Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning.

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Learning algorithms estimate pose and detect motor anomalies in flies exposed to minimal doses of a toxicant.

Pesticide exposure, even at low doses, can have detrimental effects on ecosystems. This study aimed at validating the use of machine learning for recognizing motor anomalies, produced by minimal insecticide exposure on a model insect species. The Mediterranean fruit fly, Ceratitis capitata (Diptera: Tephritidae), was exposed to food contaminated with low concentrations of Carlina acaulis essential oil (EO). A deep learning approach enabled fly pose estimation on video recordings in a custom-built arena. Five machine learning algorithms were trained on handcrafted features, extracted from the predicted pose, to distinguish treated individuals. Random Forest and K-Nearest Neighbor algorithms best performed, with an area under the receiver operating characteristic (ROC) curve of 0.75 and 0.73, respectively. Both algorithms achieved an accuracy of 0.71. Results show the machine learning potential for detecting sublethal effects arising from insecticide exposure on fly motor behavior, which could also affect other organisms and environmental health.

Investigating automated regression models for estimating left ventricular ejection fraction levels in heart failure patients using circadian ECG features.

Heart Failure (HF) significantly impacts approximately 26 million people worldwide, causing disruptions in the normal functioning of their hearts. The estimation of left ventricular ejection fraction (LVEF) plays a crucial role in the diagnosis, risk stratification, treatment selection, and monitoring of heart failure. However, achieving a definitive assessment is challenging, necessitating the use of echocardiography. Electrocardiogram (ECG) is a relatively simple, quick to obtain, provides continuous monitoring of patient's cardiac rhythm, and cost-effective procedure compared to echocardiography. In this study, we compare several regression models (support vector machine (SVM), extreme gradient boosting (XGBOOST), gaussian process regression (GPR) and decision tree) for the estimation of LVEF for three groups of HF patients at hourly intervals using 24-hour ECG recordings. Data from 303 HF patients with preserved, mid-range, or reduced LVEF were obtained from a multicentre cohort (American and Greek). ECG extracted features were used to train the different regression models in one-hour intervals. To enhance the best possible LVEF level estimations, hyperparameters tuning in nested loop approach was implemented (the outer loop divides the data into training and testing sets, while the inner loop further divides the training set into smaller sets for cross-validation). LVEF levels were best estimated using rational quadratic GPR and fine decision tree regression models with an average root mean square error (RMSE) of 3.83% and 3.42%, and correlation coefficients of 0.92 (p<0.01) and 0.91 (p<0.01), respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm demonstrated to be the lowest RMSE values between the actual and predicted LVEF levels. The findings could potentially lead to the development of an automated screening system for patients with coronary artery disease (CAD) by using the best measurement timings during their circadian cycles.

Automated image-based analysis unveils acute effects due to sub-lethal pesticide doses exposure.

Pesticides are still abused in modern agriculture. The effects of their exposure to even sub-lethal doses can be detrimental to ecosystem stability and human health. This work aims to validate the use of machine learning techniques for recognizing motor abnormalities and to assess any effect post-exposure to a minimal dosage of these substances on a model organism, gaining insights into potential risks for human health. The test subject was the Mediterranean fruit fly, Ceratitis capitata (Wiedemann) (Diptera: Tephritidae), exposed to food contaminated with the LC30 of Carlina acaulis essential oil. A deep learning approach enabled the pose estimation within an arena. Statistical analysis highlighted the most significant features between treated and untreated groups. Based on this analysis, two learning-based algorithms, Random Forest (RF) and XGBoost were employed. The results were compared through different metrics. RF algorithm generated a model capable of distinguishing treated subjects with an area under the receiver operating characteristic curve of 0.75 and an accuracy of 0.71. Through an image-based analysis, this study revealed acute effects due to minimal pesticide doses. So, even small amounts of these biocides drifted far from distribution areas may negatively affect the environment and humans.

Organisms as sensors in biohybrid entities as a novel tool for in-field aquatic monitoring.

Rapidly intensifying global warming and water pollution calls for more efficient and continuous environmental monitoring methods. Biohybrid systems connect mechatronic components to living organisms and this approach can be used to extract data from the organisms. Compared to conventional monitoring methods, they allow for a broader data collection over long periods, minimizing the need for sampling processes and human labour. We aim to develop a methodology for creating various bioinspired entities, here referred to as 'biohybrids', designed for long-term aquatic monitoring. Here, we test several aspects of the development of the biohybrid entity: autonomous power source, lifeform integration and partial biodegradability. An autonomous power source was supplied by microbial fuel cells which exploit electron flows from microbial metabolic processes in the sediments. Here, we show that by stacking multiple cells, sufficient power can be supplied. We integrated lifeforms into the developed bioinspired entity which includes organisms such as the zebra musselDreissena polymorphaand water fleaDaphniaspp. The setups developed allowed for observing their stress behaviours. Through this, we can monitor changes in the environment in a continuous manner. The further development of this approach will allow for extensive, long-term aquatic data collection and create an early-warning monitoring system.

Non-invasive technologies for heart failure, systolic and diastolic dysfunction modeling: a scoping review.

The growing global prevalence of heart failure (HF) necessitates innovative methods for early diagnosis and classification of myocardial dysfunction. In recent decades, non-invasive sensor-based technologies have significantly advanced cardiac care. These technologies ease research, aid in early detection, confirm hemodynamic parameters, and support clinical decision-making for assessing myocardial performance. This discussion explores validated enhancements, challenges, and future trends in heart failure and dysfunction modeling, all grounded in the use of non-invasive sensing technologies. This synthesis of methodologies addresses real-world complexities and predicts transformative shifts in cardiac assessment. A comprehensive search was performed across five databases, including PubMed, Web of Science, Scopus, IEEE Xplore, and Google Scholar, to find articles published between 2009 and March 2023. The aim was to identify research projects displaying excellence in quality assessment of their proposed methodologies, achieved through a comparative criteria-based rating approach. The intention was to pinpoint distinctive features that differentiate these projects from others with comparable objectives. The techniques identified for the diagnosis, classification, and characterization of heart failure, systolic and diastolic dysfunction encompass two primary categories. The first involves indirect interaction with the patient, such as ballistocardiogram (BCG), impedance cardiography (ICG), photoplethysmography (PPG), and electrocardiogram (ECG). These methods translate or convey the effects of myocardial activity. The second category comprises non-contact sensing setups like cardiac simulators based on imaging tools, where the manifestations of myocardial performance propagate through a medium. Contemporary non-invasive sensor-based methodologies are primarily tailored for home, remote, and continuous monitoring of myocardial performance. These techniques leverage machine learning approaches, proving encouraging outcomes. Evaluation of algorithms is centered on how clinical endpoints are selected, showing promising progress in assessing these approaches' efficacy.

How aggressive interactions with biomimetic agents optimize reproductive performances in mass-reared males of the Mediterranean fruit fly.

Mass-rearing procedures of insect species, often used in biological control and Sterile Insect Technique, can reduce the insects competitiveness in foraging, dispersal, and mating. The evocation of certain behaviours responsible to induce specific neuroendocrine products may restore or improve the competitiveness of mass-reared individuals. Herein, we used a mass-reared strain of Ceratitis capitata as model organism. C. capitata is a polyphagous pest exhibiting territorial displays that are closely related to its reproductive performance. We tested if the behaviour of C. capitata males could be altered by hybrid aggressive interactions with a conspecific-mimicking robotic fly, leading to more competitive individuals in subsequent mating events. Aggressive interactions with the robotic fly had a notable effect on subsequent courtship and mating sequences of males that performed longer courtship displays compared to naïve individuals. Furthermore, previous interactions with the robotic fly produced a higher mating success of males. Reproductive performances of C. capitata males may be improved by specific octopaminergic neurones activated during previous aggressive interactions with the robotic fly. This study adds fundamental knowledge on the potential role of specific neuro-behavioural processes in the ecology of tephritid species and paves the way to innovative biotechnological control methods based on robotics and bionics.

Turning earthworms into moonworms: Earthworms colonization of lunar regolith as a bioengineering approach supporting future crop growth in space.

The earthworms beneficial effects on soils may be promising to improve lunar soil fertility, enabling the use of local substrates for space farming. Herein, we investigated the effects of the lunar regolith simulant (LHS-1) at different concentrations in cow manure mixtures on the survival and fitness of Eisenia fetida. During 14 and 60-day experiments, although E. fetida showed an increased mortality with LHS-1 alone, most of the population survived. More numerous tunnels were observed when exposed to the higher concentrations of LHS-1 (poor in nutrients for earthworms). This may be related to an increased mobility for food search. The cocoons production was not affected by different substrate treatments, except for the highest concentration of LHS-1. No effects of different LHS-1 concentrations on the amount of ingested substrate were recorded. This study shows that E. fetida can potentially colonize lunar regolith representing a future valuable biological tool for supporting crops growth on the Moon.

A Deep-Learning-Based Detection Approach for the Identification of Insect Species of Economic Importance.

Artificial Intelligence (AI) and automation are fostering more sustainable and effective solutions for a wide spectrum of agricultural problems. Pest management is a major challenge for crop production that can benefit from machine learning techniques to detect and monitor specific pests and diseases. Traditional monitoring is labor intensive, time demanding, and expensive, while machine learning paradigms may support cost-effective crop protection decisions. However, previous studies mainly relied on morphological images of stationary or immobilized animals. Other features related to living animals behaving in the environment (e.g., walking trajectories, different postures, etc.) have been overlooked so far. In this study, we developed a detection method based on convolutional neural network (CNN) that can accurately classify in real-time two tephritid species (Ceratitis capitata and Bactrocera oleae) free to move and change their posture. Results showed a successful automatic detection (i.e., precision rate about 93%) in real-time of C. capitata and B. oleae adults using a camera sensor at a fixed height. In addition, the similar shape and movement patterns of the two insects did not interfere with the network precision. The proposed method can be extended to other pest species, needing minimal data pre-processing and similar architecture.

Any colour you like: fish interacting with bioinspired robots unravel mechanisms promoting mixed phenotype aggregations.

Collective behaviours in homogeneous shoals provide several benefits to conspecifics, although mixed-species aggregations have been reported to often occur. Mixed aggregations may confer several beneficial effects such as antipredator and foraging advantages. However, the mechanisms promoting phenotypically heterogeneous fish aggregations have been poorly explored so far. Herein, the neon tetraParacheirodon innesiwas selected as the ideal model organism to test the role of visible phenotypic traits in promoting fish shoaling. Robotic fish replicas of different colours, but with a morphology inspired byP. innesi, were developed to test the affiliation behaviour of neon tetra individuals towards fish replicas with different phenotypic traits.P. innesiindividuals showed a decreasing preference in shoaling with the biomimetic, the blue, the red, and the grey replicas. This could be due to the greater visibility of the blue colour even in dark conditions. Furthermore, an increased reddening of the livery is often caused by physiological processes related to a nonoptimal behavioural status. The time spent in shoaling with each fish replica was strongly influenced by different ecological contexts. The longest shoaling duration was observed when a biomimetic predator was present, while the shortest shoaling duration was recorded in the presence of food. This confirms the hypothesis that heterogeneous shoals are promoted by the antipredator benefits, and reduced by competition. This study allowed us to understand basic features of the behavioural ecology favouring heterogeneous aggregations in shoaling fish, and provided a novel paradigm for biohybrid robotics.

Linking Alzheimer's Disease and Type 2 Diabetes: Characterization and Inhibition of Cytotoxic Aß and IAPP Hetero-Aggregates.

The cytotoxic self-aggregation of ß-amyloid (Aß) peptide and islet amyloid polypeptide (IAPP) is implicated in the pathogenesis of Alzheimer's disease (AD) and Type 2 diabetes (T2D), respectively. Increasing evidence, particularly the co-deposition of Aß and IAPP in both brain and pancreatic tissues, suggests that Aß and IAPP cross-interaction may be responsible for a pathological link between AD and T2D. Here, we examined the nature of IAPP-Aß40 co-aggregation and its inhibition by small molecules. In specific, we characterized the kinetic profiles, morphologies, secondary structures and toxicities of IAPP-Aß40 hetero-assemblies and compared them to those formed by their homo-assemblies. We demonstrated that monomeric IAPP and Aß40 form stable hetero-dimers and hetero-assemblies that further aggregate into ß-sheet-rich hetero-aggregates that are toxic (cell viability <50%) to both PC-12 cells, a neuronal cell model, and RIN-m5F cells, a pancreatic cell model for ß-cells. We then selected polyphenolic candidates to inhibit IAPP or Aß40 self-aggregation and examined the inhibitory effect of the most potent candidate on IAPP-Aß40 co-aggregation. We demonstrated that epigallocatechin gallate (EGCG) form inter-molecular hydrogen bonds with each of IAPP and Aß40. We also showed that EGCG reduced hetero-aggregate formation and resulted in lower ß-sheets content and higher unordered structures in IAPP-Aß40-EGCG samples. Importantly, we showed that EGCG is highly effective in reducing the toxicity of IAPP-Aß40 hetero-aggregates on both cell models, specifically at concentrations that are equivalent to or are 2.5-fold higher than the mixed peptide concentrations. To the best of our knowledge, this is the first study to report the inhibition of IAPP-Aß40 co-aggregation by small molecules. We conclude that EGCG is a promising candidate to prevent co-aggregation and cytotoxicity of IAPP-Aß40, which in turn, contribute to the pathological link between AD and T2D.

Assessing Respiratory Activity by Using IMUs: Modeling and Validation.

This study aimed to explore novel inertial measurement unit (IMU)-based strategies to estimate respiratory parameters in healthy adults lying on a bed while breathing normally. During the experimental sessions, the kinematics of the chest wall were contemporaneously collected through both a network of 9 IMUs and a set of 45 uniformly distributed reflective markers. All inertial kinematics were analyzed to identify a minimum set of signals and IMUs whose linear combination best matched the tidal volume measured by optoelectronic plethysmography. The resulting models were finally tuned and validated through a leave-one-out cross-validation approach to assess the extent to which they could accurately estimate a set of respiratory parameters related to three trunk compartments. The adopted methodological approach allowed us to identify two different models. The first, referred to as Model 1, relies on the 3D acceleration measured by three IMUs located on the abdominal compartment and on the lower costal margin. The second, referred to as Model 2, relies on only one component of the acceleration measured by two IMUs located on the abdominal compartment. Both models can accurately estimate the respiratory rate (relative error < 1.5%). Conversely, the duration of the respiratory phases and the tidal volume can be more accurately assessed by Model 2 (relative error < 5%) and Model 1 (relative error < 5%), respectively. We further discuss possible approaches to overcome limitations and improve the overall accuracy of the proposed approach.

Hydrogen phosphate selectively induces MDA MB 231 triple negative breast cancer cell death in vitro.

Phosphate ions are the most abundant anions inside the cells, and they are increasingly gaining attention as key modulators of cellular function and gene expression. However, little is known about the effect of inorganic phosphate ions on cancer cells, particularly breast cancer cells. Here, we investigated the toxicity of different phosphate compounds to triple-negative human breast cancer cells, particularly, MDA-MB-231, and compared it to that of human monocytes, THP-1. We found that, unlike dihydrogen phosphate (H2PO4-), hydrogen phosphate (HPO42-) at 20 mM or lower concentrations induced breast cancer cell death more than immune cell death, mainly via apoptosis. We correlate this effect to the fact that phosphate in the form of HPO42- raises pH levels to alkaline levels which are not optimum for transport of phosphate into cancer cells. The results in this study highlight the importance of further exploring hydrogen phosphate (HPO42-) as a potential therapeutic for the treatment of breast cancer.

Lateralization of Courtship Traits Impacts Pentatomid Male Mating Success-Evidence from Field Observations.

Lateralization has been documented in many insect species, but limited information on courtship and mating lateralization in wild conditions is available. We conducted field investigation on the courtship and mating behavior of the neem bug, Halys dentatus, a polyphagous insect mainly infesting Azadirachta indica, with particular attention to lateralization of mating displays. We investigated the presence of population-level behavioral asymmetries during H. dentatus sexual interactions and their influence on male mating success. Two lateralized traits were found: left or right-biased male approaches to the female and left or right-biased male turning displays. Males approaching females from their left side were mainly right-biased in the 180° turning display, and males that approached females from their right side were mainly left-biased. Right-biased males by turning 180° to carry out end-to-end genital contact, performed a lower number of copulation attempts, thus starting copula earlier than left-biased males. Mating success was higher when males approached the left side of females during sexual interactions. A higher number of successful mating interactions was observed in right-biased males when turning 180°. Our results add useful knowledge on the reproductive behavior of H. dentatus in the field, with potential applications for identifying useful benchmarks to monitor the quality of individuals mass-reared for pest control purposes over time.

Nanocomposite Conductive Bioinks Based on Low-Concentration GelMA and MXene Nanosheets/Gold Nanoparticles Providing Enhanced Printability of Functional Skeletal Muscle Tissues.

There is a growing need to develop novel well-characterized biological inks (bioinks) that are customizable for three-dimensional (3D) bioprinting of specific tissue types. Gelatin methacryloyl (GelMA) is one such candidate bioink due to its biocompatibility and tunable mechanical properties. Currently, only low-concentration GelMA hydrogels (≤5% w/v) are suitable as cell-laden bioinks, allowing high cell viability, elongation, and migration. Yet, they offer poor printability. Herein, we optimize GelMA bioinks in terms of concentration and cross-linking time for improved skeletal muscle C2C12 cell spreading in 3D, and we augment these by adding gold nanoparticles (AuNPs) or a two-dimensional (2D) transition metal carbide (MXene nanosheets) for enhanced printability and biological properties. AuNP and MXene addition endowed GelMA with increased conductivity (up to 0.8 ± 0.07 and 0.9 ± 0.12 S/m, respectively, compared to 0.3 ± 0.06 S/m for pure GelMA). Furthermore, it resulted in an improvement of rheological properties and printability, specifically at 10 °C. Improvements in electrical and rheological properties led to enhanced differentiation of encapsulated myoblasts and allowed for printing highly viable (97%) stable constructs. Taken together, these results constitute a significant step toward fabrication of 3D conductive tissue constructs with physiological relevance.

Lymph Nodes-On-Chip: Promising Immune Platforms for Pharmacological and Toxicological Applications.

Organs-on-chip are gaining increasing attention as promising platforms for drug screening and testing applications. However, lymph nodes-on-chip options remain limited although the lymph node is one of the main determinants of the immunotoxicity of newly developed pharmacological drugs. In this review, we describe existing biomimetic lymph nodes-on-chip, their design, and their physiological relevance to pharmacology and shed the light on future directions associated with lymph node-on-chip design and implementation in drug discovery and development.

Transdifferentiation of Human Fibroblasts into Skeletal Muscle Cells: Optimization and Assembly into Engineered Tissue Constructs through Biological Ligands.

The development of robust skeletal muscle models has been challenging due to the partial recapitulation of human physiology and architecture. Reliable and innovative 3D skeletal muscle models recently described offer an alternative that more accurately captures the in vivo environment but require an abundant cell source. Direct reprogramming or transdifferentiation has been considered as an alternative. Recent reports have provided evidence for significant improvements in the efficiency of derivation of human skeletal myotubes from human fibroblasts. Herein we aimed at improving the transdifferentiation process of human fibroblasts (tHFs), in addition to the differentiation of murine skeletal myoblasts (C2C12), and the differentiation of primary human skeletal myoblasts (HSkM). Differentiating or transdifferentiating cells were exposed to single or combinations of biological ligands, including Follistatin, GDF8, FGF2, GDF11, GDF15, hGH, TMSB4X, BMP4, BMP7, IL6, and TNF-α. These were selected for their critical roles in myogenesis and regeneration. C2C12 and tHFs displayed significant differentiation deficits when exposed to FGF2, BMP4, BMP7, and TNF-α, while proliferation was significantly enhanced by FGF2. When exposed to combinations of ligands, we observed consistent deficit differentiation when TNF-α was included. Finally, our direct reprogramming technique allowed for the assembly of elongated, cross-striated, and aligned tHFs within tissue-engineered 3D skeletal muscle constructs. In conclusion, we describe an efficient system to transdifferentiate human fibroblasts into myogenic cells and a platform for the generation of tissue-engineered constructs. Future directions will involve the evaluation of the functional characteristics of these engineered tissues.

Assessing the Tidal Volume through Wearables: A Scoping Review.

The assessment of respiratory activity based on wearable devices is becoming an area of growing interest due to the wide range of available sensors. Accordingly, this scoping review aims to identify research evidence supporting the use of wearable devices to monitor the tidal volume during both daily activities and clinical settings. A screening of the literature (Pubmed, Scopus, and Web of Science) was carried out in December 2020 to collect studies: i. comparing one or more methodological approaches for the assessment of tidal volume with the outcome of a state-of-the-art measurement device (i.e., spirometry or optoelectronic plethysmography); ii. dealing with technological solutions designed to be exploited in wearable devices. From the initial 1031 documents, only 36 citations met the eligibility criteria. These studies highlighted that the tidal volume can be estimated by using different technologies ranging from IMUs to strain sensors (e.g., resistive, capacitive, inductive, electromagnetic, and optical) or acoustic sensors. Noticeably, the relative volumetric error of these solutions during quasi-static tasks (e.g., resting and sitting) is typically ≥10% but it deteriorates during dynamic motor tasks (e.g., walking). As such, additional efforts are required to improve the performance of these devices and to identify possible applications based on their accuracy and reliability.