Multi Class Parkinsons Disease Detection Based on Finger Tapping Using Attention-Enhanced CNN BiLSTM

2025-10-11

AI Summary

To address the challenge of non-invasive, accurate staging of Parkinson’s disease (PD) severity, this paper proposes an end-to-end multi-level classification method based on finger-tapping videos. We extract time-frequency-amplitude multimodal motion features and design a hybrid deep learning model integrating Conv1D, bidirectional LSTM (BiLSTM), and a dual-channel–temporal attention mechanism to jointly model spatiotemporal dependencies and enhance discriminative representation of critical temporal segments. Evaluated on the five-class Hoehn–Yahr staging task, our model significantly outperforms existing gesture-based PD assessment methods. To the best of our knowledge, this is the first work to apply a dual-attention–guided CNN-BiLSTM architecture for fine-grained PD severity grading. We empirically demonstrate that synergistic spatiotemporal feature modeling and attention-driven focus on clinically salient frames substantially improve both classification accuracy and clinical interpretability. This study establishes a novel paradigm for remote, unobtrusive monitoring of PD progression.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Effective clinical management and intervention development depend on accurate evaluation of Parkinsons disease (PD) severity. Many researchers have worked on developing gesture-based PD recognition systems; however, their performance accuracy is not satisfactory. In this study, we propose a multi-class Parkinson Disease detection system based on finger tapping using an attention-enhanced CNN BiLSTM. We collected finger tapping videos and derived temporal, frequency, and amplitude based features from wrist and hand movements. Then, we proposed a hybrid deep learning framework integrating CNN, BiLSTM, and attention mechanisms for multi-class PD severity classification from video-derived motion features. First, the input sequence is reshaped and passed through a Conv1D MaxPooling block to capture local spatial dependencies. The resulting feature maps are fed into a BiLSTM layer to model temporal dynamics. An attention mechanism focuses on the most informative temporal features, producing a context vector that is further processed by a second BiLSTM layer. CNN-derived features and attention-enhanced BiLSTM outputs are concatenated, followed by dense and dropout layers, before the final softmax classifier outputs the predicted PD severity level. The model demonstrated strong performance in distinguishing between the five severity classes, suggesting that integrating spatial temporal representations with attention mechanisms can improve automated PD severity detection, making it a promising non-invasive tool to support clinicians in PD monitoring and progression tracking.

Problem

• Developing accurate multi-class Parkinson's disease severity detection system
• Classifying PD severity using finger tapping videos with deep learning
• Improving automated PD assessment through spatial-temporal feature integration

Innovation

• Attention-enhanced CNN BiLSTM for PD detection
• Hybrid deep learning with spatial-temporal feature extraction
• Video-derived motion features with multi-class classification