Evaluation of Respiratory Sounds Using Image-Based Approaches for Health Measurement Applications.

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.

Novel Coronavirus Cough Database: NoCoCoDa.

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.

Comparison of Silence Removal Methods for the Identification of Audio Cough Events.

Sensing technologies are embedded in our everyday lives. Smart homes typically use an Audio Virtual Assistant (AVA) (e.g. Alexa, Siri, and Google Home) interface that collects sensor information, which can provide security, assist in everyday activities and monitor health related information. One such measure is cough, changes of which can be a marker of worsening conditions for many respiratory diseases. Creating a reliable monitoring system utilizing technology that may already be present in the home (i.e. AVA) may provide an opportunity for early intervention and reductions in the number of long-term hospitalizations. This paper focuses on the optimization of the silence removal and segmentation step in an at home setting with low to moderate background noise to identify cough events. Three commonly used methods (Standard deviation (SD), Short-term Energy (SE), Zero-crossing rate (ZCR)) were compared to manual segmentations. Each method was applied to 209 audio files that were manually verified to contain at least one cough event and the average segmentation accuracy, over segmentation and under segmentation results were compared. The ZCR method had the highest accuracy (89%); however, it completely failed under moderate noise conditions. The SD method had the best combination of accuracy (86%), ability to perform under noisy conditions and low prevalence of over and under segmentation (22% and 15% respectively). Therefore, we recommend using an adaptive approach to silence removal among cough events based on the level of background noise (i.e use the ZCR method when the background noise is low and the SD method when it is higher) prior to implementation of a cough classification system.

Smart monitoring of fluid intake and bladder voiding using pressure sensitive mats.

Pressure sensitive mats have been used in noninvasive smart monitoring for a variety of problems including breathing rate monitoring, sleep monitoring, mobility, and weight. This paper describes a proof of concept application of pressure mats to monitor fluid intake/output (fluid cycle) events during the night. The ability to more accurately track such events has potential implications for monitoring those individuals who have nocturia, a condition where a person wakes at night to urinate. Data were collected from a healthy young female subject instructed to drink as much water as was comfortable (700mL) and lie in a supine position on a mattress located directly on three pressure mats. This was compared to an initial data set collected immediately after voiding but before drinking, 30 minutes after drinking, 60 minutes after drinking and a final data set after again voiding the bladder. The additional pressure from the 700mL of water was detectible and tracked over the course of the hour-long testing session under idealized conditions. This provides a proof-of-concept that nocturnal fluid intake and bladder voiding events can be tracked using non-invasive pressure-sensitive mats, however additional testing and development is required to achieve a deployable monitoring system.

1,25(OH)2D3 induces a mineralization defect and loss of bone mineral density in genetic hypercalciuric stone-forming rats.

Genetic hypercalciuric stone-forming (GHS) rats, bred to maximize urine (u) calcium (Ca) excretion, demonstrate increased intestinal Ca absorption, increased bone Ca resorption, and reduced renal Ca reabsorption, all leading to elevated uCa compared to the parental Sprague-Dawley (SD) rats. GHS rats have increased numbers of vitamin D receptors (VDRs) at each site, with normal levels of 1,25(OH)2D3 (1,25D), suggesting their VDR is undersaturated with 1,25D. We have shown that 1,25D induces a greater increase in uCa in GHS than SD rats. To examine the effect of the increased VDR on the osseous response to 1,25D, we fed GHS and SD rats an ample Ca diet and injected either 1,25D [low dose (LD) 12.5 or high dose (HD) 25 ng/100 g body weight/day] or vehicle (veh) daily for 16 days. Femoral areal bone mineral density (aBMD, by DEXA) was decreased in GHS+LD and GHS+HD relative to GHS+veh, while there was no effect on SD. Vertebral aBMD was lower in GHS compared to SD and further decreased in GHS+HD. Both femoral and L6 vertebral volumetric BMD (by µCT) were lower in GHS and further reduced by HD. Histomorphometry indicated a decreased osteoclast number in GHS+HD compared to GHS+veh or SD+HD. In tibiae, GHS+HD trabecular thickness and number increased, with a 12-fold increase in osteoid volume but only a threefold increase in bone volume. Bone formation rate was decreased in GHS+HD relative to GHS+veh, confirming the mineralization defect. The loss of BMD and the mineralization defect in GHS rats contribute to increased hypercalciuria; if these effects persist, they would result in decreased bone strength, making these bones more fracture-prone. The enhanced effect of 1,25D in GHS rats indicates that the increased VDRs are biologically active.