Deep learning analysis of resting electrocardiograms for the detection of myocardial dysfunction, hypertrophy, and ischaemia: a systematic review.

The aim of this review was to assess the evidence for deep learning (DL) analysis of resting electrocardiograms (ECGs) to predict structural cardiac pathologies such as left ventricular (LV) systolic dysfunction, myocardial hypertrophy, and ischaemic heart disease. A systematic literature search was conducted to identify published original articles on end-to-end DL analysis of resting ECG signals for the detection of structural cardiac pathologies. Studies were excluded if the ECG was acquired by ambulatory, stress, intracardiac, or implantable devices, and if the pathology of interest was arrhythmic in nature. After duplicate reviewers screened search results, 12 articles met the inclusion criteria and were included. Three articles used DL to detect LV systolic dysfunction, achieving an area under the curve (AUC) of 0.89-0.93 and an accuracy of 98%. One study used DL to detect LV hypertrophy, achieving an AUC of 0.87 and an accuracy of 87%. Six articles used DL to detect acute myocardial infarction, achieving an AUC of 0.88-1.00 and an accuracy of 83-99.9%. Two articles used DL to detect stable ischaemic heart disease, achieving an accuracy of 95-99.9%. Deep learning models, particularly those that used convolutional neural networks, outperformed rules-based models and other machine learning models. Deep learning is a promising technique to analyse resting ECG signals for the detection of structural cardiac pathologies, which has clinical applicability for more effective screening of asymptomatic populations and expedited diagnostic work-up of symptomatic patients at risk for cardiovascular disease.

Knockout of USP19 Deubiquitinating Enzyme Prevents Muscle Wasting by Modulating Insulin and Glucocorticoid Signaling.

Muscle atrophy arises because of many chronic illnesses, as well as from prolonged glucocorticoid treatment and nutrient deprivation. We previously demonstrated that the USP19 deubiquitinating enzyme plays an important role in chronic glucocorticoid- and denervation-induced muscle wasting. However, the mechanisms by which USP19 exerts its effects remain unknown. To explore this further, we fasted mice for 48 hours to try to identify early differences in the response of wild-type and USP19 knockout (KO) mice that could yield insights into the mechanisms of USP19 action. USP19 KO mice manifested less myofiber atrophy in response to fasting due to increased rates of protein synthesis. Insulin signaling was enhanced in the KO mice, as revealed by lower circulating insulin levels, increased insulin-stimulated glucose disposal and phosphorylation of Akt and S6K in muscle, and improved overall glucose tolerance. Glucocorticoid signaling, which is essential in many conditions of atrophy, was decreased in KO muscle, as revealed by decreased expression of glucocorticoid receptor (GR) target genes upon both fasting and glucocorticoid treatment. This decreased GR signaling was associated with lower GR protein levels in the USP19 KO muscle. Restoring the GR levels in USP19-deficient muscle was sufficient to abolish the protection from myofiber atrophy. Expression of GR target genes also correlated with that of USP19 in human muscle samples. Thus, USP19 modulates GR levels and in so doing may modulate both insulin and glucocorticoid signaling, two critical pathways that control protein turnover in muscle and overall glucose homeostasis.

Inactivation of the ubiquitin-specific protease 19 deubiquitinating enzyme protects against muscle wasting.

The ubiquitin system plays a critical role in muscle wasting. Previous work has focused on the roles of ubiquitination. However, a role for deubiquitination in this process has not been established. Because ubiquitin-specific protease (USP)19 deubiquitinating enzyme is induced in skeletal muscle in many catabolic conditions, we generated USP19 knockout (KO) mice. These mice lost less muscle mass than wild-type (WT) animals in response to glucocorticoids, a common systemic cause of muscle atrophy as well as in response to denervation, a model of disuse atrophy. KO mice retained more strength and had less myofiber atrophy with both type I and type IIb fibers being protected. Rates of muscle protein synthesis were similar in WT and KO mice, suggesting that the sparing of atrophy was attributed to suppressed protein degradation. Consistent with this, expression of the ubiquitin ligases MuRF1 and MAFbx/atrogin-1 as well as several autophagy genes was decreased in the muscles of catabolic KO mice. Expression of USP19 correlates with that of MuRF1 and MAFbx/atrogin-1 in skeletal muscles from patients with lung cancer or gastrointestinal cancer, suggesting that USP19 is involved in human muscle wasting. Inhibition of USP19 may be a useful approach to the treatment of many muscle-wasting conditions.