A comparative study of feature selection and feature extraction methods for financial distress identification.

Financial distress identification remains an essential topic in the scientific literature due to its importance for society and the economy. The advancements in information technology and the escalating volume of stored data have led to the emergence of financial distress that transcends the realm of financial statements and its' indicators (ratios). The feature space could be expanded by incorporating new perspectives on feature data categories such as macroeconomics, sectors, social, board, management, judicial incident, etc. However, the increased dimensionality results in sparse data and overfitted models. This study proposes a new approach for efficient financial distress classification assessment by combining dimensionality reduction and machine learning techniques. The proposed framework aims to identify a subset of features leading to the minimization of the loss function describing the financial distress in an enterprise. During the study, 15 dimensionality reduction techniques with different numbers of features and 17 machine-learning models were compared. Overall, 1,432 experiments were performed using Lithuanian enterprise data covering the period from 2015 to 2022. Results revealed that the artificial neural network (ANN) model with 30 ranked features identified using the Random Forest mean decreasing Gini (RF_MDG) feature selection technique provided the highest AUC score. Moreover, this study has introduced a novel approach for feature extraction, which could improve financial distress classification models.

Association of uncertain significance genetic variants with myocardial mechanics and morphometrics in patients with nonischemic dilated cardiomyopathy.

BACKGROUND: Careful interpretation of the relation between phenotype changes of the heart and gene variants detected in dilated cardiomyopathy (DCM) is important for patient care and monitoring. OBJECTIVE: We sought to assess the association between cardiac-related genes and whole-heart myocardial mechanics or morphometrics in nonischemic dilated cardiomyopathy (NIDCM). METHODS: It was a prospective study consisting of patients with NIDCM. All patients were referred for genetic testing and a genetic analysis was performed using Illumina NextSeq 550 and a commercial gene capture panel of 233 genes (Systems Genomics, Cardiac-GeneSGKit®). It was analyzed whether there are significant differences in clinical, two-dimensional (2D) echocardiographic, and magnetic resonance imaging (MRI) parameters between patients with the genes variants and those without. 2D echocardiography and MRI were used to analyze myocardial mechanics and morphometrics. RESULTS: The study group consisted of 95 patients with NIDCM and the average age was 49.7 ± 10.5. All echocardiographic and MRI parameters of myocardial mechanics (left ventricular ejection fraction 28.4 ± 8.7 and 30.7 ± 11.2, respectively) were reduced and all values of cardiac chambers were increased (left ventricular end-diastolic diameter 64.5 ± 5.9 mm and 69.5 ± 10.7 mm, respectively) in this group. It was noticed that most cases of whole-heart myocardial mechanics and morphometrics differences between patients with and without gene variants were in the genes GATAD1, LOX, RASA1, KRAS, and KRIT1. These genes have not been previously linked to DCM. It has emerged that KRAS and KRIT1 genes were associated with worse whole-heart mechanics and enlargement of all heart chambers. GATAD1, LOX, and RASA1 genes variants showed an association with better cardiac function and morphometrics parameters. It might be that these variants alone do not influence disease development enough to be selective in human evolution. CONCLUSIONS: Combined variants in previously unreported genes related to DCM might play a significant role in affecting clinical, morphometrics, or myocardial mechanics parameters.

The comparison of the dynamics of Ca2+ and bleomycin intracellular delivery after cell sonoporation and electroporation in vitro.

Ca2+, in combination with SP or EP, induces cell cytotoxicity much faster compared to BLM. The application of BLM in combination with, SP or EP, reaches the level of cell death, induced by similar combination with Ca2+, only after 72 h. The methods of SP and EP were calibrated according to the level of differential cytotoxicity, determined after 6 days (using cell clonogenic assay). The combination of Ca2+ SP induces cell death faster than Ca2+ EP - after Ca2+ SP it increases to a maximum level after 15 min and remains constant for up to 6 days, while the cytotoxic efficiency after Ca2+ EP increases to the level of Ca2+ SP only after 72 h. The combination of BLM SP shows a very similar dynamics to BLM EP - both reach maximal level of cytotoxicity after 48-72 h. Ca2+ and BLM in combination with SP have shown similar levels of cytotoxicity at higher acoustic pressures (≥250 kPa); therefore, Ca2+ SP can be used to induce immediate and maximal level of cytotoxic effect. The faster cytotoxic efficiency of Ca2+ in combination with SP than EP was determined to be due to the involvement of microbubble inertial cavitation.

Digital Phenotyping for Monitoring and Disease Trajectory Prediction of Patients With Cancer: Protocol for a Prospective Observational Cohort Study.

BACKGROUND: Timely recognition of cancer progression and treatment complications is important for treatment guidance. Digital phenotyping is a promising method for precise and remote monitoring of patients in their natural environments by using passively generated data from sensors of personal wearable devices. Further studies are needed to better understand the potential clinical benefits of digital phenotyping approaches to optimize care of patients with cancer. OBJECTIVE: We aim to evaluate whether passively generated data from smartphone sensors are feasible for remote monitoring of patients with cancer to predict their disease trajectories and patient-centered health outcomes. METHODS: We will recruit 200 patients undergoing treatment for cancer. Patients will be followed up for 6 months. Passively generated data by sensors of personal smartphone devices (eg, accelerometer, gyroscope, GPS) will be continuously collected using the developed LAIMA smartphone app during follow-up. We will evaluate (1) mobility data by using an accelerometer (mean time of active period, mean time of exertional physical activity, distance covered per day, duration of inactive period), GPS (places of interest visited daily, hospital visits), and gyroscope sensors and (2) sociability indices (frequency of duration of phone calls, frequency and length of text messages, and internet browsing time). Every 2 weeks, patients will be asked to complete questionnaires pertaining to quality of life (European Organization for Research and Treatment of Cancer Core Quality of Life Questionnaire [EORTC QLQ-C30]), depression symptoms (Patient Health Questionnaire-9 [PHQ-9]), and anxiety symptoms (General Anxiety Disorder-7 [GAD-7]) that will be deployed via the LAIMA app. Clinic visits will take place at 1-3 months and 3-6 months of the study. Patients will be evaluated for disease progression, cancer and treatment complications, and functional status (Eastern Cooperative Oncology Group) by the study oncologist and will complete the questionnaire for evaluating quality of life (EORTC QLQ-C30), depression symptoms (PHQ-9), and anxiety symptoms (GAD-7). We will examine the associations among digital, clinical, and patient-reported health outcomes to develop prediction models with clinically meaningful outcomes. RESULTS: As of July 2023, we have reached the planned recruitment target, and patients are undergoing follow-up. Data collection is expected to be completed by September 2023. The final results should be available within 6 months after study completion. CONCLUSIONS: This study will provide in-depth insight into temporally and spatially precise trajectories of patients with cancer that will provide a novel digital health approach and will inform the design of future interventional clinical trials in oncology. Our findings will allow a better understanding of the potential clinical value of passively generated smartphone sensor data (digital phenotyping) for continuous and real-time monitoring of patients with cancer for treatment side effects, cancer complications, functional status, and patient-reported outcomes as well as prediction of disease progression or trajectories. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/49096.

The ParlaMint corpora of parliamentary proceedings.

This paper presents the ParlaMint corpora containing transcriptions of the sessions of the 17 European national parliaments with half a billion words. The corpora are uniformly encoded, contain rich meta-data about 11 thousand speakers, and are linguistically annotated following the Universal Dependencies formalism and with named entities. Samples of the corpora and conversion scripts are available from the project's GitHub repository, and the complete corpora are openly available via the CLARIN.SI repository for download, as well as through the NoSketch Engine and KonText concordancers and the Parlameter interface for on-line exploration and analysis.

Smartphone sensors for evaluating COVID-19 fear in patients with cancer: a prospective study.

Objective: This study aimed to analyze the association between the behavior of cancer patients, measured using passively and continuously generated data streams from smartphone sensors (as in digital phenotyping), and perceived fear of COVID-19 and COVID-19 vaccination status. Methods: A total of 202 patients with different cancer types and undergoing various treatments completed the COVID-19 Fears Questionnaire for Chronic Medical Conditions, and their vaccination status was evaluated. Patients' behaviors were monitored using a smartphone application that passively and continuously captures high-resolution data from personal smartphone sensors. In all, 107 patients were monitored for at least 2 weeks. The study was conducted between August 2022 and August 2023. Distributions of clinical and demographical parameters between fully vaccinated, partially vaccinated, and unvaccinated patients were compared using the Chi-squared test. The fear of COVID-19 among the groups was compared using the Mann-Whitney and the Kruskal-Wallis criteria. Trajectories of passively generated data were compared as a function of fear of COVID-19 and COVID-19 vaccination status using local polynomial regression. Results: In total, 202 patients were included in the study. Most patients were fully (71%) or partially (13%) vaccinated and 16% of the patients were unvaccinated for COVID-19. Fully vaccinated or unvaccinated patients reported greater fear of COVID-19 than partially vaccinated patients. Fear of COVID-19 was higher in patients being treated with biological therapy. Patients who reported a higher fear of COVID-19 spent more time at home, visited places at shorter distances from home, and visited fewer places of interest (POI). Fully or partially vaccinated patients visited more POI than unvaccinated patients. Local polynomial regression using passively generated smartphone sensor data showed that, although at the beginning of the study, all patients had a similar number of POI, after 1 week, partially vaccinated patients had an increased number of POI, which later remained, on average, around four POI per day. Meanwhile, fully vaccinated or unvaccinated patients had a similar trend of POI and it did not exceed three visits per day during the entire treatment period. Conclusion: The COVID-19 pandemic continues to have an impact on the behavior of cancer patients even after the termination of the global pandemic. A higher perceived fear of COVID-19 was associated with less movement, more time spent at home, less time spent outside of home, and a lower number of visited places. Unvaccinated patients visited fewer places and were moving less overall during a 14-week follow-up as compared to vaccinated patients.

Reply to Nicholas et al. Using a ResNet-18 Network to Detect Features of Alzheimer's Disease on Functional Magnetic Resonance Imaging: A Failed Replication. Comment on "Odusami et al. Analysis of Features of Alzheimer's Disease: Detection of Early Stage from Functional Brain Changes in Magnetic Resonance Images Using a Finetuned ResNet18 Network. Diagnostics 2021, 11, 1071".

We have studied the manuscript of Nicholas et al. [...].

Pedestrian and Animal Recognition Using Doppler Radar Signature and Deep Learning.

Pedestrian occurrences in images and videos must be accurately recognized in a number of applications that may improve the quality of human life. Radar can be used to identify pedestrians. When distinct portions of an object move in front of a radar, micro-Doppler signals are produced that may be utilized to identify the object. Using a deep-learning network and time-frequency analysis, we offer a method for classifying pedestrians and animals based on their micro-Doppler radar signature features. Based on these signatures, we employed a convolutional neural network (CNN) to recognize pedestrians and animals. The proposed approach was evaluated on the MAFAT Radar Challenge dataset. Encouraging results were obtained, with an AUC (Area Under Curve) value of 0.95 on the public test set and over 0.85 on the final (private) test set. The proposed DNN architecture, in contrast to more common shallow CNN architectures, is one of the first attempts to use such an approach in the domain of radar data. The use of the synthetic radar data, which greatly improved the final result, is the other novel aspect of our work.

A Novel Hybrid Gradient-Based Optimizer and Grey Wolf Optimizer Feature Selection Method for Human Activity Recognition Using Smartphone Sensors.

Human activity recognition (HAR) plays a vital role in different real-world applications such as in tracking elderly activities for elderly care services, in assisted living environments, smart home interactions, healthcare monitoring applications, electronic games, and various human-computer interaction (HCI) applications, and is an essential part of the Internet of Healthcare Things (IoHT) services. However, the high dimensionality of the collected data from these applications has the largest influence on the quality of the HAR model. Therefore, in this paper, we propose an efficient HAR system using a lightweight feature selection (FS) method to enhance the HAR classification process. The developed FS method, called GBOGWO, aims to improve the performance of the Gradient-based optimizer (GBO) algorithm by using the operators of the grey wolf optimizer (GWO). First, GBOGWO is used to select the appropriate features; then, the support vector machine (SVM) is used to classify the activities. To assess the performance of GBOGWO, extensive experiments using well-known UCI-HAR and WISDM datasets were conducted. Overall outcomes show that GBOGWO improved the classification accuracy with an average accuracy of 98%.

Analysis of Features of Alzheimer's Disease: Detection of Early Stage from Functional Brain Changes in Magnetic Resonance Images Using a Finetuned ResNet18 Network.

One of the first signs of Alzheimer's disease (AD) is mild cognitive impairment (MCI), in which there are small variants of brain changes among the intermediate stages. Although there has been an increase in research into the diagnosis of AD in its early levels of developments lately, brain changes, and their complexity for functional magnetic resonance imaging (fMRI), makes early detection of AD difficult. This paper proposes a deep learning-based method that can predict MCI, early MCI (EMCI), late MCI (LMCI), and AD. The Alzheimer's Disease Neuroimaging Initiative (ADNI) fMRI dataset consisting of 138 subjects was used for evaluation. The finetuned ResNet18 network achieved a classification accuracy of 99.99%, 99.95%, and 99.95% on EMCI vs. AD, LMCI vs. AD, and MCI vs. EMCI classification scenarios, respectively. The proposed model performed better than other known models in terms of accuracy, sensitivity, and specificity.

Mir-1, miR-122, miR-132, and miR-133 Are Related to Subclinical Aortic Atherosclerosis Associated with Metabolic Syndrome.

Previously, miR-1, miR-122, miR-126, miR-132, miR-133, and miR-370 were found to be related to coronary artery disease (CAD) progression. However, their relationship with subclinical atherosclerosis, especially in subjects with metabolic syndrome, is unknown. Therefore, our aim was to determine their relationship with arterial markers of subclinical atherosclerosis. Metabolic syndrome subjects (n = 182) with high cardiovascular risk but without overt cardiovascular disease (CVD) were recruited from the Lithuanian High Cardiovascular Risk (LitHiR) primary prevention program. The ardio-ankle vascular index (CAVI), augmentation index normalized to a heart rate of 75 bpm (AIxHR75), aortic pulse wave velocity (AoPWV), and carotid artery stiffness were assessed. MicroRNAs (miRs) were analyzed in serum. Pearson correlation and a univariate linear regression t-test showed that miR-1, miR-133b, and miR-133a were negatively associated with CAVI mean, whereas miR-122 was positively associated. MiR-1, miR-133b and miR-133a, and miR-145 were negatively associated with AIxHR75. MiR-122 correlated negatively with AoPWV. In multivariate linear regression models, miR-133b and miR-122 predicted CAVImean, miR-133 predicted AIxHR75, and miR-122 predicted AoPWV. MiR-132 predicted right carotid artery stiffness, and miR-1 predicted left carotid artery stiffness. The addition of smoking to miR-133b and miR-122 enhanced the prediction of CAVI. Age and triglycerides enhanced the prediction of AoPWV by miR-122. A cluster of four miRs are related to subclinical atherosclerosis in subjects with metabolic syndrome. Combined, they may have a more substantial diagnostic or prognostic value than any single miR. Future follow-up studies are needed to establish their clinical relevance.

Deep Learning Based Evaluation of Spermatozoid Motility for Artificial Insemination.

We propose a deep learning method based on the Region Based Convolutional Neural Networks (R-CNN) architecture for the evaluation of sperm head motility in human semen videos. The neural network performs the segmentation of sperm heads, while the proposed central coordinate tracking algorithm allows us to calculate the movement speed of sperm heads. We have achieved 91.77% (95% CI, 91.11-92.43%) accuracy of sperm head detection on the VISEM (A Multimodal Video Dataset of Human Spermatozoa) sperm sample video dataset. The mean absolute error (MAE) of sperm head vitality prediction was 2.92 (95% CI, 2.46-3.37), while the Pearson correlation between actual and predicted sperm head vitality was 0.969. The results of the experiments presented below will show the applicability of the proposed method to be used in automated artificial insemination workflow.

A Mobile Application for Smart Computer-Aided Self-Administered Testing of Cognition, Speech, and Motor Impairment.

We present a model for digital neural impairment screening and self-assessment, which can evaluate cognitive and motor deficits for patients with symptoms of central nervous system (CNS) disorders, such as mild cognitive impairment (MCI), Parkinson's disease (PD), Huntington's disease (HD), or dementia. The data was collected with an Android mobile application that can track cognitive, hand tremor, energy expenditure, and speech features of subjects. We extracted 238 features as the model inputs using 16 tasks, 12 of them were based on a self-administered cognitive testing (SAGE) methodology and others used finger tapping and voice features acquired from the sensors of a smart mobile device (smartphone or tablet). Fifteen subjects were involved in the investigation: 7 patients with neurological disorders (1 with Parkinson's disease, 3 with Huntington's disease, 1 with early dementia, 1 with cerebral palsy, 1 post-stroke) and 8 healthy subjects. The finger tapping, SAGE, energy expenditure, and speech analysis features were used for neural impairment evaluations. The best results were achieved using a fusion of 13 classifiers for combined finger tapping and SAGE features (96.12% accuracy), and using bidirectional long short-term memory (BiLSTM) (94.29% accuracy) for speech analysis features.