The proposed time-frequency time-space LSTM algorithm achieved 93.77% accuracy for ECG atrial fibrillation classification and 100% accuracy for Parkinson's disease gait classification, outperforming conventional LSTM.
The proposed time-frequency time-space LSTM architecture significantly improves classification accuracy and drastically reduces training time for physiological signals like ECG and gait dynamics.
Absolute Event Rate: 93.77% vs 58.37%
Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time-frequency and time-space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.
Tuan D. Pham (Thu,) conducted a other in Atrial Fibrillation and Parkinson's Disease. Time-frequency time-space LSTM (TF-TS LSTM) vs. Conventional LSTM was evaluated on Classification accuracy for ECG atrial fibrillation and normal sinus rhythm. The proposed time-frequency time-space LSTM algorithm achieved 93.77% accuracy for ECG atrial fibrillation classification and 100% accuracy for Parkinson's disease gait classification, outperforming conventional LSTM.