RESUMEN

Valvular heart diseases (VHD) are one of the major causes of cardiovascular diseases that are having high mortality rates worldwide. The early diagnosis of VHD prevents the development of cardiac diseases and allows for optimum medication. Despite of the ability of current gold standards in identifying VHD, they still lack the required accuracy and thus, several cases go misdiagnosed. In this vein, a study is conducted herein to investigate the efficiency of deep learning models in identifying VHD through phonocardiography (PCG) recordings. PCG heart sounds were obtained from an open-access data-set representing normal heart sounds along with four major VHD; namely aortic stenosis (AS), mitral stenosis (MS), mitral regurgitation (MR), and mitral valve prolapse (MVP). A total of 1,000 patients were involved in the study with 200 recordings for each class. All recordings were initially trimmed to have 9,600 samples ensuring their coverage of at least 1 cardiac cycle. In addition, they were pre-processed by applying maximal overlap discrete wavelet transform (MODWT) smoothing algorithm and z-score normalization. The neural network architecture was designed to reduce the complexity often found in literature and consisted of a combination of convolutional neural networks (CNN) and recurrent neural networks (RNN) based on Bi-directional long short-term memory (BiLSTM). The model was trained and tested following a k-fold cross-validation scheme of 10-folds utilizing the CNN-BiLSTM network as well as the CNN and BiLSTM, individually. The highest performance was achieved using the CNN-BiLSTM network with an overall Cohen's kappa, accuracy, sensitivity, and specificity of 97.87%, 99.32%, 98.30%, and 99.58%, respectively. In addition, the model had an average area under the curve (AUC) of 0.998. Furthermore, the performance of the model was assessed on the PhysioNet/Computing in Cardiology 2016 challenge data-set and reached an overall accuracy of 87.31% with an AUC of 0.900. This study paves the way towards implementing deep learning models in VHD identification under clinical settings to assist clinicians in decision making and prevent many cases from cardiac abnormalities development.

Asunto(s)

RESUMEN

This dataset is the first effort to combine the audio biodiversity of a taxonomic group in a selected location, the Boyacá department in Colombia. We conducted a detailed review of the sound recordings for birds from the Boyacá department within three repositories, the environmental sound collection of the Humboldt Institute, the Macaulay Library of the Cornell Lab of Ornithology, and the xeno-canto platform of the Naturalis Biodiversity Center. We selected recordings that were identified up to species and had complete metadata information. Using latitude and longitude information, we assigned each recording to one of the three regions and one of the 12 biotic units reported for Boyacá. We reported a total of 2321 recordings belonging to the Andean region (1892), Orinoquian region (425), and Carare-Lebrija-Nechi-Sinu (4). The sounds of Boyacá birds have been sampled for approximately three decades, with two peaks of activity in the early 2000's and 2018. We also included a map with the distribution of biotic units and sound recordings of our dataset. This dataset can be used to extract acoustic traits to test hypotheses of turnover in the acoustic space or traits by species, or to compare acoustic traits between species. It can also allow decision-makers to support biodiversity-based economies such as avitourism.