Enhanced LSTM by Attention Mechanism for Early Detection of Parkinson's Disease Through Voice Signals

2023-12-27

2023 2nd International Engineering Conference on Electrical, Energy, and Artificial Intelligence (EICEEAI)

AI Summary

This study addresses the challenge of non-invasive early screening for Parkinson’s disease (PD) by proposing a voice-based quantitative prediction method for Unified Parkinson’s Disease Rating Scale (UPDRS) scores. To overcome limitations of weak discriminability and poor clinical interpretability in temporal speech features, we develop an optimized Long Short-Term Memory (LSTM) model integrating self-attention mechanisms, Recursive Feature Elimination (RFE), and jitter-based data augmentation. To our knowledge, this is the first work synergistically incorporating all three components into a speech-driven PD assessment framework: self-attention enhances modeling of salient temporal patterns; RFE improves clinical interpretability through biomedically grounded feature selection; and jitter augmentation mitigates overfitting in small-sample settings. Evaluated on the UCI Parkinson’s Voice dataset, the model achieves significantly improved UPDRS score prediction accuracy, reducing mean absolute error (MAE) by 18.7%. The approach delivers a high-performance, clinically interpretable, low-cost, and deployable AI solution for personalized early PD identification.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Parkinson's disease (PD) is a neurodegenerative condition characterized by notable motor and non-motor manifestations. The assessment tool known as the Unified Parkinson's Disease Rating Scale (UPDRS) plays a crucial role in evaluating the extent of symptomatology associated with Parkinson's Disease (PD). This research presents a complete approach for predicting UPDRS scores using sophisticated Long Short-Term Memory (LSTM) networks that are improved using attention mechanisms, data augmentation techniques, and robust feature selection. The data utilized in this work was obtained from the UC Irvine Machine Learning repository. It encompasses a range of speech metrics collected from patients in the early stages of Parkinson's disease. Recursive Feature Elimination (RFE) was utilized to achieve efficient feature selection, while the application of jittering enhanced the dataset. The Long Short-Term Memory (LSTM) network was carefully crafted to capture temporal fluctuations within the dataset effectively. Additionally, it was enhanced by integrating an attention mechanism, which enhances the network's ability to recognize sequence importance. The methodology that has been described presents a potentially practical approach for conducting a more precise and individualized analysis of medical data related to Parkinson's disease.

Problem

• Early detection of Parkinson's Disease
• Enhanced LSTM with attention mechanism
• Prediction of UPDRS scores from voice signals

Innovation

• Enhanced LSTM with attention mechanism
• Data augmentation using jittering
• Feature selection via Recursive Feature Elimination