Publications

The issue of failed weaning is a critical concern in the intensive care unit (ICU) setting. This scenario occurs when a patient experiences difficulty maintaining spontaneous breathing and ensuring a patent airway within the first 48 hours after the withdrawal of mechanical ventilation. Approximately 20% of ICU patients experience this phenomenon, which has severe repercussions on their health. It also has a substantial impact on clinical evolution and mortality, which can increase by 25% to 50%. To address this issue, we propose a medical support system that uses a convolutional neural network (CNN) to assess a patient's suitability for disconnection from a mechanical ventilator after a spontaneous breathing test (SBT). During SBT, respiratory flow and electrocardiographic activity were recorded and after processed using time-frequency analysis (TFA) techniques. Two CNN architectures were evaluated in this study: one based on ResNet50, with parameters tuned using a Bayesian optimization algorithm, and another CNN designed from scratch, with its structure also adapted using a Bayesian optimization algorithm. The WEANDB database was used to train and evaluate both models. The results showed remarkable performance, with an average accuracy 98 +/- 1.8% when using CNN from scratch. This model has significant implications for the ICU because it provides a reliable tool to enhance patient care by assisting clinicians in making timely and accurate decisions regarding weaning. This can potentially reduce the adverse outcomes associated with failed weaning events.

JTD Keywords: Bayesian optimization algorithm (boa, Continuous wavelet transform (cwt), Convolutional, Extubation, Failur, Intensive-care-unit, Neural network (cnn) from scratch, Respiratory-distress-syndrome, Time-frequency analysis (tfa), Weaning

Under intrauterine growth restriction (IUGR), abnormal attainment of the nutrients and oxygen by the fetus restricts the normal evolution of the prenatal causing in many cases high morbidity being one of the top-ten causes of neonatal death. The current gold standards in hospitals to detect this relevant problem is the clinical observation by echography, cardiotocography and Doppler. These qualitative techniques are not conclusive and requires risky invasive fetal scalp blood testing and/or amniocentesis. We developed micro-implantable multiparametric electrochemical sensors for measuring ischemia in real time in fetal tissue and vascular. This implantable technology is designed to continuous monitoring for an early detection of ischemia to avoid potential fetal injury. Two miniaturized electrochemical sensors were developed based on oxygen and pH detection. The sensors were optimized in vitro under controlled concentration, to assess the selectivity and sensitivity required. The sensors were then validated in vivo in the ewe fetus model, by means of their insertion in the muscle leg and inside the iliac artery of the fetus. Ischemia was achieved by gradually obstructing the umbilical cord to regulate the amount of blood reaching the fetus. An important challenge in fetal monitoring is the detection of low levels of oxygen and pH changes under ischemic conditions, requiring high sensitivity sensors. Significant differences were observed in both; pH and pO(2) sensors under changes from normoxia to hypoxia states in the fetus tissue and vascular with both sensors. Herein, we demonstrate the feasibility of the developed sensors for future fetal monitoring in medical applications.

JTD Keywords: electrochemical biosensor, implantable sensor, in vivo validation, ischemia detection, tissue and vascular monitoring, Animal experiment, Animal model, Animal tissue, Article, Blood-gases, Brain, Classification, Controlled study, Diagnosis, Doppler, Early diagnosis, Electrochemical analysis, Electrochemical biosensor, Ewe, Feasibility study, Female, Fetus, Fetus disease, Fetus monitoring, Gestational age, Hypoxemia, Iliac artery, Implantable sensor, In vivo validation, Intrauterine growth restriction, Intrauterine growth retardation, Ischemia detection, Leg muscle, Management, Nonhuman, Oxygen consumption, Ph, Ph and oxygen detection, Ph measurement, Process optimization, Sheep, Tissue and vascular monitoring, Umbilical-cord occlusion

Obstructive Sleep Apnea severity is commonly determined after a sleep polysomnographic study by the Apnea-Hypopnea Index (AHI). This index does not contain information about the duration of events, and weights apneas and hypopneas alike. Significant differences in disease severity have been reported in patients with the same AHI. The aim of this work was to study the effect of obstructive event type and duration on the subsequent oxygen desaturation (SaO2) by mixed-effects models. These models allow continuous and categorical independent variables and can model within-subject variability through random effects. The desaturation depth dSaO2, desaturation duration dtSaO2 and desaturation area dSaO2A were analyzed in the 2022 apneas and hypopneas of eight severe patients. A mixed-effects model was defined to account for the influence of event duration (AD), event type, and their interaction on SaO2 parameters. A two-step backward model reduction process was applied for random and fixed effects optimization. The optimum model obtained for dtSaO2 suggests an almost subject-independent proportion increase with AD, which did not significantly change in apneas as compared to hypopneas. The optimum model for dSaO2 reveals a significantly higher increase as a function of AD in apneas than hypopneas. Dependence of on event type and duration was different in every subject, and a subject-specific model could be obtained. The optimum model for SaO2A combines the effects of the other two. In conclusion, the proposed mixed-effects models for SaO2 parameters allow to study the effect of respiratory event duration and type, and to include repeated events within each subject. This simple model can be easily extended to include the contribution of other important factors such as patient severity, sleep stage, sleeping position, or the presence of arousals.

JTD Keywords: Biological system modeling, Sleep apnea, Mathematical model, Indexes, Reduced order systems, Optimization

Compensating physiological motion in the context of minimally invasive cardiac surgery has become an attractive issue since it outperforms traditional cardiac procedures offering remarkable benefits. Owing to space restrictions, computer vision techniques have proven to be the most practical and suitable solution. However, the lack of robustness and efficiency of existing methods make physiological motion compensation an open and challenging problem. This work focusses on increasing robustness and efficiency via exploration of the classes of l1- and l2-regularized optimization, emphasizing the use of explicit regularization. Both approaches are based on natural features of the heart using intensity information. Results pointed out the l1-regularized optimization class as the best since it offered the shortest computational cost, the smallest average error and it proved to work even under complex deformations.

JTD Keywords: Motion Compensation, Optimization, Regularization, Beating Heart Surgery, Ill-posed problem

Robotic-assisted minimally invasive surgery has demonstrated its benefits in comparison with traditional procedures. However, one of the major drawbacks of current robotic system approaches is the lack of force feedback. Apart from space restrictions, the main problems of using force sensors are their high cost and the biocompatibility. In this work a proposal based on Vision Based Force Measurement is presented, in which the deformation mapping of the tissue is obtained using the `2−Regularized Optimization class, and the force is estimated via a recurrent neural network that has as inputs the kinematic variables and the deformation mapping. Moreover, the capability of RNN for predicting time series is used in order to deal with tool occlusions. The highlights of this proposal, according to the results, are: knowledge of material properties are not necessary, there is no need of adding extra sensors and a good trade-off between accuracy and efficiency has been achieved.

JTD Keywords: Force estimation, Regularized optimization, Deformable tracking, Recurrent neural network

Heart motion compensation is a challenging problem within medical robotics and it is still considered an open research area due to the lack of robustness. As it can be formulated as an energy minimization problem, an optimization technique is needed. The selection of an adequate method has a significant impact over the global solution. For this reason, a new methodology is presented here for solving heart motion compensation in which the central topic is oriented to increase robustness with the goal of achieving a balance between efficiency and efficacy. Particularly, genetic algorithms are used as optimization technique since they can be adapted to any real application, complex and oriented to work in real-time problems.

JTD Keywords: Genetic Algorithms, Deformation, Stochastic Optimization, Beating Heart Surgery, Robotic Assisted Surgery

The sensitivity and selectivity of metal oxide (MOX) gas sensors change significantly when the sensors operate at different temperatures. While previous investigations have presented systematic approaches to optimize the operating temperature of a single MOX sensor, in this paper we present a methodology to select the optimal operating temperature of all the MOX sensors constituent of a gas sensor array based on the multivariate response of all the sensing elements. Our approach estimates a widely used Information Theory measure, the so-called Mutual Information (MI), which quantifies the amount of information that the state of one random variable (response of the gas sensor array) can provide from the state of another random variable representing the gas quality. More specifically, our methodology builds sensor models from experimental data to solve the technical problem of populating the joint probability distribution for the MI estimation. We demonstrate the relevance of our approach by maximizing the MI and selecting the best operating temperatures of a four-sensor array sampled at 94 different temperatures to optimize the discrimination task of ethanol, acetic acid, 2-butanone, and acetone. In addition to being applicable in principle to sensor arrays of any size, our approach gives precise information on the ability of the system to discriminate odors according to the temperature of the MOX sensors, for either the optimal set of temperatures or the temperatures that may render inefficient operation of the system itself.

JTD Keywords: MOX gas sensor, Temperature optimization, Limit of detection, Mutual Information, E-nose, Sensor array, Information Theory, Chemical sensing

In the trend towards miniaturization, a detector module containing multiple IR sensor channels is being built and characterized. In its final form it contains thermopiles, narrow band filters and Fresnel lenses. An important feature of such module is the assembly by flip-chip of the IR filters on top of the thermopiles. The performance of the filter-thermopile ensemble has been assessed by physical simulation and experiments and it has been optimized by the use of an empirically validated model. It has been found that integration of filters (or lenses) too close to the IR detector may lead to degraded performance due to thermal coupling. The impact and extent of this degradation has been thoroughly explored, being the main parameter the distance between the IR sensor and the filter. To avoid such detrimental effects a possibility is to set the device in vacuum conditions, obtaining an improved output response and avoiding the influence of the filters. Another way is to increase the solder joint height. Beyond a certain height, the filter is considered to be isolated from the thermopile.

JTD Keywords: Assembly, Infrared sensor, Infrared filter, Fresnel lenses, FEM simulation, Optimization