Classification of Sleep Quality and Aging as a Function of Brain Complexity: A Multiband Non-Linear EEG Analysis.

Understanding and classifying brain states as a function of sleep quality and age has important implications for developing lifestyle-based interventions involving sleep hygiene. Current studies use an algorithm that captures non-linear features of brain complexity to differentiate awake electroencephalography (EEG) states, as a function of age and sleep quality. Fifty-eight participants were assessed using the Pittsburgh Sleep Quality Inventory (PSQI) and awake resting state EEG. Groups were formed based on age and sleep quality (younger adults n = 24, mean age = 24.7 years, SD = 3.43, good sleepers n = 11; older adults n = 34, mean age = 72.87; SD = 4.18, good sleepers n = 9). Ten non-linear features were extracted from multiband EEG analysis to feed several classifiers followed by a leave-one-out cross-validation. Brain state complexity accurately predicted (i) age in good sleepers, with 75% mean accuracy (across all channels) for lower frequencies (alpha, theta, and delta) and 95% accuracy at specific channels (temporal, parietal); and (ii) sleep quality in older groups with moderate accuracy (70 and 72%) across sub-bands with some regions showing greater differences. It also differentiated younger good sleepers from older poor sleepers with 85% mean accuracy across all sub-bands, and 92% at specific channels. Lower accuracy levels (<50%) were achieved in predicting sleep quality in younger adults. The algorithm discriminated older vs. younger groups excellently and could be used to explore intragroup differences in older adults to predict sleep intervention efficiency depending on their brain complexity.

Shelf-Life Management and Ripening Assessment of 'Hass' Avocado (Persea americana) Using Deep Learning Approaches.

Avocado production is mostly confined to tropical and subtropical regions, leading to lengthy distribution channels that, coupled with their unpredictable post-harvest behavior, render avocados susceptible to significant loss and waste. To enhance the monitoring of 'Hass' avocado ripening, a data-driven tool was developed using a deep learning approach. This study involved monitoring 478 avocados stored in three distinct storage environments, using a 5-stage Ripening Index to classify each fruit's ripening phase based on their shared characteristics. These categories were paired with daily photographic records of the avocados, resulting in a database of labeled images. Two convolutional neural network models, AlexNet and ResNet-18, were trained using transfer learning techniques to identify distinct ripening indicators, enabling the prediction of ripening stages and shelf-life estimations for new unseen data. The approach achieved a final prediction accuracy of 88.8% for the ripening assessment, with 96.7% of predictions deviating by no more than half a stage from their actual classifications when considering the best side of the samples. The average shelf-life estimates based on the attributed classifications were within 0.92 days of the actual shelf-life, whereas the predictions made by the models had an average deviation of 0.96 days from the actual shelf-life.

Cardiovascular Diseases Diagnosis Using an ECG Multi-Band Non-Linear Machine Learning Framework Analysis.

BACKGROUND: cardiovascular diseases (CVDs), which encompass heart and blood vessel issues, stand as the leading cause of global mortality for many people. METHODS: the present study intends to perform discrimination between seven well-known CVDs (bundle branch block, cardiomyopathy, myocarditis, myocardial hypertrophy, myocardial infarction, valvular heart disease, and dysrhythmia) and one healthy control group, respectively, by feeding a set of machine learning (ML) models with 10 non-linear features extracted every 1 s from electrocardiography (ECG) lead signals of a well-known ECG database (PTB diagnostic ECG database) using multi-band analysis performed by discrete wavelet transform (DWT). The ML models were trained and tested using a leave-one-out cross-validation approach, assessing the individual and combined capabilities of features, per each lead or combined, to distinguish between pairs of study groups and for conducting a comprehensive all vs. all analysis. RESULTS: the Accuracy discrimination results ranged between 73% and 100%, the Recall between 68% and 100%, and the AUC between 0.42 and 1. CONCLUSIONS: the results suggest that our method is a good tool for distinguishing CVDs, offering significant advantages over other studies that used the same dataset, including a multi-class comparison group (all vs. all), a wider range of binary comparisons, and the use of classical non-linear analysis under ECG multi-band analysis performed by DWT.

Enhancing Health and Public Health through Machine Learning: Decision Support for Smarter Choices.

In recent years, the integration of Machine Learning (ML) techniques in the field of healthcare and public health has emerged as a powerful tool for improving decision-making processes [...].

COVID-19 Detection by Means of ECG, Voice, and X-ray Computerized Systems: A Review.

Since the beginning of 2020, Coronavirus Disease 19 (COVID-19) has attracted the attention of the World Health Organization (WHO). This paper looks into the infection mechanism, patient symptoms, and laboratory diagnosis, followed by an extensive assessment of different technologies and computerized models (based on Electrocardiographic signals (ECG), Voice, and X-ray techniques) proposed as a diagnostic tool for the accurate detection of COVID-19. The found papers showed high accuracy rate results, ranging between 85.70% and 100%, and F1-Scores from 89.52% to 100%. With this state-of-the-art, we concluded that the models proposed for the detection of COVID-19 already have significant results, but the area still has room for improvement, given the vast symptomatology and the better comprehension of individuals' evolution of the disease.

COVID-19 activity screening by a smart-data-driven multi-band voice analysis.

COVID-19 is a disease caused by the new coronavirus SARS-COV-2 which can lead to severe respiratory infections. Since its first detection it caused more than six million worldwide deaths. COVID-19 diagnosis non-invasive and low-cost methods with faster and accurate results are still needed for a fast disease control. In this research, 3 different signal analyses have been applied (per broadband, per sub-bands and per broadband & sub-bands) to Cough, Breathing & Speech signals of Coswara dataset to extract non-linear patterns (Energy, Entropies, Correlation Dimension, Detrended Fluctuation Analysis, Lyapunov Exponent & Fractal Dimensions) for feeding a XGBoost classifier to discriminate COVID-19 activity on its different stages. Classification accuracies ranged between 83.33% and 98.46% have been achieved, surpassing the state-of-art methods in some comparisons. It should be empathized the 98.46% of accuracy reached on pair Healthy Controls vs all COVID-19 stages. The results shows that the method may be adequate for COVID-19 diagnosis screening assistance.

Image Analysis Semi-Automatic System for Colony-Forming-Unit Counting.

BACKGROUND: Accurate quantitative analysis of microorganisms is recognized as an essential tool for gauging safety and quality in microbiology settings in a wide range of fields. The enumeration process of viable microorganisms via traditional culturing techniques are methodically convenient and cost-effective, conferring high applicability worldwide. However, manual counting can be time-consuming, laborious and imprecise. Furthermore, particular cases require an urgent and accurate response for effective processing. METHODS: To reduce time limitations and discrepancies, this work introduces an image processing method capable of semi-automatically quantifying the number of colony forming units (CFUs). This rapid enumeration technique enables the technician to provide an expeditious assessment of the microbial load of a given sample. To test and validate the system, three bacterial species were cultured, and a labeled database was created, with subsequent image acquisition. RESULTS: The system demonstrated acceptable classification measures; the mean values of Accuracy, Recall and F-measure were: (1) 95%, 95% and 0.95 for E. coli; (2) 91%, 91% and 0.90 for P. aeruginosa; and (3) 84%, 86% and 0.85 for S. aureus. CONCLUSIONS: Evidence related to the time-saving potential of the system was achieved; the time spent on quantification tasks of plates with a high number of colonies might be reduced to a half and occasionally to a third.

Smart-Data-Driven System for Alzheimer Disease Detection through Electroencephalographic Signals.

BACKGROUND: Alzheimer's Disease (AD) stands out as one of the main causes of dementia worldwide and it represents around 65% of all dementia cases, affecting mainly elderly people. AD is composed of three evolutionary stages: Mild Cognitive Impairment (MCI), Mild and Moderate AD (ADM) and Advanced AD (ADA). It is crucial to create a tool for assisting AD diagnosis in its early stages with the aim of halting the disease progression. METHODS: The main purpose of this study is to develop a system with the ability of differentiate each disease stage by means of Electroencephalographic Signals (EEG). Thereby, an EEG nonlinear multi-band analysis by Wavelet Packet was performed enabling to extract several features from each study group. Classic Machine Learning (ML) and Deep Learning (DL) methods have been used for data classification per EEG channel. RESULTS: The maximum accuracies obtained were 78.9% (Healthy controls (C) vs. MCI), 81.0% (C vs. ADM), 84.2% (C vs. ADA), 88.9% (MCI vs. ADM), 93.8% (MCI vs. ADA), 77.8% (ADM vs. ADA) and 56.8% (All vs. All). CONCLUSIONS: The proposed method outperforms previous studies with the same database by 2% in binary comparison MCI vs. ADM and central and parietal brain regions revealed abnormal activity as AD progresses.

Validation of Psychophysiological Measures for Caffeine Oral Films Characterization by Machine Learning Approaches.

(1) Background: The oral films are a new delivery system that can carry several molecules, such as neuromodulator molecules, including caffeine. These delivery systems have been developed and characterized by pharmacokinetics assays. However, new methodologies, such as psychophysiological measures, can complement their characterization. This study presents a new protocol with psychophysiological parameters to characterize the oral film delivery systems based on a caffeine model. (2) Methods: Thirteen volunteers (61.5% females and 38.5% males) consumed caffeine oral films and placebo oral films (in different moments and without knowing the product). Electrocardiogram (ECG), electrodermal (EDA), and respiratory frequency (RF) data were monitored for 45 min. For the data analysis, the MATLAB environment was used to develop the analysis program. The ECG, EDA, and RF signals were digitally filtered and processed, using a windowing process, for feature extraction and an energy mean value for 5 min segments. Then, the data were computed and presented to the entries of a set of Machine Learning algorithms. Finally, a data statistical analysis was carried out using SPSS. (3) Results: Compared with placebo, caffeine oral films led to a significant increase in power energy in the signal spectrum of heart rate, skin conductance, and respiratory activity. In addition, the ECG time-series power energy activity revealed a better capacity to detect caffeine activity over time than the other physiological modalities. There was no significant change for the female or male gender. (4) Conclusions: The protocol developed, and the psychophysiological methodology used to characterize the delivery system profile were efficient to characterize the drug delivery profile of the caffeine. This is a non-invasive, cheap, and easy method to apply, can be used to determine the neuromodulator drugs delivery profile, and can be implemented in the future.

Distinction of Different Colony Types by a Smart-Data-Driven Tool.

BACKGROUND: Colony morphology (size, color, edge, elevation, and texture), as observed on culture media, can be used to visually discriminate different microorganisms. METHODS: This work introduces a hybrid method that combines standard pre-trained CNN keras models and classical machine-learning models for supporting colonies discrimination, developed in Petri-plates. In order to test and validate the system, images of three bacterial species (Escherichia coli, Pseudomonas aeruginosa, and Staphylococcus aureus) cultured in Petri plates were used. RESULTS: The system demonstrated the following Accuracy discrimination rates between pairs of study groups: 92% for Pseudomonas aeruginosa vs. Staphylococcus aureus, 91% for Escherichia coli vs. Staphylococcus aureus and 84% Escherichia coli vs. Pseudomonas aeruginosa. CONCLUSIONS: These results show that combining deep-learning models with classical machine-learning models can help to discriminate bacteria colonies with good accuracy ratios.

Protein changes as robust signatures of fish chronic stress: a proteomics approach to fish welfare research.

BACKGROUND: Aquaculture is a fast-growing industry and therefore welfare and environmental impact have become of utmost importance. Preventing stress associated to common aquaculture practices and optimizing the fish stress response by quantification of the stress level, are important steps towards the improvement of welfare standards. Stress is characterized by a cascade of physiological responses that, in-turn, induce further changes at the whole-animal level. These can either increase fitness or impair welfare. Nevertheless, monitorization of this dynamic process has, up until now, relied on indicators that are only a snapshot of the stress level experienced. Promising technological tools, such as proteomics, allow an unbiased approach for the discovery of potential biomarkers for stress monitoring. Within this scope, using Gilthead seabream (Sparus aurata) as a model, three chronic stress conditions, namely overcrowding, handling and hypoxia, were employed to evaluate the potential of the fish protein-based adaptations as reliable signatures of chronic stress, in contrast with the commonly used hormonal and metabolic indicators. RESULTS: A broad spectrum of biological variation regarding cortisol and glucose levels was observed, the values of which rose higher in net-handled fish. In this sense, a potential pattern of stressor-specificity was clear, as the level of response varied markedly between a persistent (crowding) and a repetitive stressor (handling). Gel-based proteomics analysis of the plasma proteome also revealed that net-handled fish had the highest number of differential proteins, compared to the other trials. Mass spectrometric analysis, followed by gene ontology enrichment and protein-protein interaction analyses, characterized those as humoral components of the innate immune system and key elements of the response to stimulus. CONCLUSIONS: Overall, this study represents the first screening of more reliable signatures of physiological adaptation to chronic stress in fish, allowing the future development of novel biomarker models to monitor fish welfare.

Live-cell imaging of p53 interactions using a novel Venus-based bimolecular fluorescence complementation system.

p53 plays an important role in regulating a wide variety of cellular processes, such as cell cycle arrest and/or apoptosis. Dysfunction of p53 is frequently associated with several pathologies, such as cancer and neurodegenerative diseases. In recent years substantial progress has been made in developing novel p53-activating molecules. Importantly, modulation of p53 interaction with its main inhibitor, Mdm2, has been highlighted as a promising therapeutic target. In this regard, bimolecular fluorescence complementation (BiFC) analysis, by providing direct visualization of protein interactions in living cells, offers a straightforward method to identify potential modulators of protein interactions. In this study, we developed a simple and robust Venus-based BiFC system to screen for modulators of p53-p53 and p53-Mdm2 interactions in live mammalian cells. We used nutlin-3, a well-known disruptor of p53-Mdm2 interaction, to validate the specificity of the assay. The reduction of BiFC signal mediated by nutlin-3 was correlated with an increase in Puma transactivation, PARP cleavage, and cell death. Finally, this novel BiFC approach was exploited to identify potential modulators of p53-Mdm2 complex formation among a commercially available chemical library of 33 protein phosphatase inhibitors. Our results constitute "proof-of-concept" that this model has strong potential as an alternative to traditional target-based drug discovery strategies. Identification of new modulators of p53-p53 and p53-Mdm2 interactions will be useful to achieve synergistic drug efficacy with currently used anti-tumor therapies.