RESUMO
The phonocardiogram (PCG) or heart sound auscultation is a low-cost and non-invasive method to diagnose Congenital Heart Disease (CHD). However, recognizing CHD in the pediatric population based on heart sounds is difficult because it requires high medical training and skills. Also, the dependency of PCG signal quality on sensor location and developing heart in children are challenging. This study proposed a deep learning model that classifies unprocessed or raw PCG signals to diagnose CHD using a one-dimensional Convolution Neural Network (1D-CNN) with an attention transformer. The model was built on the raw PCG data of 484 patients. The results showed that the attention transformer model had a good balance of accuracy of 0.923, a sensitivity of 0.973, and a specificity of 0.833. The Receiver Operating Characteristic (ROC) plot generated an Area Under Curve (AUC) value of 0.964, and the F1-score was 0.939. The suggested model could provide quick and appropriate real-time remote diagnosis application in classifying PCG of CHD from non-CHD subjects.Clinical Relevance- The suggested methodology can be utilized to analyze PCG signals more quickly and affordably for rural doctors as a first screening tool before sending the cases to experts.
Assuntos
Cardiopatias Congênitas , Ruídos Cardíacos , Humanos , Criança , Fonocardiografia , Processamento de Sinais Assistido por Computador , Redes Neurais de Computação , Cardiopatias Congênitas/diagnósticoRESUMO
The study aims to explore the demographic and clinical characteristics of persons with spinal cord injury (SCI) in Bangladesh. A total of 3035 persons with SCI spanning from 2018 to 2022 were included in this cross-sectional study. Information about demographic and clinical variables was obtained from the medical records and verified through telephone calls to ensure accuracy and consistency. Approximately half (48.30%) of the study participants were located in Dhaka Division. The average age of persons with SCI was 38.3 years, with a standard deviation of 15.9 years, and the largest proportion (33.4%) fell within the age range of 18-30 years. Males outnumbered females by nearly 2.5 times. In the study, 59.6% had suffered traumatic injuries, whereas 40.4% had SCI attributable to disease-related causes; 58.1% were diagnosed with tetraplegia and 40.1% with paraplegia. Fall from height (42.1%) and road traffic trauma (27%) were the most common causes of traumatic injuries. Degenerative myelopathy (41.1%) was the most frequent cause of non-traumatic SCI, followed by tumors (27.7%) and tuberculosis (TB; 14.8%). Both traumatic (58.3%) and degenerative (56.7%) causes of SCI commonly affected the cervical spine, whereas TB (24.4%) and tumors (47.5%) had a higher incidence of affecting the dorsal spine. In the absence of a registry or national database for patients with SCI in Bangladesh, this study would serve as representative data for future studies.
RESUMO
Like Smart Home and Smart Devices, Smart Navigation has become necessary to travel through the congestion of the structure of either building or in the wild. The advancement in smartphone technology and incorporation of many different precise sensors have made the smartphone a unique choice for developing practical navigation applications. Many have taken the initiative to address this by developing mobile-based solutions. Here, a cloud-based intelligent traveler assistant is proposed that exploits user-generated position and elevation data collected from ubiquitous smartphone devices equipped with Accelerometer, Gyroscope, Magnetometer, and GPS (Global Positioning System) sensors. The data can be collected by the pedestrians and the drivers, and are then automatically put into topological information. The platform and associated innovative application allow travelers to create a map of a route or an infrastructure with ease and to share the information for others to follow. The cloud-based solution that does not cost travelers anything allows them to create, access, and follow any maps online and offline. The proposed solution consumes little battery power and can be used with lowly configured resources. The ability to create unknown, unreached, or unrecognized rural/urban road maps, building structures, and the wild map with the help of volunteer traveler-generated data and to share these data with the greater community makes the presented solution unique and valuable. The proposed crowdsourcing method of knowing the unknown would be an excellent support for travelers.