Leveraging the variational Bayes autoencoder for survival analysis.

Survival analysis in medical research has witnessed a growing interest in applying deep learning techniques to model complex, high-dimensional, heterogeneous, incomplete, and censored data. Current methods make assumptions about the relations between data that may not be valid in practice. Therefore, we introduce SAVAE (Survival Analysis Variational Autoencoder).

Explainable drug repurposing via path based knowledge graph completion.

Drug repurposing aims to find new therapeutic applications for existing drugs in the pharmaceutical market, leading to significant savings in time and cost. The use of artificial intelligence and knowledge graphs to propose repurposing candidates facilitates the process, as large amounts of data can be processed. However, it is important to pay attention to the explainability needed to validate the predictions.

Propensity Weighted federated learning for treatment effect estimation in distributed imbalanced environments.

Estimating treatment effects from observational data in medicine using causal inference is a very relevant task due to the abundance of observational data and the ethical and cost implications of conducting randomized experiments or experimental interventions. However, how could we estimate the effect of a treatment in a hospital that has very restricted access to treatment? In this paper, we want to address the problem of distributed causal inference, where hospitals not only have different distributions of patients, but also different treatment assignment criteria. Furthermore, it is necessary to take into account that due to privacy restrictions, personal patient data cannot be shared between hospitals.

MOSAIC: An Artificial Intelligence-Based Framework for Multimodal Analysis, Classification, and Personalized Prognostic Assessment in Rare Cancers.

Purpose: Rare cancers constitute over 20% of human neoplasms, often affecting patients with unmet medical needs. The development of effective classification and prognostication systems is crucial to improve the decision-making process and drive innovative treatment strategies. We have created and implemented MOSAIC, an artificial intelligence (AI)-based framework designed for multimodal analysis, classification, and personalized prognostic assessment in rare cancers.

DDQN-based optimal targeted therapy with reversible inhibitors to combat the Warburg effect.

We cover the Warburg effect with a three-component evolutionary model, where each component represents a different metabolic strategy. In this context, a scenario involving cells expressing three different phenotypes is presented. One tumour phenotype exhibits glycolytic metabolism through glucose uptake and lactate secretion.

Deep Learning for Efficient and Optimal Motion Planning for AUVs with Disturbances.

We use the recent advances in Deep Learning to solve an underwater motion planning problem by making use of optimal control tools-namely, we propose using the Deep Galerkin Method (DGM) to approximate the Hamilton-Jacobi-Bellman PDE that can be used to solve continuous time and state optimal control problems. In order to make our approach more realistic, we consider that there are disturbances in the underwater medium that affect the trajectory of the autonomous vehicle. After adapting DGM by making use of a surrogate approach, our results show that our method is able to efficiently solve the proposed problem, providing large improvements over a baseline control in terms of costs, especially in the case in which the disturbances effects are more significant.

Deep Reinforcement Learning for Attacking Wireless Sensor Networks.

Recent advances in Deep Reinforcement Learning allow solving increasingly complex problems. In this work, we show how current defense mechanisms in Wireless Sensor Networks are vulnerable to attacks that use these advances. We use a Deep Reinforcement Learning attacker architecture that allows having one or more attacking agents that can learn to attack using only partial observations.

Lung ultrasound in acute myocardial infarction. Updating Killip & Kimball.

Background: Heart failure complicating acute myocardial infarction marks an ominous prognosis. Killip and Kimball's classification of heart failure remains a useful tool in these patients. Lung ultrasound can detect pulmonary congestion but its usefulness in this scenario is unknown.

Repeated Game Analysis of a CSMA/CA Network under a Backoff Attack.

We study a CSMA/CA (Carrier Sense Medium Access with Collision Avoidance) wireless network where some stations deviate from the defined contention mechanism. By using Bianchi's model, we study how this deviation impacts the network throughput and show that the fairness of the network is seriously affected, as the stations that deviate achieve a larger share of the resources than the rest of stations. Previously, we modeled this situation using a static game and now, we use repeated games, which, by means of the Folk theorem, allow all players to have better outcomes.

Model Free Localization with Deep Neural Architectures by Means of an Underwater WSN.

In recent years, there has been a significant effort towards developing localization systems in the underwater medium, with current methods relying on anchor nodes, explicitly modeling the underwater channel or cooperation from the target. Lately, there has also been some work on using the approximation capabilities of Deep Neural Networks in order to address this problem. In this work, we study how the localization precision of using Deep Neural Networks is affected by the variability of the channel, the noise level at the receiver, the number of neurons of the neural network and the utilization of the power or the covariance of the received acoustic signals.

Is ReO a mixed ionic-electronic conductor? A DFT study of defect formation and migration in a BO perovskite-type oxide.

Density-functional-theory (DFT) calculations within the generalised gradient approximation (GGA) were used to examine the behaviour of point defects in the cubic BO perovskite-type oxide, ReO. Energies of reduction and of hydration were calculated, and the results are compared with literature data for ABO perovskite oxides. The activation energies of migration were determined for O, H, Li, Na, K and HO.

Wireless Networks under a Backoff Attack: A Game Theoretical Perspective.

We study a wireless sensor network using CSMA/CA in the MAC layer under a backoff attack: some of the sensors of the network are malicious and deviate from the defined contention mechanism. We use Bianchi's network model to study the impact of the malicious sensors on the total network throughput, showing that it causes the throughput to be unfairly distributed among sensors. We model this conflict using game theory tools, where each sensor is a player.

The Impacts of Exposure to Environmental Risk on Physical and Mental Health in a Small Geographic Community in Houston, TX.

Previous research has shown that communities with low average socioeconomic status (SES) and majority minority populations are more likely to be exposed to industrial buildings, waste facilities, and poor infrastructure compared to white communities with higher average SES. While some studies have demonstrated linkages between exposures to specific environmental contaminates within these communities and negative health outcomes, little research has analyzed the effects of environmental contaminants on the mental and physical health of these populations. A cross-sectional survey collected data from residents of Manchester, a small neighborhood in Houston, TX, that is characterized by industrial sites, unimproved infrastructure, nuisance flooding, and poor air quality.

Evaluating community and campus environmental public health programs.

The National Institute of Environmental Health Sciences' (NIEHS) Partnerships for Environmental Public Health (PEPH) program created the Evaluation Metrics Manual as a tool to help grantees understand how to map out their programs using a logic model, and to identify measures for documenting their achievements in environmental public health research. This article provides an overview of the manual, describing how grantees and community partners contributed to the manual, and how the basic components of a logic model can be used to identify metrics. We illustrate how the approach can be implemented, using a real-world case study from the University of Texas Medical Branch, where researchers worked with community partners to develop a network to address environmental justice issues.

[Right ventricular septal stimulation would produce similar bi-ventricular dyssynchrony as does apical stimulation in patients with normal ejection fraction].

Objective: To determine in patients with normal ejection fraction, undergoing permanent VVI pacing, if medial septal stimulation has lower dyssynchrony than apical stimulation assessed by echocardiography.

Method: A prospective trial, 19 patients>70 years old, scheduled for VVI pacemaker implantation for complete degenerative atrioventricular block, ventricular frequency<50beat per minute and ejection fraction≥45%. Patients with atrial fibrillation, heart failure, left bundle branch block and QRS durations longer than 120milliseconds in surface electrocardiogram with sinus rhythm were excluded.

Is the Scale for Measuring Motivational Interviewing Skills a valid and reliable instrument for measuring the primary care professionals motivational skills?: EVEM study protocol.

Background: Lifestyle is one of the main determinants of people's health. It is essential to find the most effective prevention strategies to be used to encourage behavioral changes in their patients. Many theories are available that explain change or adherence to specific health behaviors in subjects.

Minor myocardial damage is a prevalent condition in patients with acute heart failure syndromes and preserved systolic function with long-term prognostic implications: a report from the CIAST-HF (Collaborative Italo-Argentinean Study on cardiac Troponin T in Heart Failure) study.

Background: Half of patients with acute heart failure syndromes (AHFS) have preserved left ventricular ejection fraction (PLVEF). In this setting, the role of minor myocardial damage (MMD), as identified by cardiac troponin T (cTnT), remains to be established.

Aim: To evaluate the prevalence and long-term prognostic significance of cTnT elevations in patients with AHFS and PLVEF.

Reduced systolic performance by tissue Doppler in patients with preserved and abnormal ejection fraction: new insights in chronic heart failure.

Background: Tissue Doppler imaging (TDI) is useful in the evaluation of systolic and diastolic function. It allows assessment of ventricular dynamics in its longitudinal axis. We sought to investigate the difference in systolic and diastolic longitudinal function in patients with chronic heart failure (CHF) with normal and reduced ejection fraction.

Cardiac troponin T levels are associated with poor short- and long-term prognosis in patients with acute cardiogenic pulmonary edema.

Background: The clinical determinants of increased cardiac troponin T (cTnT) in patients with acute cardiogenic pulmonary edema are not well defined, and the ability of this marker to predict long-term mortality has not yet been documented.

Methods: Eighty-four patients with acute cardiogenic pulmonary edema without acute myocardial infarction were prospectively enrolled. cTnT was measured in samples obtained 6 and 12 hours after admission.

Sources of SO, SO, NO, and NO- in the Air of Four Spanish Remote Stations.

In this study we have analyzed the sources of SO, SO, No, and NO in the air of four remote Spanish stations belonging to the European Monitoring and Evaluation Programme (EMEP) network. Information about trajectories has been used together with the conditional probability functions (CPFs). The most remarkable result is that the Mediterranean area is the main source of these pollutants in the air of the Spanish EMEP stations.