This paper presents an approach for automatic segmentation of cardiac events from non-invasive sounds recordings, without the need of having an auxiliary signal reference. In addition, methods are proposed to subsequently differentiate cardiac events which correspond to normal cardiac cycles, from those which are due to abnormal activity of the heart. The detection of abnormal sounds is based on a model built with parameters which are obtained following feature extraction from those segments that were previously identified as normal fundamental heart sounds. The proposed algorithm achieved a sensitivity of 91.79% and 89.23% for the identification of normal fundamental, S and S sounds, and a true positive (TP) rate of 81.48% for abnormal additional sounds. These results were obtained using the PASCAL Classifying Heart Sounds challenge (CHSC) database.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/EMBC.2019.8857695 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
An integrative taxonomic approach reveals two putatively novel species of phlebotomine sand fly (Diptera: Psychodidae) in Thailand.
Parasit Vectors
January 2025
Center of Excellence in Veterinary Parasitology, Department of Pathology, Faculty of Veterinary Science, Chulalongkorn University, Bangkok, 10330, Thailand.
Background: The subfamily Phlebotominae comprises 1028 species of sand fly, of which only 90 are recognized as vectors of pathogenic agents such as Trypanosoma, Leishmania, and Bartonella. In Thailand, leishmaniasis-a sand fly-borne disease-is currently endemic, with 36 documented sand fly species. However, many cryptic species likely remain unidentified.
View Article and Find Full Text PDFAutomatic image generation and stage prediction of breast cancer immunobiological through a proposed IHC-GAN model.
BMC Med Imaging
January 2025
Electronics and Communications, Arab Academy for Science, Heliopolis, Cairo, 2033, Egypt.
Invasive breast cancer diagnosis and treatment planning require an accurate assessment of human epidermal growth factor receptor 2 (HER2) expression levels. While immunohistochemical techniques (IHC) are the gold standard for HER2 evaluation, their implementation can be resource-intensive and costly. To reduce these obstacles and expedite the procedure, we present an efficient deep-learning model that generates high-quality IHC-stained images directly from Hematoxylin and Eosin (H&E) stained images.
View Article and Find Full Text PDFAutonomous International Classification of Diseases Coding Using Pretrained Language Models and Advanced Prompt Learning Techniques: Evaluation of an Automated Analysis System Using Medical Text.
JMIR Med Inform
January 2025
Medical Big Data Research Center, Chinese PLA General Hospital, Beijing, China.
Background: Machine learning models can reduce the burden on doctors by converting medical records into International Classification of Diseases (ICD) codes in real time, thereby enhancing the efficiency of diagnosis and treatment. However, it faces challenges such as small datasets, diverse writing styles, unstructured records, and the need for semimanual preprocessing. Existing approaches, such as naive Bayes, Word2Vec, and convolutional neural networks, have limitations in handling missing values and understanding the context of medical texts, leading to a high error rate.
View Article and Find Full Text PDFThe study of heat tolerance in Drosophila melanogaster has been of particular interest to researchers for decades, with a common approach to assessing heat tolerance being to monitor the time to knockdown (TKD) after exposure to an elevated temperature. Classically, flies are housed in individual vials and placed inside a heated water bath. TKD is then monitored manually by researchers.
View Article and Find Full Text PDFhvEEGNet: a novel deep learning model for high-fidelity EEG reconstruction.
Front Neuroinform
December 2024
Department of Informatics, Systems and Communication, University of Milano-Bicocca, Milan, Italy.
Introduction: Modeling multi-channel electroencephalographic (EEG) time-series is a challenging tasks, even for the most recent deep learning approaches. Particularly, in this work, we targeted our efforts to the high-fidelity reconstruction of this type of data, as this is of key relevance for several applications such as classification, anomaly detection, automatic labeling, and brain-computer interfaces.
Methods: We analyzed the most recent works finding that high-fidelity reconstruction is seriously challenged by the complex dynamics of the EEG signals and the large inter-subject variability.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!