ABSTRACT
A progressive neurodegenerative disease affecting motor neurons, Amyotrophic Lateral Sclerosis (ALS) requires early diagnosis as quickly as possible. For such situations, surface electromyography (S-EMG) is widely used as a non-invasive diagnostic tool to measure muscles' activity through electrodes placed on the skin's surface. Artificial intelligence (AI) approaches can be employed to analyze captured signals and distinguish abnormal patterns. However, previous work focused primarily on spatial information. It does not consider temporal information, effectively capturing the dynamic nature of muscle activity and identifying subtle abnormalities that might indicate ALS. Therefore, we fill the gap in this study by proposing a combination of CNN, Long-Short-Term Memory Networks (LSTM), and attention mechanisms to exploit temporal information in EMG signals. Stability assessment using K-fold cross-validation ensures reliable model performance. Our results demonstrate that combining spatial and temporal information can enhance performance and acquire 98.15% and 98.45% for CNN and LSTM, and CNN, LSTM, and Attention combination. In addition, our proposed model remains stable compared to previous work.
- Elisa Longinetti and Fang Fang. 2019. Epidemiology of amyotrophic lateral sclerosis: an update of recent literature. Current Opinion in Neurology 32, 5: 771–776. https://doi.org/10.1097/WCO.0000000000000730Google ScholarCross Ref
- Ijeoma Nnake, Orien L. Tulp, and George P. Einstein. 2022. Integrative therapies for amyotrophic lateral sclerosis disease using dynamic physiological systems. The FASEB Journal 36, S1. https://doi.org/10.1096/fasebj.2022.36.S1.R2497Google ScholarCross Ref
- Michael Swash. 1998. Early diagnosis of ALS/MND. Journal of the Neurological Sciences 160: S33–S36. https://doi.org/10.1016/S0022-510X(98)00215-9Google ScholarCross Ref
- Xu Zhang, Paul E. Barkhaus, William Zev Rymer, and Ping Zhou. 2014. Machine Learning for Supporting Diagnosis of Amyotrophic Lateral Sclerosis Using Surface Electromyogram. IEEE Transactions on Neural Systems and Rehabilitation Engineering 22, 1: 96–103. https://doi.org/10.1109/TNSRE.2013.2274658Google ScholarCross Ref
- Gregg D. Meekins, Yuen So, and Dianna Quan. 2008. American Association of Neuromuscular & Electrodiagnostic Medicine evidenced-based review: Use of surface electromyography in the diagnosis and study of neuromuscular disorders. Muscle & Nerve 38, 4: 1219–1224. https://doi.org/10.1002/mus.21055Google ScholarCross Ref
- Abul Barkat Mollah Sayeed Ud Doulah and Shaikh Anowarul Fattah. 2014. Neuromuscular disease classification based on mel frequency cepstrum of motor unit action potential. In 2014 International Conference on Electrical Engineering and Information & Communication Technology, 1–4. https://doi.org/10.1109/ICEEICT.2014.6919167Google ScholarCross Ref
- Felipe Fernandes, Ingridy Barbalho, Daniele Barros, Ricardo Valentim, César Teixeira, Jorge Henriques, Paulo Gil, and Mário Dourado Júnior. 2021. Biomedical signals and machine learning in amyotrophic lateral sclerosis: a systematic review. BioMedical Engineering OnLine 20, 1: 61. https://doi.org/10.1186/s12938-021-00896-2Google ScholarCross Ref
- Abdulhamit Subasi, Emine Yaman, Yara Somaily, Halah A. Alynabawi, Fatemah Alobaidi, and Sumaiah Altheibani. 2018. Automated EMG Signal Classification for Diagnosis of Neuromuscular Disorders Using DWT and Bagging. Procedia Computer Science 140: 230–237. https://doi.org/10.1016/j.procs.2018.10.333Google ScholarCross Ref
- Vipin K. Mishra, Varun Bajaj, Anil Kumar, and Girish Kumar Singh. 2016. Analysis of ALS and normal EMG signals based on empirical mode decomposition. IET Science, Measurement & Technology 10, 8: 963–971. https://doi.org/10.1049/iet-smt.2016.0208Google ScholarCross Ref
- Abdulkadir Sengur, Mehmet Gedikpinar, Yaman Akbulut, Erkan Deniz, Varun Bajaj, and Yanhui Guo. 2018. DeepEMGNet: An Application for Efficient Discrimination of ALS and Normal EMG Signals. . 619–625. https://doi.org/10.1007/978-3-319-65960-2_77Google ScholarCross Ref
- Abdulkadir Sengur, Yaman Akbulut, Yanhui Guo, and Varun Bajaj. 2017. Classification of amyotrophic lateral sclerosis disease based on convolutional neural network and reinforcement sample learning algorithm. Health Information Science and Systems 5, 1: 9. https://doi.org/10.1007/s13755-017-0029-6Google ScholarCross Ref
- K. M. Naimul Hassan, Md. Shamiul Alam Hridoy, Naima Tasnim, Atia Faria Chowdhury, Tanvir Alam Roni, Sheikh Tabrez, Arik Subhana, and Celia Shahnaz. 2022. ALSNet: A Dilated 1-D CNN for Identifying ALS from Raw EMG Signal. In ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1181–1185. https://doi.org/10.1109/ICASSP43922.2022.9747366Google ScholarCross Ref
- Margarida Antunes, Duarte Folgado, Marília Barandas, André Carreiro, Carla Quintão, Mamede de Carvalho, and Hugo Gamboa. 2023. A morphology-based feature set for automated Amyotrophic Lateral Sclerosis diagnosis on surface electromyography. Biomedical Signal Processing and Control 79: 104011. https://doi.org/10.1016/j.bspc.2022.104011Google ScholarCross Ref
- Carla Quintão, Ricardo Vigário, Maria Marta Santos, Ana Luísa Gomes, Mamede de Carvalho, Susana Pinto, and Hugo Gamboa. 2021. Surface electromyography for testing motor dysfunction in amyotrophic lateral sclerosis. Neurophysiologie Clinique 51, 5: 454–465. https://doi.org/10.1016/j.neucli.2021.06.001Google ScholarCross Ref
- Miki Nikolic. 2001. Detailed Analysis of Clinical Electromyography Signals EMG Decomposition, Findings and Firing Pattern Analysis in Controls and Patients with Myopathy and Amytrophic Lateral Sclerosis. University of Copenhagen. Retrieved June 1, 2023 from https://www.emglab.net/Google Scholar
- Cries Avian, Setya Widyawan Prakosa, Muhamad Faisal, and Jenq Shiou Leu. 2022. Estimating finger joint angles on surface EMG using Manifold Learning and Long Short-Term Memory with Attention mechanism. Biomedical Signal Processing and Control 71, PA: 103099. https://doi.org/10.1016/j.bspc.2021.103099Google ScholarCross Ref
- Abul Barkat Mollah Sayeed Ud Doulah, Shaikh Anowarul Fattah, Wei‐Ping Zhu, and M. Omair Ahmad. 2014. DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification. Healthcare Technology Letters 1, 1: 26–31. https://doi.org/10.1049/htl.2013.0036Google ScholarCross Ref
- Anju Krishna and Paul Thomas. 2015. Classification of EMG Signals Using Spectral Features Extracted from Dominant Motor Unit Action Potential. International Journal of Engineering and Advanced Technology (IJEAT), 5: 2249–8958. Retrieved from www.ijeat.orgGoogle Scholar
Index Terms
- Revisiting the K-Fold Approach for a Stable Model on Amyotrophic Lateral Sclerosis Prediction Scheme using LSTM and Attention Mechanism
Recommendations
An efficient hybrid approach for the prediction of epilepsy using CNN with LSTM
Epileptic seizures are a severe neurological disorder with significant implications for public health. Epileptic seizure is one of the neurological disorders which affect either children in the age group of 10-20 years old or adults in the age group of 65-...
Amyotrophic Lateral Sclerosis Patients Regain Head-Neck Control Using a Powered Neck Exoskeleton
2022 9th IEEE RAS/EMBS International Conference for Biomedical Robotics and Biomechatronics (BioRob)A cross-sectional human study was conducted to validate a powered neck exoskeleton to assist with head-neck motions in five head drop patients. Head drop, a condition caused by neck muscle weakness, is commonly seen in patients with neurological disorder, ...
Automatic prediction of epileptic seizure using hybrid deep ResNet-LSTM model
Numerous advanced data processing and machine learning techniques for identifying epileptic seizures have been developed in the last two decades. Nonetheless, many of these solutions need massive data sets and intricate computations. Our approach ...
Comments