Abstract
In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitting that has witnessed significant success in various classification applications. Recently, many efforts have been made to improve the Standard dropout using an unsupervised merit-based semantic selection of neurons in the latent space. However, these studies do not consider the task-relevant information quality and quantity and the diversity of the latent kernels. To solve the challenge of dropping less informative neurons in deep learning, we propose an efficient end-to-end dropout algorithm that selects the most informative neurons with the highest correlation with the target output considering the sparsity in its selection procedure. First, to promote activation diversity, we devise an approach to select the most diverse set of neurons by making use of determinantal point process (DPP) sampling. Furthermore, to incorporate task specificity into deep latent features, a mutual information (MI)-based merit function is developed. Leveraging the proposed MI with DPP sampling, we introduce the novel DPPMI dropout that adaptively adjusts the retention rate of neurons based on their contribution to the neural network task. Empirical studies on real-world classification benchmarks including, MNIST, SVHN, CIFAR10, CIFAR100, demonstrate the superiority of our proposed method over recent state-of-the-art dropout algorithms in the literature.

Abstract
Objective: Patients with epilepsy, mainly drug-resistant, have reduced heart rate variability (HRV), linked to an increased risk of sudden death in various other diseases. In this context, it could play a role in SUDEP. Generalized convulsive seizures (GCS) are one of the most consensual risk factors for SUDEP. Our objective was to assess the influence of GCS in HRV parameters in patients with drug-resistant epilepsy. Methods: We prospectively evaluated 121 patients with refractory epilepsy admitted to our Epilepsy Monitoring Unit. All patients underwent a 48-hour Holter recording. Only patients with GCS were included (n = 23), and we selected the first as the index seizure. We evaluated HRV (AVNN, SDNN, RMSSD, pNN50, LF, HF, and LF/HF) in 5-min epochs (diurnal and nocturnal baselines; preictal - 5 min before the seizure; ictal; postictal - 5 min after the seizure; and late postictal - >5 h after the seizure). These data were also compared with normative values from a healthy population (controlling for age and gender). Results: We included 23 patients, with a median age of 36 (min-max, 16-55) years and 65% were female. Thirty percent had cardiovascular risk factors, but no previously known cardiac disease. HRV parameters AVNN, RMSSD, pNN50, and HF were significantly lower in the diurnal than in the nocturnal baseline, whereas the opposite occurred with LF/HF and HR. Diurnal baseline parameters were inferior to the normative population values (which includes only diurnal values). We found significant differences in HRV parameters between the analyzed periods, especially during the postictal period. All parameters but LF/HF suffered a reduction in that period. LF/HF increased in that period but did not reach statistical significance. Visually, there was a tendency for a global reduction in our patients' HRV parameters, namely AVNN, RMSSD, and pNN50, in each period, comparing with those from a normative healthy population. No significant differences were found in HRV between diurnal and nocturnal seizures, between temporal lobe and extra-temporal-lobe seizures, between seizures with and without postictal generalized EEG suppression, or between seizures of patients with and without cardiovascular risk factors. Significance/conclusion: Our work reinforces the evidence of autonomic cardiac dysfunction in patients with refractory epilepsy, at baseline and mainly in the postictal phase of a GCS. Those changes may have a role in some SUDEP cases. By identifying patients with worse autonomic cardiac function, HRV could fill the gap of a lacking SUDEP risk biomarker.

Abstract
Liquid biopsy is an emerging technology with a potential role in the screening and early detection of lung cancer. Several liquid biopsy-derived biomarkers have been identified and are currently under ongoing investigation. In this article, we review the available data on the use of circulating biomarkers for the early detection of lung cancer, focusing on the circulating tumor cells, circulating cell-free DNA, circulating micro-RNAs, tumor-derived exosomes, and tumor-educated platelets, providing an overview of future potential applicability in the clinical practice. While several biomarkers have shown exciting results, diagnostic performance and clinical applicability is still limited. The combination of different biomarkers, as well as their combination with other diagnostic tools show great promise, although further research is still required to define and validate the role of liquid biopsies in clinical practice.

Abstract
The classification of the type of trapped particles is a crucial task for an efficient integration of optical-tweezers in intelligent microfluidic devices. In the recent years, the use of the temporal scattering signal of the trapped particle paved for the use of versatile optical fiber solutions for performing such tasks, a feature previously unavailable as most methods required conventional optical tweezer setups. This work presents a comprehensive comparison of performances achieved with two distinct implementations – i)optical fiber and ii)conventional optical tweezers – for the classification of the material of particles through the analysis of the scattering signal with machine learning algorithms. The results suggest that while micron-sized particles can be accurately classified using the forward scattering information in conventional optical tweezers, when equipped with a quadrant photodetector, the optical fiber tweezers solutions can easily surpass its performance using the back-scattered information if the laser is modulated. Together with the advantages of being simpler, less expensive and more versatile, the results presented suggest that optical fiber solutions can become a valuable tool for miniaturization and integration of intelligent microfluidic devices working towards nanoscopic scales. © 2021 The Authors

Abstract
Heart failure (HF) is a multifactorial chronic syndrome with progressive increasing incidence causing a huge financial burden worldwide. Remote monitoring should, in theory, improve HF management, but given increasing morbidity and mortality, a question remains: are we monitoring it properly? Device-based home monitoring enables objective and continuous measurement of vital variables and non-invasive devices should be first choice for elderly patients. There is no shortage of literature on the subject, however, most studies were designed to monitor a single variable or class of variables that were not properly assembled and, to the best of our knowledge, there are no large randomized studies about their impact on HF patient management. To overcome this problem, we carefully selected the most critical possible HF decompensating factors to design MONITORIA, a non-invasive device for comprehensive HF home monitoring. MONITORIA stands for MOnitoring Non-Invasively To Overcome mortality Rates of heart Insufficiency on Ambulatory, and in this paper, which is part I of a series of three articles, we discuss the theoretical basis for its design. MONITORIA and its inherent follow-up strategy will optimize HF patient care as it is a promising device, which will essentially adapt innovation not to the disease but rather to the patients. (C) 2020 Sociedade Portuguesa de Cardiologia. Published by Elsevier Espana, S.L.U.

Abstract
[No abstract available]