Rehabilitation Assessment System for Stroke Patients Based on Fusion-Type Optoelectronic Plethysmography Device and Multi-Modality Fusion Model: Design and Validation

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 9; p. 2925
• Main Authors: Yan, Liangwen, Long, Ze, Qian, Jie, Lin, Jianhua, Xie, Sheng Quan, Sheng, Bo
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 01.05.2024
• Subjects: Accuracy; Adult; Algorithms; Blood; Computational linguistics; Data collection; Data entry; Design; Digital signal processors; Electrocardiography; Electromyography; Equipment Design; Female; Humans; Language processing; Male; MCNN-LSTM-Attention; Middle Aged; multi-modality fusion; Natural language interfaces; Neural networks; Neural Networks, Computer; Patients; photoplethysmography; Photoplethysmography - instrumentation; Photoplethysmography - methods; Physiology; Plethysmography - instrumentation; Plethysmography - methods; Rehabilitation; rehabilitation assessment; Sensors; Stroke; Stroke - physiopathology; Stroke patients; Stroke Rehabilitation - instrumentation; Stroke Rehabilitation - methods; Wearable Electronic Devices; China; multi-modality fusion; MCNN-LSTM-Attention; photoplethysmography; stroke; rehabilitation assessment
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s24092925

This study aimed to propose a portable and intelligent rehabilitation evaluation system for digital stroke-patient rehabilitation assessment. Specifically, the study designed and developed a fusion device capable of emitting red, green, and infrared lights simultaneously for photoplethysmography (PPG) acquisition. Leveraging the different penetration depths and tissue reflection characteristics of these light wavelengths, the device can provide richer and more comprehensive physiological information. Furthermore, a Multi-Channel Convolutional Neural Network–Long Short-Term Memory–Attention (MCNN-LSTM-Attention) evaluation model was developed. This model, constructed based on multiple convolutional channels, facilitates the feature extraction and fusion of collected multi-modality data. Additionally, it incorporated an attention mechanism module capable of dynamically adjusting the importance weights of input information, thereby enhancing the accuracy of rehabilitation assessment. To validate the effectiveness of the proposed system, sixteen volunteers were recruited for clinical data collection and validation, comprising eight stroke patients and eight healthy subjects. Experimental results demonstrated the system’s promising performance metrics (accuracy: 0.9125, precision: 0.8980, recall: 0.8970, F1 score: 0.8949, and loss function: 0.1261). This rehabilitation evaluation system holds the potential for stroke diagnosis and identification, laying a solid foundation for wearable-based stroke risk assessment and stroke rehabilitation assistance.