Clinical human activity recognition based on a wearable patch of combined tri-axial ACC and ECG sensors

Background

In digital medicine, human activity recognition (HAR) can be used to track and assess a patient's progress throughout rehabilitation, enhancing the quality of life for the elderly and the disabled.

Methods

A patch-type flexible sensor that integrated dynamic electrocardiogram (ECG) and acceleration signal (ACC) was used to record the signals of the various behavioral activities of 20 healthy volunteers and 25 patients with pneumoconiosis. Seven HAR tasks were then carried out on the data using four different deep learning methods (CNN, LSTM, CNN-LSTM and GRU).

Results

When ECG and ACC were obtained simultaneously, the overall accuracy rates of HAR for healthy group were 0.9371, 0.8829, 0.9843 and 0.9486 by the CNN, LSTM, CNN-LSTM and GRU models, respectively. In contrast, the overall accuracy rates of HAR for the pneumoconiosis patients' group were 0.8850, 0.7975, 0.9425 and 0.8525 by the four corresponding models. The accuracy of HAR for both groups using all four models is higher than when only ACC signal is detected.

Conclusion

The addition of the ECG signal significantly improves HAR outcomes in the group of healthy individuals, while having relatively less enhancing effects on the group of patients with pneumoconiosis. When ECG and ACC signals were combined, the increase in HAR accuracy was notable compared to cases where no ECG data was provided. These results suggest that the combination of ACC and ECG data can represent a novel method for the clinical application of HAR.

Correlation of balance posturographic parameters during quiet standing with the berg balance scale in patients with parkinson's disease

BACKGROUND

Parkinson's disease (PD) is often clinically associated with posture instability and more easily falling. The Berg balance scale is a clinical indicator commonly used to subjectively evaluate a patient's balance ability. Meanwhile, computerized force platforms have been used in research on postural control. The various parameters obtained from posturography are interpreted to assess balance ability. The present study aims to explore the correlations between posturographic variables and the BBS, and furthermore to efficiently evaluate postural instability and fall risk of early and moderate PD patients.

METHODS

A total of 46 PD patients were involved in the experiment. Patients were asked to perform BBS tests and force platform tests under eye open (EO) and eye closed (EC) conditions. The recorded COP signal was analyzed with the time domain statistical method, the frequency domain method of Power Spectral Density (PSD), and structural methods of Stabilogram Diffusion Analysis (SDA), Sway Density Plot (SDP) to retrieve different posturographic variables. The correlation between posturographic variables under EO and EC conditions with BBS was compared statistically. The significantly correlated posturographic parameters were then applied to analyze posturographic differences between different groups: faller vs. non-faller (patients with/without a history of falls in the past 12 months).

RESULTS

Among the different posturographic parameters, the prediction ellipse area, the slope of the regression line at a high-frequency band of PSD in the medial-lateral (ML) direction, the crossover point of the regression lines of SDA in the anterior-posterior (AP) direction, and the distance between successive peaks of SDP had significant correlations with BBS. These selected BBS-related parameters also showed significant differences between faller and non-faller. The selected posturographic parameters can be used as effective indicators to evaluate the balance ability of Parkinson's disease patients.