip, and pinch grip), considering three repetitions for each gesture. Also, the dataset contains general information such as anthropometric measures of the upper limb, gender, age, laterally of the person, and physical condition. Likewise, the implemented acquisition system consists of a portable armband with four sEMG channels distributed equidistantly for each forearm. The database could be used for the recognition of hand gestures, evaluation of the evolution of patients in rehabilitation processes, control of upper limb orthoses or prostheses, and biomechanical analysis of the forearm.
Collapse
Affiliation(s)
- Manuela Gomez-Correa
- Centro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Z.C, 07700, Mexico City, Mexico
| | - Mariana Ballesteros
- Centro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Z.C, 07700, Mexico City, Mexico
- Medical Robotics and Biosignals Laboratory, Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Z.C, 07340, Mexico City, Mexico
| | - Ivan Salgado
- Centro de Innovación y Desarrollo Tecnológico en Cómputo, Instituto Politécnico Nacional, Z.C, 07700, Mexico City, Mexico
| | - David Cruz-Ortiz
- Medical Robotics and Biosignals Laboratory, Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Z.C, 07340, Mexico City, Mexico.
| |
Collapse
|
6
|
Gomez-Correa M, Cruz-Ortiz D. Low-Cost Wearable Band Sensors of Surface Electromyography for Detecting Hand Movements. SENSORS (BASEL, SWITZERLAND) 2022; 22:s22165931. [PMID: 36015692 PMCID: PMC9416605 DOI: 10.3390/s22165931] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/28/2022] [Revised: 07/29/2022] [Accepted: 08/03/2022] [Indexed: 05/30/2023]
Abstract
Surface electromyography (sEMG) is a non-invasive measure of electrical activity generated due to muscle contraction. In recent years, sEMG signals have been increasingly used in diverse applications such as rehabilitation, pattern recognition, and control of orthotic and prosthetic systems. This study presents the development of a versatile multi-channel sEMG low-cost wearable band system to acquire 4 signals. In this case, the signals acquired with the proposed device have been used to detect hand movements. However, the WyoFlex band could be used in some sections of the arm or the leg if the section's diameter matches the diameter of the WyoFlex band. The designed WyoFlex band was fabricated using three-dimensional (3D) printing techniques employing thermoplastic polyurethane and polylactic acid as manufacturing materials. Then, the proposed wearable electromyographic system (WES) consists of 2 WyoFlex bands, which simultaneously allow the wireless acquisition of 4 sEMG channels of each forearm. The collected sEMG can be visualized and stored for future post-processing stages using a graphical user interface designed in Node-RED. Several experimental tests were conducted to verify the performance of the WES. A dataset with sEMG collected from 15 healthy humans has been obtained as part of the presented results. In addition, a classification algorithm based on artificial neural networks has been implemented to validate the usability of the collected sEMG signals.
Collapse
Affiliation(s)
- Manuela Gomez-Correa
- Medical Robotics and Biosignal Processing Laboratory, Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Mexico City 07340, Mexico
- Facultad de Ingeniería, Universidad de Antioquia, Medellin 050010, Colombia
| | - David Cruz-Ortiz
- Medical Robotics and Biosignal Processing Laboratory, Unidad Profesional Interdisciplinaria de Biotecnología, Instituto Politécnico Nacional, Mexico City 07340, Mexico
| |
Collapse
|