Search

Goal: The evaluation of respiratory events using audio sensing in an at-home setting can be indicative of worsening health conditions. This paper investigates the use of image-based transfer learning applied to five audio visualizations to evaluate three classification tasks (C1: wet vs. dry vs. whooping cough vs. restricted breathing; C2: wet vs. dry cough; C3: cough vs. restricted breathing). Methods: The five visualizations (linear spectrogram, logarithmic spectrogram, Mel-spectrogram, wavelet scalograms, and aggregate images) are applied to a pre-trained AlexNet image classifier for all tasks. Results: The aggregate image-based classifier achieved the highest overall performance across all tasks with C1, C2, and C3 having testing accuracies of 0.88, 0.88, and 0.91 respectively. However, the Mel-spectrogram method had the highest testing accuracy (0.94) for C2. Conclusions: The classification of respiratory events using aggregate image inputs to transfer learning approaches may help healthcare professionals by providing information that would otherwise be unavailable to them.

Polysomnography (PSG) is the standard test for diagnosing sleep apnea. However, the approach is obtrusive, time-consuming, and with limited access for patients in need of sleep apnea diagnosis. In recent years, there have been many attempts to search for an alternative device or approach that avoids the limitations of PSG. Pressure-sensitive mats (PSM) have proven to be able to detect central sleep apneas (CSA) and be a potential alternative for PSG. In the current study, we combine advanced machine learning approaches with a practical unobtrusive home monitoring device (PSM) to detect CSA events from data collected nocturnally and unattended. Two deep learning methods are implemented for the automatic detection of CSA events: a temporal convolutional network (TCN) and a bidirectional long short-term memory (BiLSTM) network. The deep learning models are compared to a classical machine learning approach (linear support vector machine, SVM) and a simple threshold-based algorithm. Considering the characteristics of each method, we choose strategies, including resampling and weighted cost-functions, to optimize the methods and to perform CSA detection as anomaly detection in an imbalanced data set. We evaluate the performance of all models on a database containing 7 days of data from 9 elderly patients. From the resulting 63 days, data from 7 patients (49 days) are devoted to training for optimizing hyperparameters, and data from 2 patients (14 days) are devoted to testing. Experimental results indicate that the best-performing model achieves an accuracy of 95.1% through training an BiLSTM network. Overall, the implemented deep learning methods achieve better performance than the conventional classification approach (SVM) and the simple threshold-based method, and show good potential for the use of PSM for practical unobtrusive monitoring of CSA.

The current pandemic associated with the novel coronavirus (COVID-19) presents a new area of research with its own set of challenges. Creating unobtrusive remote monitoring tools for medical professionals that may aid in diagnosis, monitoring and contact tracing could lead to more efficient and accurate treatments, especially in this time of physical distancing. Audio based sensing methods can address this by measuring the frequency, severity and characteristics of the COVID-19 cough. However, the feasibility of accumulating coughs directly from patients is low in the short term. This article introduces a novel database (NoCoCoDa), which contains COVID-19 cough events obtained through public media interviews with COVID-19 patients, as an interim solution. After manual segmentation of the interviews, a total of 73 individual cough events were extracted and cough phase annotation was performed. Furthermore, the COVID-19 cough is typically dry but can present as a more productive cough in severe cases. Therefore, an investigation of cough sub-type (productive vs. dry) of the NoCoCoDa was performed using methods previously published by our research group. Most of the NoCoCoDa cough events were recorded either during or after a severe period of the disease, which is supported by the fact that 77% of the COVID-19 coughs were classified as productive based on our previous work. The NoCoCoDa is designed to be used for rapid exploration and algorithm development, which can then be applied to more extensive datasets and potentially real time applications. The NoCoCoDa is available for free to the research community upon request.

Losing the capacity to drive due to age-related cognitive decline can have a detrimental impact on the daily life functioning of older adults living alone and in remote areas. Semi-autonomous vehicles (SAVs) could have the potential to preserve driving independence of this population with high health needs. This paper explores if SAVs could be used as a cognitive assistive device for older aging drivers with cognitive challenges. We illustrate the impact of age-related changes of cognitive functions on driving capacity. Furthermore, following an overview on the current state of SAVs, we propose a model for connecting cognitive health needs of older drivers to SAVs. The model demonstrates the connections between cognitive changes experienced by aging drivers, their impact on actual driving, car sensors’ features, and vehicle automation. Finally, we present challenges that should be considered when using the constantly changing smart vehicle technology, adapting it to aging drivers and vice versa. This paper sheds light on age-related cognitive characteristics that should be considered when developing future SAVs manufacturing policies which may potentially help decrease the impact of cognitive change on older adult drivers.

Driving is an activity that facilitates physical, cognitive, and social stimulation in older adults, ultimately leading to better physical and cognitive health. However, aging is associated with declines in vision, physical health, and cognitive health, all of which can affect driving ability. One way of assessing driving ability is with the use of sensors in the older adult’s own vehicle. This paper provides a framework for driving assessment and addresses how naturalistic driving studies can assist in such assessments. The framework includes driving characteristics (how much driving, speed, position, type of road), actions and reactions (lane changes, intersections, passing, merging, traffic lights, pedestrians, other vehicles), destinations (variety and distance, sequencing and route planning), and driving conditions (time of day and season). Data from a subset of Ottawa drivers from the Candrive study is used to illustrate the use of naturalistic driving data. Challenges in using naturalistic driving big data and the changing technology in vehicles are discussed.