Investigating the Relationship between Cough Detection and Sampling Frequency for Wearable Devices.

Cough detection can provide an important marker to monitor chronic respiratory conditions. However, manual techniques which require human expertise to count coughs are both expensive and time-consuming. Recent Automatic Cough Detection Algorithms (ACDAs) have shown promise to meet clinical monitoring requirements, but only in recent years they have made their way to non-clinical settings due to the required portability of sensing technologies and the extended duration of data recording. More precisely, these ACDAs operate at high sampling frequencies, which leads to high power consumption and computing requirements, making these difficult to implement on a wearable device. Additionally, reproducibility of their performance is essential. Unfortunately, as the majority of ACDAs were developed using private clinical data, it is difficult to reproduce their results. We, hereby, present an ACDA that meets clinical monitoring requirements and reliably operates at a low sampling frequency. This ACDA is implemented using a convolutional neural network (CNN), and publicly available data. It achieves a sensitivity of 92.7%, a specificity of 92.3%, and an accuracy of 92.5% using a sampling frequency of just 750 Hz. We also show that a low sampling frequency allows us to preserve patients' privacy by obfuscating their speech, and we analyze the trade-off between speech obfuscation for privacy and cough detection accuracy.Clinical relevance-This paper presents a new cough detection technique and preliminary analysis on the trade-off between detection accuracy and obfuscation of speech for privacy. These findings indicate that, using a publicly available dataset, we can sample signals at 750 Hz while still maintaining a sensitivity above 90%, suggested to be sufficient for clinical monitoring [1].

Ondansetron Is an Effective Alternative to Decrease the Incidence of Postspinal Hypotension in Healthy Subjects Undergoing Infra-Umbilical Surgeries Compared To Combined Volume Loading and Vasoconstrictors: Randomized Controlled Trial.

BACKGROUND: One of the important and predicted physiological effects of spinal anaesthesia is hypotension. A range of strategies including mechanical interventions, intravenous fluids and vasoconstrictor drugs have been used to minimise or prevent spinal anaesthesia-induced hypotension. Observational studies suggest that ondansetron reduces the incidence of post-spinal hypotension (PSH) and support the use of combined fluid preloading and vasoconstrictors for this purpose (but with limited doses) to avoid side effects as fluid overload and tachycardia respectively. AIM: As no RCT had ever compared the use of Ondansetron alone with combined vasoconstrictors and fluid preload, so, this randomised controlled trial has evaluated the efficacy of the use of ondansetron alone compared to the combined use of fluid preload and vasoconstrictors to decrease the incidence of spinal hypotension. METHODS: Ninety patients of ASA grade I between the age of 18 and 45 years scheduled to undergo elective surgical procedures on the lower extremity or lower abdomen under spinal anaesthesia were included in the study. The patients were randomly allocated into two groups of 45 each. Group I patients (ondansetron group) received 4 mg ondansetron in 5 ml normal saline (IV) 15 minutes before induction of spinal anaesthesia. Group II patients (combination group) received preloading with 7.5 ml/kg/min of Ringer's lactate over 10 minute period preceding the spinal block followed by intravenous bolus of 2.5 mg ephedrine in the first and second minute and 2.5 mg ephedrine every 5 minutes for the next 20 minutes after the injection of spinal anesthetic drug. Non-invasive measurement of mean arterial pressures, heart rate, reactive hypertension, nausea and vomiting were documented. RESULTS: The incidence of hypotension following the subarachnoid block in Group I (ondansetron group) was 17.6% versus group II (combination group) was 13.3%, while difference among the groups is statistically insignificant (P = 0.082). Group IV fluids alone could reverse hypotension in 57.1% of patients in group I 33.3% in group II. 42.9% of patients in group I and 67.7% in group II could not be managed with IV fluids alone and had to be treated with 5 mg boluses of ephedrine for reversal of hypotension. The difference in the mean number of fluid boluses and a dose of ephedrine used between both groups was statistically insignificant (P = 0.11 and P = 0.21). HR showed a significant increase in group II and a statistically insignificant change in group I with a statistically significant difference in the heart rate (HR) between both groups (P < 0.05). Reactive hypertension, nausea and vomiting between both groups were statistically insignificant. CONCLUSION: The preemptive use of Ondansetron alone versus combined vasoconstrictors with fluid preload significantly reduces the incidence of post-spinal hypotension (PSH) with no significant difference between both regimens. Furthermore, they also reduced consumption of the used vasoconstrictors and fluids to correct hypotension.