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

The optimal extubating moment is still a challenge in clinical practice. Respiratory pattern variability analysis in patients assisted through mechanical ventilation to identify this optimal moment could contribute to this process. This work proposes the analysis of this variability using several time series obtained from the respiratory flow and electrocardiogram signals, applying techniques based on artificial intelligence. 154 patients undergoing the extubating process were classified in three groups: successful group, patients who failed during weaning process, and patients who after extubating failed before 48 hours and need to reintubated. Power Spectral Density and time-frequency domain analysis were applied, computing Discrete Wavelet Transform. A new Q index was proposed to determine the most relevant parameters and the best decomposition level to discriminate between groups. Forward selection and bidirectional techniques were implemented to reduce dimensionality. Linear Discriminant Analysis and Neural Networks methods were implemented to classify these patients. The best results in terms of accuracy were, 84.61 ± 3.1% for successful versus failure groups, 86.90 ± 1.0% for successful versus reintubated groups, and 91.62 ± 4.9% comparing the failure and reintubated groups. Parameters related to Q index and Neural Networks classification presented the best performance in the classification of these patients.

JTD Keywords: Mechanical ventilation, Neural networks, Wavelet transform, Weaning

Biological cognition is based on the ability to autonomously acquire knowledge, or epistemic autonomy. Such self-supervision is largely absent in artificial neural networks (ANN) because they depend on externally set learning criteria. Yet training ANN using error backpropagation has created the current revolution in artificial intelligence, raising the question of whether the epistemic autonomy displayed in biological cognition can be achieved with error backpropagation-based learning. We present evidence suggesting that the entorhinal–hippocampal complex combines epistemic autonomy with error backpropagation. Specifically, we propose that the hippocampus minimizes the error between its input and output signals through a modulatory counter-current inhibitory network. We further discuss the computational emulation of this principle and analyze it in the context of autonomous cognitive systems. © 2021 Elsevier Ltd

JTD Keywords: computational model, dentate gyrus, error backpropagation, granule cells, grid cells, hippocampus, inhibition, input, neural-networks, neurons, transformation, Artificial intelligence, Artificial neural network, Back propagation, Backpropagation, Brain, Cognitive systems, Counter current, Error back-propagation, Error backpropagation, Errors, Expressing interneurons, Hippocampal complex, Hippocampus, Human experiment, Input and outputs, Learning, Mammal, Mammalian hippocampus, Mammals, Neural networks, Nonhuman, Review, Self-supervised learning

Mapping the biochemical composition of eukaryotic cells without the use of exogenous labels is a long-sought objective in cell biology. Recently, it has been shown that composition maps on dry single bacterial cells with nanoscale spatial resolution can be inferred from quantitative nanoscale dielectric constant maps obtained with the scanning dielectric microscope. Here, it is shown that this approach can also be applied to the much more challenging case of fixed and dry eukaryotic cells, which are highly heterogeneous and show micrometric topographic variations. More importantly, it is demonstrated that the main bottleneck of the technique (the long computation times required to extract the nanoscale dielectric constant maps) can be shortcut by using supervised neural networks, decreasing them from weeks to seconds in a wokstation computer. This easy-to-use data-driven approach opens the door for in situ and on-the-fly label free nanoscale composition mapping of eukaryotic cells with scanning dielectric microscopy. © 2021 The Authors. Small Methods published by Wiley-VCH GmbH

JTD Keywords: eukaryotic cells, label-free mapping, machine learning, nanoscale, scanning dielectric microscopy, Biochemical composition, Cells, Constant, Cytology, Data-driven approach, Dielectric forces, Dielectric materials, Eukaryotic cells, Label-free mapping, Machine learning, Mapping, Microscopy, atomic force, Nanoscale, Nanoscale composition, Nanoscale spatial resolution, Nanotechnology, Scanning, Scanning dielectric microscopy, Supervised neural networks

The hippocampal formation displays a wide range of physiological responses to different spatial manipulations of the environment. However, very few attempts have been made to identify core computational principles underlying those hippocampal responses. Here, we capitalize on the observation that the entorhinal-hippocampal complex (EHC) forms a closed loop and projects inhibitory signals “countercurrent” to the trisynaptic pathway to build a self-supervised model that learns to reconstruct its own inputs by error backpropagation. The EHC is then abstracted as an autoencoder, with the hidden layers acting as an information bottleneck. With the inputs mimicking the firing activity of lateral and medial entorhinal cells, our model is shown to generate place cells and to respond to environmental manipulations as observed in rodent experiments. Altogether, we propose that the hippocampus builds conjunctive compressed representations of the environment by learning to reconstruct its own entorhinal inputs via gradient descent.

JTD Keywords: cognitive neuroscience, grid cells, long-term, networks, neural networks, novelty, oscillations, pattern separation, region, representation, working-memory, Cognitive neuroscience, Neural networks, Rat dentate gyrus, Systems neuroscience

Providing force feedback as relevant information in current Robot-Assisted Minimally Invasive Surgery systems constitutes a technological challenge due to the constraints imposed by the surgical environment. In this context, force estimation techniques represent a potential solution, enabling to sense the interaction forces between the surgical instruments and soft-tissues. Specifically, if visual feedback is available for observing soft-tissues’ deformation, this feedback can be used to estimate the forces applied to these tissues. To this end, a force estimation model, based on Convolutional Neural Networks and Long-Short Term Memory networks, is proposed in this work. This model is designed to process both, the spatiotemporal information present in video sequences and the temporal structure of tool data (the surgical tool-tip trajectory and its grasping status). A series of analyses are carried out to reveal the advantages of the proposal and the challenges that remain for real applications. This research work focuses on two surgical task scenarios, referred to as pushing and pulling tissue. For these two scenarios, different input data modalities and their effect on the force estimation quality are investigated. These input data modalities are tool data, video sequences and a combination of both. The results suggest that the force estimation quality is better when both, the tool data and video sequences, are processed by the neural network model. Moreover, this study reveals the need for a loss function, designed to promote the modeling of smooth and sharp details found in force signals. Finally, the results show that the modeling of forces due to pulling tasks is more challenging than for the simplest pushing actions.

JTD Keywords: Convolutional neural networks, Force estimation, LSTM networks, Robotic surgery

This book constitutes the proceedings of the 8th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2019, held in Nara, Japan, in July 2019. The 26 full and 16 short papers presented in this volume were carefully reviewed and selected from 45 submissions. They deal with research on novel life-like technologies inspired by the scientific investigation of biological systems, biomimetics, and research that seeks to interface biological and artificial systems to create biohybrid systems.

JTD Keywords: Artificial intelligence, Biomimetics, Computer architecture, Human robot interaction, Human-Computer Interaction (HCI), Humanoid robot, Image processing, Learning algorithms, Mobile robots, Multipurpose robots, Neural networks, Quadruped robots, Reinforcement learning, Robot learning, Robotics, Robots, Sensor, Sensors, Swarm robotics, User interfaces

The quality and composition of bitter orange essential oils (EOs) strongly depend on the ripening stage of the citrus fruit. The concentration of volatile compounds and consequently its organoleptic perception varies. While this can be detected by trained humans, we propose an objective approach for assessing the bitter orange from the volatile composition of their EO. The method is based on the combined use of headspace gas chromatography–mass spectrometry (HS-GC-MS) and artificial neural networks (ANN) for predictive modeling. Data obtained from the analysis of HS-GC-MS were preprocessed to select relevant peaks in the total ion chromatogram as input features for ANN. Results showed that key volatile compounds have enough predictive power to accurately classify the EO, according to their ripening stage for different applications. A sensitivity analysis detected the key compounds to identify the ripening stage. This study provides a novel strategy for the quality control of bitter orange EO without subjective methods.

JTD Keywords: Bitter orange essential oil, Headspace gas chromatography–mass spectrometry, Artificial neural network, Foodomics, Chemometrics, Feature selection

Machine Learning algorithms (and in particular Reinforcement Learning (RL)) have proved very successful in recent years. These have managed to achieve super-human performance in many different tasks, from video-games to board-games and complex cognitive tasks such as path-planning or Theory of Mind (ToM) on artificial agents. Nonetheless, this super-human performance is also super-artificial. Despite some metrics are better than what a human can achieve (i.e. cumulative reward), in less common metrics (i.e. time to learning asymptote) the performance is significantly worse. Moreover, the means by which those are achieved fail to extend our understanding of the human or mammal brain. Moreover, most approaches used are based on black-box optimization, making any comparison beyond performance (e.g. at the architectural level) difficult. In this position paper, we review the origins of reinforcement learning and propose its extension with models of learning derived from fear and avoidance behaviors. We argue that avoidance-based mechanisms are required when training on embodied, situated systems to ensure fast and safe convergence and potentially overcome some of the current limitations of the RL paradigm.

JTD Keywords: Avoidance, Neural networks, Reinforcement learning

This book constitutes the proceedings of the 7th International Conference on Biomimetic and Biohybrid Systems, Living Machines 2018, held in Paris, France, in July 2018. The 40 full and 18 short papers presented in this volume were carefully reviewed and selected from 60 submissions. The theme of the conference targeted at the intersection of research on novel life-like technologies inspired by the scientific investigation of biological systems, biomimetics, and research that seeks to interface biological and artificial systems to create biohybrid systems.

JTD Keywords: Artificial neural network, Bio-actuators, Bio-robotics, Biohybrid systems, Biomimetics, Bipedal robots, Earthoworm-like robots, Robotics, Decision-making, Tactile sensing, Soft robots, Locomotion, Insects, Sensors, Actuators, Robots, Artificial intelligence, Neural networks, Motion planning, Learning algorithms

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

The process of weaning from mechanical ventilation is one of the challenges in intensive care units. 66 patients under extubation process (T-tube test) were studied: 33 patients with successful trials and 33 patients who failed to maintain spontaneous breathing and were reconnected. Each patient was characterized using 7 time series from respiratory signals, and for each serie was evaluated the discrete wavelet transform. It trains a neural network for discriminating between patients from the two groups.

JTD Keywords: discrete wavelet transforms, neural nets, patient treatment, pneumodynamics, time series, ventilation, T-tube test, discrete wavelet transform, extubation process, intensive care units, mechanical ventilation, moment of disconnection, neural network, patients, respiratory signals, spontaneous breathing, time series, weaning, Mechanical Ventilation, Neural Networks, Time series from respiratory signals, Wavelet Transform

Statistical analysis, power spectral density, and Lempel Ziv complexity, are used in a multi-parameter approach to analyze four temporal series obtained from the Electrocardiographic and Respiratory Flow signals of 126 patients on weaning trials. In which, 88 patients belong to successful group (SG), and 38 patients belong to failure group (FG), i.e. failed to maintain spontaneous breathing during trial. It was found that mean values of cardiac inter-beat and breath durations give higher values for SG than for FG; Kurtosis coefficient of the spectrum of the rapid shallow breathing index is higher for FG; also Lempel Ziv complexity mean values associated with the respiratory flow signal are bigger for FG. Patients were then classified with a pattern recognition neural network, obtaining 80% of correct classifications (81.6% for FG and 79.5% for SG).

JTD Keywords: Electrocardiography, Medical signal processing, Neural nets, Pattern recognition, Pneumodynamics, Signal classification, Statistical analysis, ECG, Kurtosis coefficient, Lempel Ziv complexity, Breath durations, Cardiac interbeat durations, Electrocardiography, Multiparameter analysis, Pattern recognition neural network, Power spectral density, Respiratory flow signals, Signal classification, Spontaneous breathing, Statistical analysis, Weaning trials