No abstract

Heart disease is a malignant threat to human health. Electrocardiogram (ECG) tests are used to help diagnose heart disease by recording the heart’s activity. However, automated medical-aided diagnosis with computers usually requires a large volume of labeled clinical data without patients' privacy to train the model, which is an empirical problem that still needs to be solved. To address this problem, we propose a generative adversarial network (GAN), which is composed of a bidirectional long short-term memory(LSTM) and convolutional neural network(CNN), referred as BiLSTM-CNN,to generate synthetic ECG data that agree with existing clinical data so that the features of patients with heart disease can be retained. The model includes a generator and a discriminator, where the generator employs the two layers of the BiLSTM networks and the discriminator is based on convolutional neural networks. The 48 ECG records from individuals of the MIT-BIH database were used to train the model. We compared the performance of our model with two other generative models, the recurrent neural network autoencoder(RNN-AE) and the recurrent neural network variational autoencoder (RNN-VAE). The results showed that the loss function of our model converged to zero the fastest. We also evaluated the loss of the discriminator of GANs with different combinations of generator and discriminator. The results indicated that BiLSTM-CNN GAN could generate ECG data with high morphological similarity to real ECG recordings.

No abstract

No abstract

Mutations in the tubulin beta 8 class VIII (TUBB8) gene have been proven to cause oocyte maturation arrest. The aim of this study was to describe newly discovered mutations in TUBB8 and to investigate the prevalence of TUBB8 mutations in our cohort. Nine women with oocyte maturation arrest and 100 fertile female controls were recruited. Sanger sequencing of the coding regions of TUBB8 revealed a heterozygous variant c.535G > A (p.V179M) in two unrelated affected individuals and a heterozygous variant c.5G > T (p.R2M) in one affected individual. These TUBB8 variants were inherited from the unaffected fathers and were absent in 100 fertile female control individuals. In total, 33.33% (3/9) of the affected individuals in our cohort obtained a clear genetic diagnosis through sequencing of the TUBB8 gene. These two novel variants extend the spectrum of TUBB8 mutations and this study confirmed that TUBB8 mutations occur in a high proportion of infertile women with oocyte maturation arrest.