Search

Background: Malignant breast cancer is the most common cancer affecting women worldwide. The COVID-19 pandemic appears to have slowed the diagnostic process, leading to an enhanced use of invasive approaches such as mastectomy. The increased use of a surgical procedure pushes towards an objective analysis of patient flow with measurable quality indicators such as length of stay (LOS) in order to optimize it. Methods: In this work, different regression and classification models were implemented to analyze the total LOS as a function of a set of independent variables (age, gender, pre-op LOS, discharge ward, year of discharge, type of procedure, presence of hypertension, diabetes, cardiovascular disease, respiratory disease, secondary tumors, and surgery with complications) extracted from the discharge records of patients undergoing mastectomy at the ‘San Giovanni di Dio e Ruggi d’Aragona’ University Hospital of Salerno (Italy) in the years 2011–2021. In addition, the impact of COVID-19 was assessed by statistically comparing data from patients discharged in 2018–2019 with those discharged in 2020–2021. Results: The results obtained generally show the good performance of the regression models in characterizing the particular case studies. Among the models, the best at predicting the LOS from the set of variables described above was polynomial regression, with an R2 value above 0.689. The classification algorithms that operated on a LOS divided into 3 arbitrary classes also proved to be good tools, reaching 79% accuracy with the voting classifier. Among the independent variables, both implemented models showed that the ward of discharge, year of discharge, type of procedure and complications during surgery had the greatest impact on LOS. The final focus to assess the impact of COVID-19 showed a statically significant increase in surgical complications. Conclusion: Through this study, it was possible to validate the use of regression and classification models to characterize the total LOS of mastectomy patients. LOS proves to be an excellent indicator of performance, and through its analysis with advanced methods, such as machine learning algorithms, it is possible to understand which of the demographic and organizational variables collected have a significant impact and thus build simple predictors to support healthcare management.

Stroke prediction is a vital research area due to its significant implications for public health. This comparative study offers a detailed evaluation of algorithmic methodologies and outcomes from three recent prominent studies on stroke prediction. Ivanov et al. tackled issues of imbalanced datasets and algorithmic bias using deep learning techniques, achieving notable results with a 98% accuracy and a 97% recall rate. They utilized resampling methods to balance the classes and advanced imputation techniques to handle missing data, underscoring the critical role of data preprocessing in enhancing the performance of Support Vector Machines (SVMs). Hassan et al. addressed missing data and class imbalance using multiple imputations and the Synthetic Minority Oversampling Technique (SMOTE). They developed a Dense Stacking Ensemble (DSE) model with over 96% accuracy. Their results underscore the efficiency of ensemble learning techniques and imputation for handling imbalanced datasets in stroke prediction. Bathla et al. employed various classifiers and feature selection techniques, including SMOTE, for class balancing. Their Random Forest (RF) classifier, combined with Feature Importance (FI) selection, achieved an accuracy of 97.17%, illustrating the positive impact of RF and relevant feature selection on model performance. A comparative analysis indicated that Ivanov et al.’s method achieved the highest accuracy rate. However, the studies collectively highlight that the choice of models and techniques for stroke prediction should be tailored to the specific characteristics of the dataset used. This study emphasizes the importance of effective data management and model selection in enhancing predictive performance.

Background: Mechanical ventilation is a critical but resource-intensive treatment. Automated tools are common in screening diagnostics, whereas real-time, continuous trend analysis in mechanical ventilation remains rare. Current techniques for monitoring lung conditions are often invasive, lack accuracy, and fail to isolate respiratory resistance—making them impractical for continuous monitoring and diagnosis. To address this challenge, we propose an automated, non-invasive condition monitoring method to support pulmonologists. Methods: Our method leverages ventilation waveform time-series data in controlled modes to monitor lung conditions automatically and non-invasively on a breath-by-breath basis while accurately isolating respiratory resistance. Results: Using statistical classification and regression models, the approach achieves 99.1% accuracy for ventilation mode classification, 97.5% accuracy for feature extraction, and 99.0% for predicting mechanical lung parameters. The models are both computationally efficient (720 K predictions per second per core) and lightweight (24.5 MB). Conclusions: By storing breath-by-breath predictions, pulmonologists can access a high-resolution trend of lung conditions, gaining clear insights into sudden changes without speculation and streamlining diagnosis and decision-making. The deployment of this solution could expand domain knowledge, enhance the understanding of patient conditions, and enable real-time dashboards for parallel monitoring, helping to prioritize patients and optimize resource use, which is especially valuable during pandemics.

The development of current sexing methods largely depends on the use of adequate sources of data and adjustable classification techniques. Most sex estimation methods have been based on linear measurements, while the angles have been largely ignored, potentially leading to the loss of valuable information for sex discrimination. This study aims to evaluate the usefulness of cranial angles for sex estimation and to differentiate the most dimorphic ones by training machine learning algorithms. Computed tomography images of 154 males and 180 females were used to derive data of 36 cranial angles. The classification models were created by support vector machines, naïve Bayes, logistic regression, and the rule-induction algorithm CN2. A series of cranial angle subsets was arranged by an attribute selection scheme. The algorithms achieved the highest accuracy on subsets of cranial angles, most of which correspond to well-known features for sex discrimination. Angles characterizing the lower forehead and upper midface were included in the best-performing models of all algorithms. The accuracy results showed the considerable classification potential of the cranial angles. The study demonstrates the value of the cranial angles as sex indicators and the possibility to enhance the sex estimation accuracy by using them.

Physical activity recognition using accelerometry is a rapidly advancing field with significant implications for healthcare, sports science, and wearable technology. This research presents an interesting approach for classifying physical activities using solely accelerometry data, signals that were taken from the available “MHEALTH dataset” and processed through artificial neural networks (ANNs). The methodology involves data acquisition, preprocessing, feature extraction, and the application of deep learning algorithms to accurately identify activity patterns. A major innovation in this study is the incorporation of a new feature derived from the radius of curvature. This time-domain feature is computed by segmenting accelerometry signals into windows, conducting double integration to derive positional data, and subsequently estimating a circumference based on the positional data obtained within each window. This characteristic is computed across the three movement planes, providing a robust and comprehensive feature for activity classification. The integration of the radius of curvature into the ANN models significantly enhances their accuracy, achieving over 95%. In comparison with other methodologies, our proposed approach, which utilizes a feedforward neural network (FFNN), demonstrates superior performance. This outperforms previous methods such as logistic regression, which achieved 93%, KNN models with 90%, and the InceptTime model with 88%. The findings demonstrate the potential of this model to improve the precision and reliability of physical activity recognition in wearable health monitoring systems.

Date palm (Phoenix dactylifera L.) fruit samples belonging to the ‘Mejhoul’ and ‘Boufeggous’ cultivars were harvested at the Tamar stage and used in our experiments. Before scanning, date samples were dried using convective drying at 60 °C and infrared drying at 60 °C with a frequency of 50 Hz, and then they were scanned. The scanning trials were performed for two hundred date palm fruit in fresh, convective-dried, and infrared-dried forms of each cultivar using a flatbed scanner. The image-texture parameters of date fruit were extracted from images converted to individual color channels in RGB, Lab, XYZ, and UVS color models. The models to classify fresh and dried samples were developed based on selected image textures using machine learning algorithms belonging to the groups of Bayes, Trees, Lazy, Functions, and Meta. For both the ‘Mejhoul’ and ‘Boufeggous’ cultivars, models built using Random Forest from the group of Trees turned out to be accurate and successful. The average classification accuracy for fresh, convective-dried, and infrared-dried ‘Mejhoul’ reached 99.33%, whereas fresh, convective-dried, and infrared-dried samples of ‘Boufeggous’ were distinguished with an average accuracy of 94.33%. In the case of both cultivars and each model, the higher correctness of discrimination was between fresh and infrared-dried samples, whereas the highest number of misclassified cases occurred between fresh and convective-dried fruit. Thus, the developed procedure may be considered an innovative approach to the non-destructive assessment of drying impact on the external quality characteristics of date palm fruit.

The profile of secondary metabolites present in the apple cuticular layer is not only characteristic of a particular apple cultivar; it also dynamically reflects various external factors in the growing environment. In this study, the possibility of authenticating apple samples by analyzing their cuticular layer extracts was investigated. Ultra-high-performance liquid chromatography coupled with high-resolution tandem mass spectrometry (UHPLC-HRMS/MS) was employed for obtaining metabolomic fingerprints. A total of 274 authentic apple samples from four cultivars harvested in the Czech Republic and Poland between 2020 and 2022 were analyzed. The complex data generated, processed using univariate and multivariate statistical methods, enabled the building of classification models to distinguish apple cultivars as well as their geographical origin. The models showed very good performance in discriminating Czech and Polish samples for three out of four cultivars: “Gala”, “Golden Delicious” and “Idared”. Moreover, the validity of the models was tested over several harvest seasons. In addition to metabolites of the triterpene biosynthetic pathway, the diagnostic markers were mainly wax esters. “Jonagold”, which is known to be susceptible to mutations, was the only cultivar for which an unambiguous classification of geographical origin was not possible.

Radiomics is an emerging approach to support the diagnosis of pulmonary nodules detected via low-dose computed tomography lung cancer screening. Serum metabolome is a promising source of auxiliary biomarkers that could help enhance the precision of lung cancer diagnosis in CT-based screening. Thus, we aimed to verify whether the combination of these two techniques, which provides local/morphological and systemic/molecular features of disease at the same time, increases the performance of lung cancer classification models. The collected cohort consists of 1086 patients with radiomic and 246 patients with serum metabolomic evaluations. Different machine learning techniques, i.e., random forest and logistic regression were applied for each omics. Next, model predictions were combined with various integration methods to create a final model. The best single omics models were characterized by an AUC of 83% in radiomics and 60% in serum metabolomics. The model integration only slightly increased the performance of the combined model (AUC equal to 85%), which was not statistically significant. We concluded that radiomics itself has a good ability to discriminate lung cancer from benign lesions. However, additional research is needed to test whether its combination with other molecular assessments would further improve the diagnosis of screening-detected lung nodules.

Background: Mechanical ventilation is a critical but resource-intensive treatment. Automated tools are common in screening diagnostics, whereas real-time, continuous trend analysis in mechanical ventilation remains rare. Current techniques for monitoring lung conditions are often invasive, lack accuracy, and fail to isolate respiratory resistance-making them impractical for continuous monitoring and diagnosis. To address this challenge, we propose an automated, non-invasive condition monitoring method to support pulmonologists., Methods: Our method leverages ventilation waveform time-series data in controlled modes to monitor lung conditions automatically and non-invasively on a breath-by-breath basis while accurately isolating respiratory resistance., Results: Using statistical classification and regression models, the approach achieves 99.1% accuracy for ventilation mode classification, 97.5% accuracy for feature extraction, and 99.0% for predicting mechanical lung parameters. The models are both computationally efficient (720 K predictions per second per core) and lightweight (24.5 MB)., Conclusions: By storing breath-by-breath predictions, pulmonologists can access a high-resolution trend of lung conditions, gaining clear insights into sudden changes without speculation and streamlining diagnosis and decision-making. The deployment of this solution could expand domain knowledge, enhance the understanding of patient conditions, and enable real-time dashboards for parallel monitoring, helping to prioritize patients and optimize resource use, which is especially valuable during pandemics.

Stroke is a major public health issue with significant economic consequences. This study aims to enhance stroke prediction by addressing imbalanced datasets and algorithmic bias. Our research focuses on accurately and precisely detecting stroke possibility to aid prevention. We tackle the overlooked aspect of imbalanced datasets in the healthcare literature. Our study focuses on predicting stroke in a general context rather than specific subtypes. This clarification will not only ensure a clear understanding of our study’s scope but also enhance the overall transparency and impact of our findings. We construct an optimization model and describe an effective methodology and algorithms for machine learning classification, accommodating missing data and imbalances. Our models outperform previous efforts in stroke prediction, demonstrating higher sensitivity, specificity, accuracy, and precision. Data quality and preprocessing play a crucial role in developing reliable models. The proposed algorithm using SVMs achieves 98% accuracy and 97% recall score. In-depth data analysis and advanced machine learning techniques improve stroke prediction. This research highlights the value of data-oriented approaches, leading to enhanced accuracy and understanding of stroke risk factors. These methods can be applied to other medical domains, benefiting patient care and public health outcomes. By incorporating our findings, the efficiency and effectiveness of the public health system can be improved.

This research aims to enhance the classification and prediction of ischemic heart diseases using machine learning techniques, with a focus on resource efficiency and clinical applicability. Specifically, we introduce novel non-invasive indicators known as Campello de Souza features, which require only a tensiometer and a clock for data collection. These features were evaluated using a comprehensive dataset of heart disease cases from a machine learning data repository. Our findings highlight the ability of machine learning algorithms to not only streamline diagnostic procedures but also reduce diagnostic errors and the dependency on extensive clinical testing. Three key features—mean arterial pressure, pulsatile blood pressure index, and resistance-compliance indicator—were found to significantly improve the accuracy of machine learning algorithms in binary heart disease classification. Logistic regression achieved the highest average accuracy among the examined classifiers when utilizing these features. While such novel indicators contribute substantially to the classification process, they should be integrated into a broader diagnostic framework that includes comprehensive patient evaluations and medical expertise. Therefore, the present study offers valuable insights for leveraging data science techniques in the diagnosis and management of cardiovascular diseases.

This study aimed to develop an analytical method to determine the geographical origin of Moroccan Argan oil through near-infrared (NIR) or mid-infrared (MIR) spectroscopic fingerprints. However, the classification may be problematic due to the spectral similarity of the components in the samples. Therefore, unsupervised and supervised classification methods—including principal component analysis (PCA), Partial Least Squares-Discriminant Analysis (PLS-DA) and Soft Independent Modeling of Class Analogy (SIMCA)—were evaluated to distinguish between Argan oils from four regions. The spectra of 93 samples were acquired and preprocessed using both standard preprocessing methods and multivariate filters, such as External Parameter Orthogonalization, Generalized Least Squares Weighting and Orthogonal Signal Correction, to improve the models. Their accuracy, precision, sensitivity, and selectivity were used to evaluate the performance of the models. SIMCA and PLS-DA models generated after standard preprocessing failed to correctly classify all samples. However, successful models were produced after using multivariate filters. The NIR and MIR classification models show an equivalent accuracy. The PLS-DA models outperformed the SIMCA with 100% accuracy, specificity, sensitivity and precision. In conclusion, the studied multivariate filters are applicable on the spectroscopic fingerprints to geographically identify the Argan oils in routine monitoring, significantly reducing analysis costs and time.

This research paper focuses on developing an effective gesture-to-text translation system using state-of-the-art computer vision techniques. The existing research on sign language translation has yet to utilize skin masking, edge detection, and feature extraction techniques to their full potential. Therefore, this study employs the speeded-up robust features (SURF) model for feature extraction, which is resistant to variations such as rotation, perspective scaling, and occlusion. The proposed system utilizes a bag of visual words (BoVW) model for gesture-to-text conversion. The study uses a dataset of 42,000 photographs consisting of alphabets (A–Z) and numbers (1–9), divided into 35 classes with 1200 shots per class. The pre-processing phase includes skin masking, where the RGB color space is converted to the HSV color space, and Canny edge detection is used for sharp edge detection. The SURF elements are grouped and converted to a visual language using the K-means mini-batch clustering technique. The proposed system’s performance is evaluated using several machine learning algorithms such as naïve Bayes, logistic regression, K nearest neighbors, support vector machine, and convolutional neural network. All the algorithms benefited from SURF, and the system’s accuracy is promising, ranging from 79% to 92%. This research study not only presents the development of an effective gesture-to-text translation system but also highlights the importance of using skin masking, edge detection, and feature extraction techniques to their full potential in sign language translation. The proposed system aims to bridge the communication gap between individuals who cannot speak and those who cannot understand Indian Sign Language (ISL).

Seagrass is an essential component of coastal ecosystems because of its capability to absorb blue carbon, and its involvement in sustaining marine biodiversity. In this study, support vector machine (SVM) technologies with corrected satellite imagery data, were applied to identify the distribution of seagrasses. Observations of seagrasses from satellite imagery were obtained using GeoEye-1, Sentinel-2 MSI level 1C, and Landsat-8 OLI satellite imagery. The satellite imagery from Google Earth has been obtained at a very high resolution, and was to be used within both the training and testing of a classification method. The optical satellite imagery must be processed for image classification, throughout which radiometric correction, sunglint, and water column adjustments were applied. We restricted the scope of the study area to a maximum depth of 10 m due to the fact that light does not penetrate beyond this level. When classifying the distribution of seagrasses present in the research region, the recently developed SVM technique achieved overall accuracy values of up to 92% (GeoEye-1), 88% (Sentinel-2 MSI level 1C), and 83% (Landsat-8 OLI), respectively. The results of the overall accuracy values are also used to evaluate classification models.

With the rise of social networks and the introduction of data protection laws, companies are training machine learning models using data generated locally by their users or customers in various types of devices. The data may include sensitive information such as family information, medical records, personal habits, or financial records that, if leaked, can generate problems. For this reason, this paper aims to introduce a protocol for training Multi-Layer Perceptron (MLP) neural networks via combining federated learning and homomorphic encryption, where the data are distributed in multiple clients, and the data privacy is preserved. This proposal was validated by running several simulations using a dataset for a multi-class classification problem, different MLP neural network architectures, and different numbers of participating clients. The results are shown for several metrics in the local and federated settings, and a comparative analysis is carried out. Additionally, the privacy guarantees of the proposal are formally analyzed under a set of defined assumptions, and the added value of the proposed protocol is identified compared with previous works in the same area of knowledge.

With the current shift in the mass media landscape from journalistic rigor to social media, personalized social media is becoming the new norm. Although the digitalization progress of the media brings many advantages, it also increases the risk of spreading disinformation, misinformation, and malformation through the use of fake news. The emergence of this harmful phenomenon has managed to polarize society and manipulate public opinion on particular topics, e.g., elections, vaccinations, etc. Such information propagated on social media can distort public perceptions and generate social unrest while lacking the rigor of traditional journalism. Natural Language Processing and Machine Learning techniques are essential for developing efficient tools that can detect fake news. Models that use the context of textual data are essential for resolving the fake news detection problem, as they manage to encode linguistic features within the vector representation of words. In this paper, we propose a new approach that uses document embeddings to build multiple models that accurately label news articles as reliable or fake. We also present a benchmark on different architectures that detect fake news using binary or multi-labeled classification. We evaluated the models on five large news corpora using accuracy, precision, and recall. We obtained better results than more complex state-of-the-art Deep Neural Network models. We observe that the most important factor for obtaining high accuracy is the document encoding, not the classification model's complexity.

Bayesian networks are a powerful tool for modelling multivariate random variables. However, when applied in practice, for example, for industrial projects, problems arise because the existing learning and inference algorithms are not adapted to real data. This article discusses two learning and inference problems on mixed data in Bayesian networks—learning and inference at nodes of a Bayesian network that have non-Gaussian distributions and learning and inference for networks that require edges from continuous nodes to discrete ones. First, an approach based on the use of mixtures of Gaussian distributions is proposed to solve a problem when the joint normality assumption is not confirmed. Second, classification models are proposed to solve a problem with edges from continuous nodes to discrete nodes. Experiments have been run on both synthetic datasets and real-world data and have shown gains in modelling quality.

Olives are an essential crop for Greece and constitute a major economic and agricultural factor. Diseases, pests, and environmental conditions are all factors that can deteriorate the health status of olive crops by causing plant stress. Researchers can utilize remote sensing to assist their actions in detecting these sources of stress and act accordingly. In this experiment, Sentinel-2 data were used to create vegetation indices for commercial olive fields in Halkidiki, Northern Greece. Twelve machine learning algorithms were tested to determine which type would be the most efficient to detect plant stress in olive trees. In parallel, a test was conducted by testing 26 thresholds to determine how setting different thresholds for stress incidence affects model performance and which threshold constitutes the best choice for more accurate classification. The results show that among all tested classification algorithms, the quadratic discriminant analysis provided the best performance of 0.99. The stress incidence threshold used in the current case to generate the best-performing model was 6%, but the results suggest that setting customized thresholds relevant to specific cases would provide optimal results. The best-performing model was used in a one-vs.-rest multiclass classification task to determine the source of the stress between four possible classes: “healthy”, “verticillium”, “spilocaea”, and “unidentified”. The multiclass model was more accurate in detection for the “healthy” class (0.99); the “verticillium” and “unidentified” classes were less accurate (0.76); and “spilocaea” had the lowest score (0.72). Findings from this research can be used by experts as a service to enhance their decision-making and support the application of efficient strategies in the field of precision crop protection.

Atrial fibrillation (AF) is the most common cardiac arrhythmia, and in response to increasing clinical demand, a variety of signals and indices have been utilized for its analysis, which include complex fractionated atrial electrograms (CFAEs). New methodologies have been developed to characterize the atrial substrate, along with straightforward classification models to discriminate between paroxysmal and persistent AF (ParAF vs. PerAF). Yet, most previous works have missed the mark for the assessment of CFAE signal quality, as well as for studying their stability over time and between different recording locations. As a consequence, an atrial substrate assessment may be unreliable or inaccurate. The objectives of this work are, on the one hand, to make use of a reduced set of nonlinear indices that have been applied to CFAEs recorded from ParAF and PerAF patients to assess intra-recording and intra-patient stability and, on the other hand, to generate a simple classification model to discriminate between them. The dominant frequency (DF), AF cycle length, sample entropy (SE), and determinism (DET) of the Recurrence Quantification Analysis are the analyzed indices, along with the coefficient of variation (CV) which is utilized to indicate the corresponding alterations. The analysis of the intra-recording stability revealed that discarding noisy or artifacted CFAE segments provoked a significant variation in the CV(%) in any segment length for the DET and SE, with deeper decreases for longer segments. The intra-patient stability provided large variations in the CV(%) for the DET and even larger for the SE at any segment length. To discern ParAF versus PerAF, correlation matrix filters and Random Forests were employed, respectively, to remove redundant information and to rank the variables by relevance, while coarse tree models were built, optimally combining high-ranked indices, and tested with leave-one-out cross-validation. The best classification performance combined the SE and DF, with an accuracy (Acc) of 88.3%, to discriminate ParAF versus PerAF, while the highest single Acc was provided by the DET, reaching 82.2%. This work has demonstrated that due to the high variability of CFAEs data averaging from one recording place or among different recording places, as is traditionally made, it may lead to an unfair oversimplification of the CFAE-based atrial substrate characterization. Furthermore, a careful selection of reduced sets of features input to simple classification models is helpful to accurately discern the CFAEs of ParAF versus PerAF.

The detection of hypertension (HT) is of great importance for the early diagnosis of cardiovascular diseases (CVDs), as subjects with high blood pressure (BP) are asymptomatic until advanced stages of the disease. The present study proposes a classification model to discriminate between normotensive (NTS) and hypertensive (HTS) subjects employing electrocardiographic (ECG) and photoplethysmographic (PPG) recordings as an alternative to traditional cuff-based methods. A total of 913 ECG, PPG and BP recordings from 69 subjects were analyzed. Then, signal preprocessing, fiducial points extraction and feature selection were performed, providing 17 discriminatory features, such as pulse arrival and transit times, that fed machine-learning-based classifiers. The main innovation proposed in this research uncovers the relevance of previous calibration to obtain accurate HT risk assessment. This aspect has been assessed using both close and distant time test measurements with respect to calibration. The k-nearest neighbors-classifier provided the best outcomes with an accuracy for new subjects before calibration of 51.48%. The inclusion of just one calibration measurement into the model improved classification accuracy by 30%, reaching gradually more than 96% with more than six calibration measurements. Accuracy decreased with distance to calibration, but remained outstanding even days after calibration. Thus, the use of PPG and ECG recordings combined with previous subject calibration can significantly improve discrimination between NTS and HTS individuals. This strategy could be implemented in wearable devices for HT risk assessment as well as to prevent CVDs.

Date palm ( Phoenix dactylifera L.) fruit samples belonging to the 'Mejhoul' and 'Boufeggous' cultivars were harvested at the Tamar stage and used in our experiments. Before scanning, date samples were dried using convective drying at 60 °C and infrared drying at 60 °C with a frequency of 50 Hz, and then they were scanned. The scanning trials were performed for two hundred date palm fruit in fresh, convective-dried, and infrared-dried forms of each cultivar using a flatbed scanner. The image-texture parameters of date fruit were extracted from images converted to individual color channels in RGB, Lab, XYZ, and UVS color models. The models to classify fresh and dried samples were developed based on selected image textures using machine learning algorithms belonging to the groups of Bayes, Trees, Lazy, Functions, and Meta. For both the 'Mejhoul' and 'Boufeggous' cultivars, models built using Random Forest from the group of Trees turned out to be accurate and successful. The average classification accuracy for fresh, convective-dried, and infrared-dried 'Mejhoul' reached 99.33%, whereas fresh, convective-dried, and infrared-dried samples of 'Boufeggous' were distinguished with an average accuracy of 94.33%. In the case of both cultivars and each model, the higher correctness of discrimination was between fresh and infrared-dried samples, whereas the highest number of misclassified cases occurred between fresh and convective-dried fruit. Thus, the developed procedure may be considered an innovative approach to the non-destructive assessment of drying impact on the external quality characteristics of date palm fruit.

Litchi downy blight caused by Peronophythora litchii is the most serious disease in litchi production, storage and transportation. Existing disease identification technology has difficulty identifying litchi downy blight sufficiently early, resulting in economic losses. Thus, the use of diffuse reflectance spectroscopy to identify litchi downy blight at different stages of disease, particularly to achieve the early identification of downy blight, is very important. The diffuse reflectance spectral data of litchi fruits inoculated with P. litchii were collected in the wavelength range of 350–1350 nm. According to the duration of inoculation and expert evaluation, they were divided into four categories: healthy, latent, mild and severe. First, the SG smoothing method and derivation method were used to denoise the spectral curves. Then, the wavelength screening methods competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) were compared to verify that the SPA method was more effective. Eleven characteristic wavelengths were selected, accounting for only 1.1% of the original data. Finally, the characteristic wavelengths were tested by six different classification models, and their accuracy was calculated. Among them, the ANN model performed best, with an accuracy of 90.7%. The results showed that diffuse reflectance spectroscopic technology has potential for identifying litchi downy blight at different stages, providing technical support for the subsequent development of related automatic detection devices.

Dual-specific tyrosine phosphorylation regulated kinase 1 (DYRK1A) has been regarded as a potential therapeutic target of neurodegenerative diseases, and considerable progress has been made in the discovery of DYRK1A inhibitors. Identification of pharmacophoric fragments provides valuable information for structure- and fragment-based design of potent and selective DYRK1A inhibitors. In this study, seven machine learning methods along with five molecular fingerprints were employed to develop qualitative classification models of DYRK1A inhibitors, which were evaluated by cross-validation, test set, and external validation set with four performance indicators of predictive classification accuracy (CA), the area under receiver operating characteristic (AUC), Matthews correlation coefficient (MCC), and balanced accuracy (BA). The PubChem fingerprint-support vector machine model (CA = 0.909, AUC = 0.933, MCC = 0.717, BA = 0.855) and PubChem fingerprint along with the artificial neural model (CA = 0.862, AUC = 0.911, MCC = 0.705, BA = 0.870) were considered as the optimal modes for training set and test set, respectively. A hybrid data balancing method SMOTETL, a combination of synthetic minority over-sampling technique (SMOTE) and Tomek link (TL) algorithms, was applied to explore the impact of balanced learning on the performance of models. Based on the frequency analysis and information gain, pharmacophoric fragments related to DYRK1A inhibition were also identified. All the results will provide theoretical supports and clues for the screening and design of novel DYRK1A inhibitors.

The adulteration in Chinese chestnuts affects the quality, taste, and brand value. The objective of this study was to explore the feasibility of the hyperspectral imaging (HSI) technique to determine the geographical origin of Chinese chestnuts. An HSI system in spectral range of 400–1000 nm was applied to identify a total of 417 Chinese chestnuts from three different geographical origins. Principal component analysis (PCA) was preliminarily used to investigate the differences of average spectra of the samples from different geographical origins. A deep-learning-based model (1D-CNN, one-dimensional convolutional neural network) was developed first, and then the model based on full spectra and optimal wavelengths were established for various machine learning methods, including partial least squares-discriminant analysis (PLS-DA) and particle swarm optimization-support vector machine (PSO-SVM). The optimal results based on full spectra for 1D-CNN, PLS-DA, and PSO-SVM models were 97.12%, 97.12%, and 95.68%, respectively. Competitive adaptive reweighted sampling (CARS) and a successive projections algorithm (SPA) were individually utilized for wavelengths selection, and the results of simplified models generally improved. The contrasting results demonstrated that the prediction accuracies of SPA-PLS-DA and 1D-CNN both reached 97.12%, but 1D-CNN presented a higher Kappa coefficient value than SPA-PLS-DA. Meanwhile, the sensitivities and specificities of SPA-PLS-DA and 1D-CNN models were both above 90% for the samples from each geographical origin. These results indicated that both SPA-PLS-DA and 1D-CNN models combined with HSI have great potential for the geographical origin identification of Chinese chestnuts.

Fourier transform infrared spectroscopy (FT-IR) and multispectral imaging (MSI) were evaluated for the prediction of the microbiological quality of poultry meat via regression and classification models. Chicken thigh fillets (n = 402) were subjected to spoilage experiments at eight isothermal and two dynamic temperature profiles. Samples were analyzed microbiologically (total viable counts (TVCs) and Pseudomonas spp.), while simultaneously MSI and FT-IR spectra were acquired. The organoleptic quality of the samples was also evaluated by a sensory panel, establishing a TVC spoilage threshold at 6.99 log CFU/cm2. Partial least squares regression (PLS-R) models were employed in the assessment of TVCs and Pseudomonas spp. counts on chicken’s surface. Furthermore, classification models (linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machines (SVMs), and quadratic support vector machines (QSVMs)) were developed to discriminate the samples in two quality classes (fresh vs. spoiled). PLS-R models developed on MSI data predicted TVCs and Pseudomonas spp. counts satisfactorily, with root mean squared error (RMSE) values of 0.987 and 1.215 log CFU/cm2, respectively. SVM model coupled to MSI data exhibited the highest performance with an overall accuracy of 94.4%, while in the case of FT-IR, improved classification was obtained with the QDA model (overall accuracy 71.4%). These results confirm the efficacy of MSI and FT-IR as rapid methods to assess the quality in poultry products.

Physical exercise contributes to the success of rehabilitation programs and rehabilitation processes assisted through social robots. However, the amount and intensity of exercise needed to obtain positive results are unknown. Several considerations must be kept in mind for its implementation in rehabilitation, as monitoring of patients’ intensity, which is essential to avoid extreme fatigue conditions, may cause physical and physiological complications. The use of machine learning models has been implemented in fatigue management, but is limited in practice due to the lack of understanding of how an individual’s performance deteriorates with fatigue; this can vary based on physical exercise, environment, and the individual’s characteristics. As a first step, this paper lays the foundation for a data analytic approach to managing fatigue in walking tasks. The proposed framework establishes the criteria for a feature and machine learning algorithm selection for fatigue management, classifying four fatigue diagnoses states. Based on the proposed framework and the classifier implemented, the random forest model presented the best performance with an average accuracy of ≥98% and F-score of ≥93%. This model was comprised of ≤16 features. In addition, the prediction performance was analyzed by limiting the sensors used from four IMUs to two or even one IMU with an overall performance of ≥88%.

The profile of secondary metabolites present in the apple cuticular layer is not only characteristic of a particular apple cultivar; it also dynamically reflects various external factors in the growing environment. In this study, the possibility of authenticating apple samples by analyzing their cuticular layer extracts was investigated. Ultra-high-performance liquid chromatography coupled with high-resolution tandem mass spectrometry (UHPLC-HRMS/MS) was employed for obtaining metabolomic fingerprints. A total of 274 authentic apple samples from four cultivars harvested in the Czech Republic and Poland between 2020 and 2022 were analyzed. The complex data generated, processed using univariate and multivariate statistical methods, enabled the building of classification models to distinguish apple cultivars as well as their geographical origin. The models showed very good performance in discriminating Czech and Polish samples for three out of four cultivars: "Gala", "Golden Delicious" and "Idared". Moreover, the validity of the models was tested over several harvest seasons. In addition to metabolites of the triterpene biosynthetic pathway, the diagnostic markers were mainly wax esters. "Jonagold", which is known to be susceptible to mutations, was the only cultivar for which an unambiguous classification of geographical origin was not possible.

Focusing on coronary artery disease (CAD) patients, this research paper addresses the problem of automatic diagnosis of ischemia or infarction using single-photon emission computed tomography (SPECT) (Siemens Symbia S Series) myocardial perfusion imaging (MPI) scans and investigates the capabilities of deep learning and convolutional neural networks. Considering the wide applicability of deep learning in medical image classification, a robust CNN model whose architecture was previously determined in nuclear image analysis is introduced to recognize myocardial perfusion images by extracting the insightful features of an image and use them to classify it correctly. In addition, a deep learning classification approach using transfer learning is implemented to classify cardiovascular images as normal or abnormal (ischemia or infarction) from SPECT MPI scans. The present work is differentiated from other studies in nuclear cardiology as it utilizes SPECT MPI images. To address the two-class classification problem of CAD diagnosis, achieving adequate accuracy, simple, fast and efficient CNN architectures were built based on a CNN exploration process. They were then employed to identify the category of CAD diagnosis, presenting its generalization capabilities. The results revealed that the applied methods are sufficiently accurate and able to differentiate the infarction or ischemia from healthy patients (overall classification accuracy = 93.47% ± 2.81%, AUC score = 0.936). To strengthen the findings of this study, the proposed deep learning approaches were compared with other popular state-of-the-art CNN architectures for the specific dataset. The prediction results show the efficacy of new deep learning architecture applied for CAD diagnosis using SPECT MPI scans over the existing ones in nuclear medicine.

Paratuberculosis is an important disease of ruminants caused by Mycobacterium avium ssp. paratuberculosis (MAP). Early detection is crucial for successful infection control, but available diagnostic tests are still dissatisfying. Methods allowing a rapid, economic, and reliable identification of animals or herds affected by MAP are urgently required. This explorative study evaluated the potential of volatile organic compounds (VOCs) to discriminate between cattle with and without MAP infections. Headspaces above fecal samples and alveolar fractions of exhaled breath of 77 cows from eight farms with defined MAP status were analyzed in addition to stable air samples. VOCs were identified by GC–MS and quantified against reference substances. To discriminate MAP-positive from MAP-negative samples, VOC feature selection and random forest classification were performed. Classification models, generated for each biological specimen, were evaluated using repeated cross-validation. The robustness of the results was tested by predicting samples of two different sampling days. For MAP classification, the different biological matrices emitted diagnostically relevant VOCs of a unique but partly overlapping pattern (fecal headspace: 19, alveolar gas: 11, stable air: 4–5). Chemically, relevant compounds belonged to hydrocarbons, ketones, alcohols, furans, and aldehydes. Comparing the different biological specimens, VOC analysis in fecal headspace proved to be most reproducible, discriminatory, and highly predictive.

This research aims to enhance the classification and prediction of ischemic heart diseases using machine learning techniques, with a focus on resource efficiency and clinical applicability. Specifically, we introduce novel non-invasive indicators known as Campello de Souza features, which require only a tensiometer and a clock for data collection. These features were evaluated using a comprehensive dataset of heart disease cases from a machine learning data repository. Our findings highlight the ability of machine learning algorithms to not only streamline diagnostic procedures but also reduce diagnostic errors and the dependency on extensive clinical testing. Three key features-mean arterial pressure, pulsatile blood pressure index, and resistance-compliance indicator-were found to significantly improve the accuracy of machine learning algorithms in binary heart disease classification. Logistic regression achieved the highest average accuracy among the examined classifiers when utilizing these features. While such novel indicators contribute substantially to the classification process, they should be integrated into a broader diagnostic framework that includes comprehensive patient evaluations and medical expertise. Therefore, the present study offers valuable insights for leveraging data science techniques in the diagnosis and management of cardiovascular diseases.

This article describes an investigation to determine the optimal placement of accelerometers for the purpose of detecting a range of everyday activities. The paper investigates the effect of combining data from accelerometers placed at various bodily locations on the accuracy of activity detection. Eight healthy males participated within the study. Data were collected from six wireless tri-axial accelerometers placed at the chest, wrist, lower back, hip, thigh and foot. Activities included walking, running on a motorized treadmill, sitting, lying, standing and walking up and down stairs. The Support Vector Machine provided the most accurate detection of activities of all the machine learning algorithms investigated. Although data from all locations provided similar levels of accuracy, the hip was the best single location to record data for activity detection using a Support Vector Machine, providing small but significantly better accuracy than the other investigated locations. Increasing the number of sensing locations from one to two or more statistically increased the accuracy of classification. There was no significant difference in accuracy when using two or more sensors. It was noted, however, that the difference in activity detection using single or multiple accelerometers may be more pronounced when trying to detect finer grain activities. Future work shall therefore investigate the effects of accelerometer placement on a larger range of these activities.

Protein biomarkers are of great benefit for clinical research and applications, as they are powerful means for diagnosing, monitoring and treatment prediction of different diseases. Even though numerous biomarkers have been reported, the translation to clinical practice is still limited. This mainly due to: (i) incorrect biomarker selection, (ii) insufficient validation of potential biomarkers, and (iii) insufficient clinical use. In this review, we focus on the biomarker selection process and critically discuss the chemometrical and statistical decisions made in proteomics biomarker discovery to increase to selection of high value biomarkers. The characteristics of the data, the computational resources, the type of biomarker that is searched for and the validation strategy influence the decision making of the chemometrical and statistical methods and a decision made for one component directly influences the choice for another. Incorrect decisions could increase the false positive and negative rate of biomarkers which requires independent confirmation of outcome by other techniques and for comparison between different related studies. There are few guidelines for authors regarding data analysis documentation in peer reviewed journals, making it hard to reproduce successful data analysis strategies. Here we review multiple chemometrical and statistical methods for their value in proteomics-based biomarker discovery and propose to include key components in scientific documentation.

In this paper, we apply various data mining techniques including continuous numeric and discrete classification prediction models of base oils biodegradability, with emphasis on improving prediction accuracy. The results show that highly biodegradable oils can be better predicted through numeric models. In contrast, classification models did not uncover a similar dichotomy. With the exception of Memory Based Reasoning and Decision Trees, tested classification techniques achieved high classification prediction. However, the technique of Decision Trees helped uncover the most significant predictors. A simple classification rule derived based on this predictor resulted in good classification accuracy. The application of this rule enables efficient classification of base oils into either low or high biodegradability classes with high accuracy. For the latter, a higher precision biodegradability prediction can be obtained using continuous modeling techniques.

Fourier transform infrared spectroscopy (FT-IR) and multispectral imaging (MSI) were evaluated for the prediction of the microbiological quality of poultry meat via regression and classification models. Chicken thigh fillets ( n = 402) were subjected to spoilage experiments at eight isothermal and two dynamic temperature profiles. Samples were analyzed microbiologically (total viable counts (TVCs) and Pseudomonas spp.), while simultaneously MSI and FT-IR spectra were acquired. The organoleptic quality of the samples was also evaluated by a sensory panel, establishing a TVC spoilage threshold at 6.99 log CFU/cm 2 . Partial least squares regression (PLS-R) models were employed in the assessment of TVCs and Pseudomonas spp. counts on chicken's surface. Furthermore, classification models (linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), support vector machines (SVMs), and quadratic support vector machines (QSVMs)) were developed to discriminate the samples in two quality classes (fresh vs. spoiled). PLS-R models developed on MSI data predicted TVCs and Pseudomonas spp. counts satisfactorily, with root mean squared error (RMSE) values of 0.987 and 1.215 log CFU/cm 2 , respectively. SVM model coupled to MSI data exhibited the highest performance with an overall accuracy of 94.4%, while in the case of FT-IR, improved classification was obtained with the QDA model (overall accuracy 71.4%). These results confirm the efficacy of MSI and FT-IR as rapid methods to assess the quality in poultry products.