Blood Pressure Models for Wearable Sensors

<div>As cardiovascular diseases are one of the most prominent illnesses, a continuous, non-invasive, and comfortable monitoring of blood pressure (BP) is indispensable. This paper investigates the best method for obtaining highly accurate BP values in non-invasive measurements when using an ultrasound (US) sensor projected for a wrist-worn device. State-of-the-art BP models were analyzed and qualitatively compared. Relevant arterial parameters such as luminal area, flow velocity and pulse wave velocity, of 729 subjects were extracted from a computer simulated database and served as input parameters for the wearable US. A linear in-silico model calibrated to each arterial-site revealed to be most accurate model. The linear model was used for the extraction of BP by using the US sensor and validated with a commercial pressure sensor in an ex-vivo experimental setup. The results showed an in-silico pulse pressure correlation of 0.978 and mean difference of (-2.134±2.477) mmHg at the radial artery and ex-vivo pressure correlation of 0.994 and mean difference of (0.554 ± 2.315) mmHg. Thus, with the linear model, the US measurement complies with the Association for the Advancement of Medical Instrumentation standard with deviations lower than 5 mmHg.</div>

Purwarupa Spirometer Digital Berbasis LABVIEW

Spirometer is an instrument used to measure the vital capacity of the human lung and is usually only found in large hospitals or clinical laboratories because of its relatively high price. However, to find out how this instrument works, a prototype of the spirometer is made by utilizing a Labview-based interface. This prototype was developed by making an air channel or funnel the size of a human mouth which then the air will be detected by a pressure sensor connected to a signal conditioning circuit and then the measurement information data is forwarded by the Arduino to a computer to be processed into digital data which is then converted into vital capacity information data. lungs. The results obtained from this research are that it can make a spirometer prototype according to its function which is hoped to be used as a learning medium in the field of medical instrumentation by measuring the vital capacity of the lungs in the form of height, age, and gender of a person, besides that the results are in the form of a graphic display. and numerical data from the measurement process on the GUI display in LabVIEW. This prototype was calibrated using a syringe with a volume of 2 liters and the accuracy rate was 99.63% with a standard deviation value of ± 70.61 ml and a precision value of 1.76% from these results.

Nosocomial transmission of necrotising fasciitis organisms from prepartum patient to healthcare worker

Necrotising fasciitis is an aggressive skin and soft tissue infection requiring urgent surgical treatment, resuscitative efforts and intensive care management. We herein present a case of necrotising fasciitis with nosocomial transmission of causative organisms from patient to healthcare worker. Bacterial transmission from human to human despite personal protective equipment is quite rare, and with limited reports in the literature. The patient was also prepartum, representing to our knowledge, one of only a handful of cases of prepartum necrotising fasciitis. Recommendations to avoid healthcare worker transmission include wearing Association of the Advancement of Medical Instrumentation level 4 gowns during debridement, as well as eye protection and changing scrubs and showering between cases.

KecNet: A Light Neural Network for Arrhythmia Classification Based on Knowledge Reinforcement

Acquiring electrocardiographic (ECG) signals and performing arrhythmia classification in mobile device scenarios have the advantages of short response time, almost no network bandwidth consumption, and human resource savings. In recent years, deep neural networks have become a popular method to efficiently and accurately simulate nonlinear patterns of ECG data in a data-driven manner but require more resources. Therefore, it is crucial to design deep learning (DL) algorithms that are more suitable for resource-constrained mobile devices. In this paper, KecNet, a lightweight neural network construction scheme based on domain knowledge, is proposed to model ECG data by effectively leveraging signal analysis and medical knowledge. To evaluate the performance of KecNet, we use the Association for the Advancement of Medical Instrumentation (AAMI) protocol and the MIT-BIH arrhythmia database to classify five arrhythmia categories. The result shows that the ACC, SEN, and PRE achieve 99.31%, 99.45%, and 98.78%, respectively. In addition, it also possesses high robustness to noisy environments, low memory usage, and physical interpretability advantages. Benefiting from these advantages, KecNet can be applied in practice, especially wearable and lightweight mobile devices for arrhythmia classification.

Elimination of Multicollinearity in Continuous Non-Invasive Blood Pressure Approximation by Information Criterion

Continuous and unobtrusive method of measuring blood pressure has been gaining more attention in the healthcare community. With the application of data analysis techniques in biosignals like Electrocardiogram (ECG) and Photoplethysmogram (PPG), several predictors are obtained that correlates well with the blood pressure. But the BP approximation regression models formed using these predictors suffers from multicollinearity (higher correlation between predictors). The article proposes the use of information criterion-based model ensemble approach to reduce the effect of multicollinearity in the continuous BP estimation. The study focuses on forming pool of candidate models from feature subsets. The best performing models are selected based on information criterion and combined to form the ensemble model. Experiments with performed with MIMIC-II dataset that consists of 104 records with simultaneously recorded PPG and arterial BP. The results suggest that the technique achieves Mean Absolute Error (MAE) of 5.81 mm Hg and 3.35 mm Hg for systolic and diastolic BP and Root Mean Square Error (RMSE) of 6.08 mm Hg and 4.12 mm Hg for systolic and diastolic BP respectively. The error measures conform to the standards set by American Association of Medical Instrumentation (AAMI). The method reveals that the ensemble model based on information criterion outperforms well compared to the usage of single model.