Coronary artery disease (CAD) is the most common cause of heart disease globally. This is because there is no symptom exhibited in its initial phase until the disease progresses to an advanced stage. The electrocardiogram (ECG) is a widely accessible diagnostic tool to diagnose CAD that captures abnormal activity of the heart. However, it lacks diagnostic sensitivity. One reason is that, it is very challenging to visually interpret the ECG signal due to its very low amplitude. Hence, identification of abnormal ECG morphology by clinicians may be prone to error. Thus, it is essential to develop a software which can provide an automated and objective interpretation of the ECG signal. This paper proposes the implementation of long short-term memory (LSTM) network with convolutional neural network (CNN) to automatically diagnose CAD ECG signals accurately. Our proposed deep learning model is able to detect CAD ECG signals with a diagnostic accuracy of 99.85% with blindfold strategy. The developed prototype model is ready to be tested with an appropriate huge database before the clinical usage.
Epitheliotropic intestinal T-cell lymphoma (EITL, also known as type II enteropathy-associated T-cell lymphoma) is an aggressive intestinal disease with poor prognosis and its molecular alterations have not been comprehensively characterized. We aimed to identify actionable easy-to-screen alterations that would allow better diagnostics and/or treatment of this deadly disease. By performing whole-exome sequencing of four EITL tumor-normal pairs, followed by amplicon deep sequencing of 42 tumor samples, frequent alterations of the JAK-STAT and G-protein-coupled receptor (GPCR) signaling pathways were discovered in a large portion of samples. Specifically, STAT5B was mutated in a remarkable 63% of cases, JAK3 in 35% and GNAI2 in 24%, with the majority occurring at known activating hotspots in key functional domains. Moreover, STAT5B locus carried copy-neutral loss of heterozygosity resulting in the duplication of the mutant copy, suggesting the importance of mutant STAT5B dosage for the development of EITL. Dysregulation of the JAK-STAT and GPCR pathways was also supported by gene expression profiling and further verified in patient tumor samples. In vitro overexpression of GNAI2 mutants led to the upregulation of pERK1/2, a member of MEK-ERK pathway. Notably, inhibitors of both JAK-STAT and MEK-ERK pathways effectively reduced viability of patient-derived primary EITL cells, indicating potential therapeutic strategies for this neoplasm with no effective treatment currently available.