Increases in throughput and installed base of biomedical research equipment led to a massive accumulation of -omics data known to be highly variable, high-dimensional, and sourced from multiple often incompatible data platforms. While this data may be useful for biomarker identification and drug discovery, the bulk of it remains underutilized. Deep neural networks (DNNs) are efficient algorithms based on the use of compositional layers of neurons, with advantages well matched to the challenges -omics data presents. While achieving state-of-the-art results and even surpassing human accuracy in many challenging tasks, the adoption of deep learning in biomedicine has been comparatively slow. Here, we discuss key features of deep learning that may give this approach an edge over other machine learning methods. We then consider limitations and review a number of applications of deep learning in biomedical studies demonstrating proof of concept and practical utility.

The virtual reality format had improved selective attention and conflict resolution ability, revealing the potential of CR, specifically with virtual reality exercise, on executive function. Implications for Rehabilitation In cardiac rehabilitation, especially in phase III, it is important to develop and to present alternative strategies, as virtual reality using the Kinect in a home context. Taking into account the relationship between the improvement of the executive function with physical exercise, it is relevant to access the impact of a cardiac rehabilitation program on the executive function. Enhancing the value of the phase III of cardiac rehabilitation.

Subjects with cardiovascular diseases are referred to cardiac rehabilitation, with a possibility of using virtual reality environments. The study aimed to analyze the effect of a home-based specific exercise program, maintenance phase, with a six months period, performed in a virtual reality (Kinect) or conventional (booklet) environment, on the body composition, eating patter ns and lipid profile of subjects with coronary artery disease. Methods: A randomized controlled trial was conducted with subjects from a hospital in Porto, Portugal. Subjects were randomly assigned to either intervention group 1 (n = 11), whose program encompassed the use of Kinect; or intervention group 2, a booklet (n = 11) or a control group, only receiving education concerning cardiovascular risk factors (n = 11) during 6 months. Beyond the baseline, at 3 and 6 months the body composition was assessed with a bioimpedance scale and a tape-measure, eating patterns with the semi-quantitative food frequency questionnaire and three months later, the lipid profile with laboratory tests. Descriptive and inferential statistical measures were used with a significance level of 0.05. Results: The intervention group 1 revealed significant improvements in the waist-to-hip ratio after 6 months (p = 0.033) and, between the baseline and third month, when compared with the control group (p = 0.041). The intervention group 1 also decreased their ingestion of total fat (p = 0.032) after six months and increased the high-density lipoprotein cholesterol (p = 0.017) 3 months after the program's conclusion. Conclusions: The virtual reality format had a positive influence on body composition, specifically on the waist-to-hip ratio, in the first three months.