Pressure sensor-based tongue-placed electrotactile biofeedback for balance improvement--biomedical application to prevent pressure sores formation and falls

Depression assessment using integrated multi-featured EEG bands deep neural network models: Leveraging ensemble learning techniques

Mental Status Assessment (MSA) holds significant importance in psychiatry. In recent years, several studies have leveraged Electroencephalogram (EEG) technology to gauge an individual's mental state or level of depression. This study introduces a novel multi-tier ensemble learning approach to integrate multiple EEG bands for conducting mental state or depression assessments. Initially, the EEG signal is divided into eight sub-bands, and then a Long Short-Term Memory (LSTM)-based Deep Neural Network (DNN) model is trained for each band. Subsequently, the integration of multi-band EEG frequency models and the evaluation of mental state or depression level are facilitated through a two-tier ensemble learning approach based on Multiple Linear Regression (MLR). The authors conducted numerous experiments to validate the performance of the proposed method under different evaluation metrics. For clarity and conciseness, the research employs the simplest commercialized one-channel EEG sensor, positioned at FP1, to collect data from 57 subjects (49 depressed and 18 healthy subjects). The obtained results, including an accuracy of 0.897, F1-score of 0.921, precision of 0.935, negative predictive value of 0.829, recall of 0.908, specificity of 0.875, and AUC of 0.8917, provide evidence of the superior performance of the proposed method compared to other ensemble learning techniques. This method not only proves effective but also holds the potential to significantly enhance the accuracy of depression assessment.

Review of assistive devices for the prevention of pressure ulcers: an engineering perspective

PURPOSE

Pressure ulcers (PUs) are prevalent among immobile bed or wheelchair-reliant individuals who experience prolonged sedentary positions. Pressure relief and frequent repositioning of body posture help to mitigate complications associated with PUs. Adherence with regular repositioning is difficult to maintain due to nursing labour shortages or constraints of in-home caregivers. Manual repositioning, transferring, and lifting of immobile patients are physically demanding tasks for caregivers. This review aimed to explore and categorize these devices, discuss the significant technical challenges that need addressing, and identify potential design opportunities.

MATERIALS AND METHODS

In this review, a literature search was conducted using PubMED, Science Direct, Google Scholar and IEEE Xplore databases including studies from 1995 until Feb 2023 with keywords such as pressure ulcer, assistive device, pressure relief, repositioning, transfer, etc. Both commercial and research-level devices were included in the search.

RESULTS

142 devices or technologies were identified and classified into four main categories that were further subcategorized. Within each category, the devices were investigated in terms of their mechanical design, actuation methods, control strategies, sensing technologies, and level of autonomy. Limitations of current technologies are design complexity, lack of patient comfort, and a lack of autonomy requiring caregivers frequent intervention.

CONCLUSIONS

Several devices have been developed to help with prevention and mitigation of PUs. There remain challenges that hinder the widespread accessibility and use of current technologies. Advancements in assistive technologies for pressure ulcer mitigation could lie at the intersection of robotics, sensors, perception, user-centered design, and autonomous systems.

Influence of sparkle and saccades on tongue electro-stimulation-based vision substitution of 2D vectors

Vision substitution by electro-stimulation has been studied since the 60s beginning with P. Bach-y-Rita. Camera pictures or movies encoded in gray levels are displayed using an electro-stimulation display device on the surface of a body part, such as the skin or the tongue. Medical-technical devices have been developed on this principle to compensate for sensory-motor disabilities such as blindness or loss of balance, or to guide specific actions, such as surgery. However, the electrical signals of stationary or moving slowly moving objects, displayed on a Tongue display unit (TDU), are quickly lost due to saturation of receptors undergoing electrostimulation. We propose to add random saccades or sparkle to the displayed visual scene to increase the quality of pattern recognition by the subjects. In the present experimental trimodal study (normal vision, TDU vision substitution, or both), we show that the presence of a moderate sparkle level enhances the perception of the direction of lines drawn on a TDU and reduces the response time.