Autism Spectrum Disorders (ASD) is a collection of complicated neurological disorders that first show in early childhood. Electroencephalogram (EEG) signals are widely used to record the electrical activities of the brain. Manual screening is prone to human errors, tedious, and time-consuming. Hence, a novel automated method involving the Douglas-Peucker (DP) algorithm, sparse coding-based feature mapping approach, and deep convolutional neural networks (CNNs) is employed to detect ASD using EEG recordings. Initially, the DP algorithm is used for each channel to reduce the number of samples without degradation of the EEG signal. Then, the EEG rhythms are extracted by using the wavelet transform. The EEG rhythms are coded by using the sparse representation. The matching pursuit algorithm is used for sparse coding of the EEG rhythms. The sparse coded rhythms are segmented into 8 bits length and then converted to decimal numbers. An image is formed by concatenating the histograms of the decimated rhythm signals. Extreme learning machines (ELM)-based autoencoders (AE) are employed at a data augmentation step. After data augmentation, the ASD and healthy EEG signals are classified using pre-trained deep CNN models. Our proposed method yielded an accuracy of 98.88%, the sensitivity of 100% and specificity of 96.4%, and the F1-score of 99.19% in the detection of ASD automatically. Our developed model is ready to be tested with more EEG signals before its clinical application.

Nail psoriasis significantly impacts the quality of life in patients with psoriasis, which affects approximately 2-3% of the population worldwide. Disease severity measures are essential in guiding treatment and evaluation of therapeutic efficacy. However, due to subsidy, convenience and low costs of health care in Taiwan, doctor usually needs to manage nearly hundreds of patients in single outpatient clinic, leading to difficulty in performing complex assessment tools. For instance, Nail Psoriasis Severity index (NAPSI) is used by dermatologists to measure the severity of nail psoriasis in clinical trials, but its calculation is quite time-consuming, which hampers its application in daily clinical practice. Therefore, we developed a simple, fast and automatic system for the assessment of nail psoriasis severity by constructing a standard photography capturing system combined with utilizing one of the deep learning architectures, mask R-CNN. This system not only assist doctors in capturing signs of disease and normal skin, but also able to extract features without pre-processing of image data. Expectantly, the system could help dermatologists make accurate diagnosis, assessment as well as provide precise treatment decision more efficiently.

OBJECTIVE: Noninvasive screening of hypo- and hyperkalemia can prevent fatal arrhythmia in end-stage renal disease (ESRD) patients, but current methods for monitoring of serum potassium (K+) have important limitations. We investigated changes in nonlinear dynamics and morphology of the T wave in the electrocardiogram (ECG) of ESRD patients during hemodialysis (HD), assessing their relationship with K+ and designing a K+ estimator. METHODS: ECG recordings from twenty-nine ESRD patients undergoing HD were processed. T waves in 2-min windows were extracted at each hour during an HD session as well as at 48 h after HD start. T wave nonlinear dynamics were characterized by two indices related to the maximum Lyapunov exponent (λt, λwt) and a divergence-related index (η). Morphological variability in the T wave was evaluated by three time warping-based indices (dw, reflecting morphological variability in the time domain, and da and daNL, in the amplitude domain). K+was measured from blood samples extracted during and after HD. Stage-specific and patient-specific K+ estimators were built based on the quantified indices and leave-one-out cross-validation was performed separately for each of the estimators. RESULTS: The analyzed indices showed high inter-individual variability in their relationship with K+. Nevertheless, all of them had higher values at the HD start and 48 h after it, corresponding to the highest K+. The indices η and dw were the most strongly correlated with K+ (median Pearson correlation coefficient of 0.78 and 0.83, respectively) and were used in univariable and multivariable linear K+ estimators. Agreement between actual and estimated K+ was confirmed, with averaged errors over patients and time points being 0.000 ± 0.875 mM and 0.046 ± 0.690 mM for stage-specific and patient-specific multivariable K+ estimators, respectively. CONCLUSION: ECG descriptors of T wave nonlinear dynamics and morphological variability allow noninvasive monitoring of K+ in ESRD patients. SIGNIFICANCE: ECG markers have the potential to be used for hypo- and hyperkalemia screening in ESRD patients.

There has been recent success in prediction of the three-dimensional folded native structures of proteins, most famously by the AlphaFold Algorithm running on Google's/Alphabet's DeepMind computer. However, this largely involves machine learning of protein structures and is not a de novo protein structure prediction method for predicting three-dimensional structures from amino acid residue sequences. A de novo approach would be based almost entirely on general principles of energy and entropy that govern protein folding energetics, and importantly do so without the use of the amino acid sequences and structural features of other proteins. Most consider that problem as still unsolved even though it has occupied leading scientists for decades. Many consider that it remains one of the major outstanding issues in modern science. There is crucial continuing help from experimental findings on protein unfolding and refolding in the laboratory, but only to a limited extent because many researchers consider that the speed by which real proteins folds themselves, often from milliseconds to minutes, is itself still not fully understood. This is unfortunate, because a practical solution to the problem would probably have a major effect on personalized medicine, the pharmaceutical industry, biotechnology, and nanotechnology, including for example "smaller" tasks such as better modeling of flexible "unfolded" regions of the SARS-COV-2 spike glycoprotein when interacting with its cell receptor, antibodies, and therapeutic agents. Some important ideas from earlier studies are given before moving on to lessons from periodic and aperiodic crystals, and a possible role for quantum phenomena. The conclusion is that better computation of entropy should be the priority, though that is presented guardedly.

BACKGROUND: Interleukin 13 (IL-13) is an immunoregulatory cytokine, primarily released by activated T-helper 2 cells. IL-13 induces the pathogenesis of many allergic diseases, such as airway hyperresponsiveness, glycoprotein hypersecretion, and goblet cell hyperplasia. In addition, IL-13 inhibits tumor immunosurveillance, leading to carcinogenesis. Since elevated IL-13 serum levels are severe in COVID-19 patients, predicting IL-13 inducing peptides or regions in a protein is vital to designing safe protein therapeutics particularly immunotherapeutic. OBJECTIVE: The present study describes a method to develop, predict, design, and scan IL-13 inducing peptides. METHODS: The dataset experimentally validated 313 IL-13 inducing peptides, and 2908 non-inducing homo-sapiens peptides extracted from the immune epitope database (IEDB). A total of 95 key features using the linear support vector classifier with the L1 penalty (SVC-L1) technique was extracted from the originally generated 9165 features using Pfeature. These key features were ranked based on their prediction ability, and the top 10 features were used to build machine learning prediction models. Various machine learning techniques were deployed to develop models for predicting IL-13 inducing peptides. These models were trained, tested, and evaluated using five-fold cross-validation techniques; the best model was evaluated on an independent dataset. RESULTS: Our best model based on XGBoost achieves a maximum AUC of 0.83 and 0.80 on the training and independent dataset, respectively. Our analysis indicates that certain SARS-COV2 variants are more prone to induce IL-13 in COVID-19 patients. CONCLUSION: The best performing model was incorporated in web-server and standalone package named 'IL-13Pred' for precise prediction of IL-13 inducing peptides. For large dataset analysis standalone package of IL-13Pred is available at (https://webs.iiitd.edu.in/raghava/il13pred/) webserver and over GitHub link: https://github.com/raghavagps/il13pred.

OBJECTIVE: The current study aims to propose the auto-segmentation model on CT images of head and neck cancer using a stepwise deep neural network (stepwise-net). MATERIAL AND METHODS: Six normal tissue structures in the head and neck region of 3D CT images: Brainstem, optic nerve, parotid glands (left and right), and submandibular glands (left and right) were segmented with deep learning. In addition to a conventional convolutional neural network (CNN) on U-net, a stepwise neural network (stepwise-network) was developed. The stepwise-network was based on 3D FCN. We designed two networks in the stepwise-network. One is identifying the target region for the segmentation with the low-resolution images. Then, the target region is cropped, which used for the input image for the prediction of the segmentation. These were compared with a clinical used atlas-based segmentation. RESULTS: The DSCs of the stepwise-net was significantly higher than the atlas-based method for all organ at risk structures. Similarly, the JSCs of the stepwise-net was significantly higher than the atlas-based methods for all organ at risk structures. The Hausdorff distance (HD) was significantly smaller than the atlas-based method for all organ at-risk structures. For the comparison of the stepwise-net and U-net, the stepwise-net had a higher DSC and JSC and a smaller HD than the conventional U-net. CONCLUSIONS: We found that the stepwise-network plays a role is superior to conventional U-net-based and atlas-based segmentation. Our proposed model that is a potentially valuable method for improving the efficiency of head and neck radiotherapy treatment planning.

Motor Imagery Brain Computer Interface (MI-BCI) has become a promising technology in the field of neurorehabilitation. However, the performance and computational complexity of the current multiclass MI-BCI have not been fully optimized, and the intuitive interpretation of individual differences on motor imagery tasks is seldom investigated. In this paper, a well-designed multiscale time-frequency segmentation scheme is first applied to multichannel EEG recordings to obtain Time-Frequency Segments (TFSs). Then, the TFS selection based on a specific wrapper feature selection rule is utilized to determine optimum TFSs. Next, One-Versus-One (OvO)-divCSP implemented in divergence framework is used to extract discriminative features. Finally, One-Versus-Rest (OvR)-SVM is utilized to predict the class label based on selected multiclass MI features. Experimental results indicate our method yields a superior performance on two publicly available multiclass MI datasets with a mean accuracy of 80.00% and a mean kappa of 0.73. Meanwhile, the proposed TFS selection method can significantly alleviate the computational burden with little accuracy reduction, demonstrating the feasibility of real-time multiclass MI-BCI. Furthermore, the Motor Imagery Time-Frequency Reaction Map (MI-TFRM) is visualized, contributing to analyzing and interpreting the performance differences between different subjects.

Data mining has proven to be a reliable method to analyze and discover useful knowledge about various diseases, including cancer research. In particular, data mining and machine learning algorithms to study oral squamous cell carcinoma (OSCC), the most common form of oral cancer, is a new area of research. This malignant neoplasm can be studied using saliva samples. Saliva is an important biofluid that must be used to verify potential biomarkers associated with oral cancer. In this study, first, we provide an overview of OSSC diagnoses based on machine learning and salivary metabolites. To our knowledge, this is the first study to apply advanced data mining techniques to diagnose OSCC. Then, we give new results of classification and feature selection algorithms used to identify potential salivary biomarkers of OSCC. To accomplish this task, we used the filter feature selection random forest importance algorithm and a wrapper methodology to evaluate the importance of metabolites obtained from gas chromatography mass-spectrometry (GC-MS) in the context of differentiation of OSCC and the control group. Salivary samples (n = 68) were collected for the control group, and the OSCC group were from patients matched for gender, age, and smoking habit. The classification process occurred based on Random Forest (RF) classification algorithm along with 10-cross validation. The results showed that glucuronic acid, maleic acid, and batyl alcohol can classify the samples with an area under the curve (AUC) of 0.91 versus an AUC of 0.76 using all 51 metabolites analyzed. The methodology used in this study can assist healthcare professionals and be adopted to discover diagnostic biomarkers for other diseases.

The Legionellaceae group comprises the Legionella, containing 58 species with 70 serotypes. For instance, Legionella pneumophila is the deadliest serotype to cause Legionnaires infectious and is responsible for 90% of the infections in humans. The bacterial pathogen is associated with a severe lung infection, known as legionaries' disease. It is resistant to multiple drugs, thus warranting novel vaccine candidates identification to immune the host against infections caused by the said pathogen. For this, we applied the subtractive proteomics and reverse vaccinology approaches to annotate the most essential genes suitable for vaccine designing. From the whole proteome, only five proteins (Q5ZVG4, Q5ZRZ1, Q5ZWE6, Q5ZT09, and Q5ZUZ8) as the best targets for further processing as they fulfill all the standard parameters set for in silico vaccine design. Immuno-informatics approaches were further applied to the selected protein sequences to prioritized antigenic epitopes for design a multi-epitope subunit vaccine. A multi-epitopes vaccine was designed by using suitable linkers to link the CTL (cytotoxic T lymphocytes), HTL (Helper T lymphocytes), B cell epitopes, and adjuvant to strengthen the vaccine's immunogenicity. The MEVC(multi-epitopes vaccine construct) was reported to interact with human immune receptor TLR-2 (toll-like receptor) robustly (docking score = -357.18 kcal/mol), and a higher expression was achieved in the Escherichia coli system (CAI = 0.88, and GC contents = 54.34%). Moreover, immune simulation revealed that on the 3rd day, the neutralization of the antigen started, while on the 5th day, the antigen was completely neutralized by the secreted immune factors. In conclusion, the designed vaccine candidate effectively triggered the immune response against eh pathogen; however, wet lab-based experimentations are highly recommended to prove the protective immunological proficiency of the vaccine against L. pneumophila.

Massive evidence from all sources including zoology, neurobiology and immunology has confirmed that psychological factors can raise remarkable physiological effects. Researchers have long been aware of the potential value of these effects and wanted to harness them in the development of new drugs and therapies, for which the mechanism study is a necessary prerequisite. However, most of these studies are restricted to neuroscience, or starts with blood sample and fall into the area of immunity. In this study, we choose to focus on the psychological factor of happiness, mining existing publicly available single cell RNA sequencing (scRNA-seq) data for the expression of happiness-related genes collected from various sources of literature in all types of cells in the samples, finding that the expression of these genes is not restricted within neuro-regulated cells or tissue-resident immune cells, on the opposite, cell types that are unique to tissue and organ without direct regulation from nervous system account for the majority to express the happiness-related genes. Our research is a preliminary exploration of where our body respond to our mind at cell level, and lays the foundation for more detailed mechanism research.

OBJECTIVE: Negative schizophrenia (NSZ) and depressive disorder (DE) have many clinical similarities (e.g., lack of energy, social withdrawal). The purpose of this study was to explore microstate (MS) and scale-free dynamics of microstate sequence (SFML) in NSZ patients, DE patients and healthy controls (HC). METHODS: The subjects included 30 NSZ patients, 32 DE patients and 34 age-matched healthy controls. A resting-state electroencephalogram (rsEEG) was recorded under two conditions: (1) resting state with eyes opened (EO) and (2) resting state with eyes closed (EC). First, rsEEG signals were filtered into 1-45 Hz. Then, MS analysis was performed using the Microstate EEGLAB toolbox. Finally, the SFML feature of the sequence, which was transformed from the MS label sequence, was extracted by the Hurst exponent (HE). RESULTS: The rsEEG data of all subjects were clustered into six topographies. We could conclude that DE and NSZ patients show similar abnormalities in EO state. However, in the EC state, MS A, and B values were unique to NSZ patients, while DE patients had different values for MS C D and F. We also found a large correlation between these features and clinical information. In SFML, the Hurst exponent of the EO state might be more useful in assessing the characteristics of NSZ, while that of EC state can be used to understand these disorders with different random walk classifications. SIGNIFICANCE: The methods are associated with the ability to dynamically change of brain and information processing system. The MS and SFML of the EO state can be used to reflect the similar abnormalities of NSZ and DE patients. We recommend the EC state as the appropriate state to study the difference between the disorders. By combing the two states and these method, we can learn and study more similarities and differences between NSZ and DE.

Studying brain aging improves our understanding in differentiating typical and atypical aging. Directly utilizing traditional morphological features for brain age estimation did not show significant performance in healthy controls (HCs), which may be due to the negligence of the information of structural similarities among cortical regions. For this issue, the multi-feature-based network (MFN) built upon morphological features can be employed to describe these similarities. Based on this, we hypothesized that the MFN is more efficient and robust than traditional morphological features in brain age estimating. In this work, we used six different types of morphological features (i.e., cortical volume, cortical thickness, curvature index, folding index, local gyrification index, and surface area) to build individual MFN for brain age estimation. The efficacy of MFN was estimated on 2501 HCs with T1-weighted structural magnetic resonance imaging (sMRI) data and compared with traditional morphological features. We attained a mean absolute error (MAE) of 3.73 years using the proposed method on an independent test set, whereas a mean absolute error of 5.30 years was derived from morphological features. Our experimental results demonstrated that the MFN is an efficient and robust metric for estimating brain age.

BACKGROUND: Compulsive hand washing is one of the most frequent compulsions and includes highly ritualized, repetitive hand motions. Developing an algorithm that can automatically detect compulsive washing with off-the-shelf wearable devices is a first step toward developing more sophisticated sensor-based assessments and micro-interventions that might ultimately supplement cognitive behavioral therapy for obsessive-compulsive disorder (OCD). OBJECTIVE: The main objective was to establish whether enacted compulsive hand washing can be distinguished from routine hand washing. This distinction will inform future research on the development of an algorithm that can automatically detect compulsive hand washing. METHOD: Twenty-one participants were trained individually to wash their hands according to 1 of 5 scripted hand-washing procedures that were based on descriptions of pathological compulsive washes and additionally to wash their hands as they usually would, while wearing a smartwatch. Washes were video recorded to obtain validation data. To generate a baseline model, we opted to extract well-known features only (mean and variance of each sensor axis). We tested four classification models: linear support vector machine (SVM), SVM with radial basis functions, random forest (RF), and naive Bayes (NB). Leave-one-subject-out cross-validation was applied to gather F1, specificity, and sensitivity scores. RESULTS: The best-performing parameters were a classification window duration of 10 s, with a mean-variance feature set calculated from quaternions, rate of turn, and magnetic flux measurements. The detection performance varied with the particular enacted compulsive hand wash (F1 range: 0.65-0.87). Overall, enacted compulsive and routine hand washing could be distinguished with an F1 score of 79% (user independent), a sensitivity of 84%, and a specificity of 30%. CONCLUSIONS: Our analysis of the sensor data demonstrates that enacted compulsive hand washing could be distinguished from routine hand washing with acceptable sensitivity. However, specificity was low. This study is a starting point for a series of follow-ups, including the application in individuals diagnosed with OCD.

Nucleus detection is an important step for the analysis of histology images in the field of computational pathology. Pathologists use quantitative nuclear morphology for better cancer grading and prognostication. The nucleus detection becomes very challenging because of the large morphological variations across different types of nuclei, nuclei clutter, and heterogeneity. To address these challenges, we aim to improve the nucleus detection using multi-level feature fusion based on discriminative correlation filters. The proposed algorithm employs multiple features pool, based on varying features combinations. Early fusion is employed to integrate multi-feature information within a pool and inter-pool fusion is proposed to fuse information across multiple pools. Inter-pool consistency is proposed to find the pools which are consistent and complement each other to improve performance. For this purpose, the relative standard deviation is used as an inter-pool consistency measure. Pool robustness to noise is also estimated using relative standard deviation as a robustness measure. High-level pool fusion is proposed using inter-pool consistency and pool-robustness scores. The proposed algorithm facilitates a robust and reliable appearance model for nucleus detection. The proposed algorithm is evaluated on three publicly available datasets and compared with several existing state-of-the-art methods. Our proposed algorithm has consistently outperformed existing methods on a wide range of experiments.

Single-Cell RNA sequencing technology provides an opportunity to discover gene regulatory networks(GRN) that control cell differentiation and drive cell type transformation. However, it is faced with the challenge of high loss and high noise of sequencing data and contains many pseudo-connections. To solve these problems, we propose a framework called Fusion prior gene network for Gene Regulatory Network inference Accuracy Enhancement(FGRNAE) to infer a high reliable gene regulatory network. Specifically, based on the Single-Cell RNA-sequencing Network Propagation and network Fusion(scNPF) preprocessing framework, we employ the Random Walk with Restart on the prior gene network to interpolate the missing data. Furthermore, we infer the network using the Random Forest algorithm with the results achieved above. In addition, we apply data from the Co-Function Network to build a meta-gene network and select the regulatory connection with the Markov Random Field. Extensive experiments based on datasets from BEELINE validate the effectiveness of our framework for improving the accuracy of inference.

As a kind of novel non-invasive marker for molecular detection, cell-free DNA (cfDNA) has potential value for the early diagnosis of diseases, prognosis assessment, and efficacy monitoring. The constant developments in molecular biology detection technologies have led to an increase in clinical studies on the use of cfDNA detection methods for patients, and many gratifying outcomes have been achieved. In this review, the contributions of bioinformatics tools to the study of cfDNA are well discussed. The focus of the review is on cfDNA identification signals, cfDNA identification methods, and the relationship of cfDNA with human diseases such as hepatic cancer, lung cancer, end-stage kidney disease, and ischemic stroke. The research significance and existing problems of using cfDNA as a biomarker for diseases are also discussed.

Polyhistidine is among the cell-penetrating peptides that in an acidic environment can facilitate membrane transition. Keeping in mind that the pH of the tumor intercellular medium is ∼5.5, in this paper, we examined the functionalization of a convenient drug delivery vehicle with cell-penetrating poly(l-histidine) to provide a smart drug delivery system. Classical molecular dynamics and metadynamics simulations are used to investigate the interactions between doxorubicin, carbon nanotube, poly(l-histidine), and the cell membrane. Metadynamics simulation revealed that not only the global minimum of FES reduced in an acidic environment but also the difference between the free energy of Doxorubicin as being adsorbed on poly(l-histidine) compared to when being freely dissolved in the aqueous medium show a dramatic reduction. MD simulations showed that functionalization of carbon nanotube with poly(l-histidine) groups has no detriment effect in the adsorption of Doxorubicin. The L-J interaction between Doxorubicin and carrier at the equilibrium states reached around -600 kJ/mol, both for the pristine and functionalized carbon nanotube. The coulombic interactions for both complexes were negligible in the neutral environment. At the acidic environment, the L-J interactions retained the same values as the neutral, while the coulombic interactions showed positive values, which suggested its participation in the detachments. At the vicinity of the membrane, the complexes retain their integrity both in neutral and acidic environments. In the present work, we performed metadynamics simulation to investigate the effects of poly(l-histidine) on the adsorption capacity of the carbon nanotubes, and explore the adsorption/desorption processed of Doxorubicin on pristine and poly(l-histidine)-grafted carbon nanotube. The resulted complexes were then subjected to interact with the POPC membrane model in both acidic and neutral environments via molecular dynamic simulations. The results provided here will hopefully help in a better understanding of future drug delivery systems and be helpful in designing more efficient and smart drug delivery systems.

Temporal interference stimulation (TIS) has been proved to be effective in stimulating deep brain regions while avoiding the stimulation of neocortical regions in animal experiments. In the traditional TIS, two alternating currents are injected with different frequencies via two electrode pairs attached to the scalp. In the human brain, however, it is difficult to achieve a focal stimulation of deep brain structures due to the high complexity of human brain structures. In this study, we hypothesized that the use of multiple electrode pairs may contribute to the more focalized delivery of temporal interference (TI) currents to the target site in the deep area of the brain. Based on this hypothesis, we proposed a novel multipair TIS method that employs more than two electrode pairs for improved focalized stimulation of the deep brain region (in this study, the head of the right hippocampus). Three realistic finite element models were used to validate the feasibility of the proposed multipair TIS. Additional electrode pairs were sequentially added to the conventional two-electrode pairs with the aim of maximizing the delivery of TI currents to the target while minimizing TI currents in the neocortical regions. The results confirmed that the multipair TIS provides better focalized stimulation than the conventional two-pair TIS for all three head models. It is expected that the proposed multipair TIS can be used to enhance the effectiveness of noninvasive deep brain stimulation.

The COVID-19 (coronavirus disease 2019) pandemic affected more than 186 million people with over 4 million deaths worldwide by June 2021. The magnitude of which has strained global healthcare systems. Chest Computed Tomography (CT) scans have a potential role in the diagnosis and prognostication of COVID-19. Designing a diagnostic system, which is cost-efficient and convenient to operate on resource-constrained devices like mobile phones would enhance the clinical usage of chest CT scans and provide swift, mobile, and accessible diagnostic capabilities. This work proposes developing a novel Android application that detects COVID-19 infection from chest CT scans using a highly efficient and accurate deep learning algorithm. It further creates an attention heatmap, augmented on the segmented lung parenchyma region in the chest CT scans which shows the regions of infection in the lungs through an algorithm developed as a part of this work, and verified through radiologists. We propose a novel selection approach combined with multi-threading for a faster generation of heatmaps on a Mobile Device, which reduces the processing time by about 93%. The neural network trained to detect COVID-19 in this work is tested with a F1 score and accuracy, both of 99.58% and sensitivity of 99.69%, which is better than most of the results in the domain of COVID diagnosis from CT scans. This work will be beneficial in high-volume practices and help doctors triage patients for the early diagnosis of COVID-19 quickly and efficiently.

Recently, a large number of studies have indicated that circRNAs with covalently closed loops play important roles in biological processes and have potential as diagnostic biomarkers. Therefore, research on the circRNA-disease relationship is helpful in disease diagnosis and treatment. However, traditional biological verification methods require considerable labor and time costs. In this paper, we propose a new computational method (RGCNCDA) to predict circRNA-disease associations based on relational graph convolutional networks (R-GCNs). The method first integrates the circRNA similarity network, miRNA similarity network, disease similarity network and association networks among them to construct a global heterogeneous network. Then, it employs the random walk with restart (RWR) and principal component analysis (PCA) models to learn low-dimensional and high-order information from the global heterogeneous network as the topological features. Finally, a prediction model based on an R-GCN encoder and a DistMult decoder is built to predict the potential disease-associated circRNA. The predicted results demonstrate that RGCNCDA performs significantly better than the other six state-of-the-art methods in a 5-fold cross validation. Furthermore, the case study illustrates that RGCNCDA can effectively discover potential circRNA-disease associations.

BACKGROUND: The world has been suffering from the COVID-19 pandemic since 2019. More than 5 million people have died. Pneumonia is caused by the COVID-19 virus, which can be diagnosed using chest X-ray and computed tomography (CT) scans. COVID-19 also causes clinical and subclinical cardiovascular injury that may be detected on electrocardiography (ECG), which is easily accessible. METHOD: For ECG-based COVID-19 detection, we developed a novel attention-based 3D convolutional neural network (CNN) model with residual connections (RC). In this paper, the deep learning (DL) approach was developed using 12-lead ECG printouts obtained from 250 normal subjects, 250 patients with COVID-19 and 250 with abnormal heartbeat. For binary classification, the COVID-19 and normal classes were considered; and for multiclass classification, all classes. The ECGs were preprocessed into standard ECG lead segments that were channeled into 12-dimensional volumes as input to the network model. Our developed model comprised of 19 layers with three 3D convolutional, three batch normalization, three rectified linear unit, two dropouts, two additional (for residual connections), one attention, and one fully connected layer. The RC were used to improve gradient flow through the developed network, and attention layer, to connect the second residual connection to the fully connected layer through the batch normalization layer. RESULTS: A publicly available dataset was used in this work. We obtained average accuracies of 99.0% and 92.0% for binary and multiclass classifications, respectively, using ten-fold cross-validation. Our proposed model is ready to be tested with a huge ECG database.

Data with finite samples results in accuracy and robustness reduction of data covariance matrix estimation, which in turn results in performance reduction of minimum variance beamformer (MVB) for brain source localization (BSL). General linear combination (GLC) and convex combination (CC) are methods of interest for data covariance matrix estimation and increasing its accuracy and robustness because their scalar coefficients are obtained automatically and adaptively. However, based on our best knowledge, the applicability of GLC and CC algorithms has not been investigated for BSL to inform us about their performance. In this paper, we have two goals: 1) Investigation of GLC and CC covariance matrices applications for BSL is carried out using various simulated MEG scenarios and real MEG and clinical epilepsy data; 2) Modified GLC and CC are developed for more accurate and robust estimation of data covariance matrix when data with finite samples is available. In the modified versions, the scalar coefficients are replaced by diagonal matrix form coefficients. These matrix form coefficients are computed using the Hadamard product and mean square error concept. The evaluations show that the CC and modified CC based MVBs are not robust for BSL due to very small values of coefficients. Based on the simulated, real, and clinical data results, it can be stated that the modified GLC is significantly superior to conventional GLC in terms of localization error, spatial resolution (all z < -2; all p-values < 0.001), and offering reliable results. Also, the proposed GLC offers fewer missed sources and less sensitivity to the depth biasing problem, particularly in a high signal-to-noise ratio. In conclusion, it can be said that the covariance matrix of modified GLC which is user-free and robust against the finite data samples can improve the MVB performance for BSL in terms of localization error and spatial resolution.

BACKGROUND: The main screening parameter to monitor prostate cancer recurrence (PCR) after primary treatment is the serum concentration of prostate-specific antigen (PSA). In recent years, Ga-68-PSMA PET/CT has become an important method for additional diagnostics in patients with biochemical recurrence. PURPOSE: While Ga-68-PSMA PET/CT performs better, it is an expensive, invasive, and time-consuming examination. Therefore, in this study, we aim to employ modern multivariate Machine Learning (ML) methods on electronic health records (EHR) of prostate cancer patients to improve the prediction of imaging confirmed PCR (IPCR). METHODS: We retrospectively analyzed the clinical information of 272 patients, who were examined using Ga-68-PSMA PET/CT. The PSA values ranged from 0 ng/mL to 2270.38 ng/mL with a median PSA level at 1.79 ng/mL. We performed a descriptive analysis using Logistic Regression. Additionally, we evaluated the predictive performance of Logistic Regression, Support Vector Machine, Gradient Boosting, and Random Forest. Finally, we assessed the importance of all features using Ensemble Feature Selection (EFS). RESULTS: The descriptive analysis found significant associations between IPCR and logarithmic PSA values as well as between IPCR and performed hormonal therapy. Our models were able to predict IPCR with an AUC score of 0.78 ± 0.13 (mean ± standard deviation) and a sensitivity of 0.997 ± 0.01. Features such as PSA, PSA doubling time, PSA velocity, hormonal therapy, radiation treatment, and injected activity show high importance for IPCR prediction using EFS. CONCLUSION: This study demonstrates the potential of employing a multitude of parameters into multivariate ML models to improve identification of non-recurring patients compared to the current focus on the main screening parameter (PSA). We showed that ML models are able to predict IPCR, detectable by Ga-68-PSMA PET/CT, and thereby pave the way for optimized early imaging and treatment.

Deep learning (DL) technologies have recently shown great potential in emotion recognition based on electroencephalography (EEG). However, existing DL-based EEG emotion recognition methods are built on single-task learning, i.e., learning arousal, valence, and dominance individually, which may ignore the complementary information of different tasks. In addition, single-task learning involves a new round of training every time a new task appears, which is time consuming. To this end, we propose a novel method for EEG-based emotion recognition based on multi-task learning with capsule network (CapsNet) and attention mechanism. First, multi-task learning can learn multiple tasks simultaneously while exploiting commonalities and differences across tasks, it can also obtain more data from different tasks, which can improve generalization and robustness. Second, the innovative structure of the CapsNet enables it to effectively characterize the intrinsic relationship among various EEG channels. Finally, the attention mechanism can change the weight of different channels to extract important information. In the DEAP dataset, the average accuracy reached 97.25%, 97.41%, and 98.35% on arousal, valence, and dominance, respectively. In the DREAMER dataset, average accuracy reached 94.96%, 95.54%, and 95.52% on arousal, valence, and dominance, respectively. Experimental results demonstrate the efficiency of the proposed method for EEG emotion recognition.

BACKGROUND: Artificial intelligence (AI) has become a prominent technique for medical diagnosis and represents an essential role in detecting brain tumors. Although AI-based models are widely used in brain lesion segmentation (BLS), understanding their effectiveness is challenging due to their complexity and diversity. Several reviews on brain tumor segmentation are available, but none of them describe a link between the threats due to risk-of-bias (RoB) in AI and its architectures. In our review, we focused on linking RoB and different AI-based architectural Cluster in popular DL framework. Further, due to variance in these designs and input data types in medical imaging, it is necessary to present a narrative review considering all facets of BLS. APPROACH: The proposed study uses a PRISMA strategy based on 75 relevant studies found by searching PubMed, Scopus, and Google Scholar. Based on the architectural evolution, DL studies were subsequently categorized into four classes: convolutional neural network (CNN)-based, encoder-decoder (ED)-based, transfer learning (TL)-based, and hybrid DL (HDL)-based architectures. These studies were then analyzed considering 32 AI attributes, with clusters including AI architecture, imaging modalities, hyper-parameters, performance evaluation metrics, and clinical evaluation. Then, after these studies were scored for all attributes, a composite score was computed, normalized, and ranked. Thereafter, a bias cutoff (AP(ai)Bias 1.0, AtheroPoint, Roseville, CA, USA) was established to detect low-, moderate- and high-bias studies. CONCLUSION: The four classes of architectures, from best-to worst-performing, are TL > ED > CNN > HDL. ED-based models had the lowest AI bias for BLS. This study presents a set of three primary and six secondary recommendations for lowering the RoB.

MRI is an inherently slow process, which leads to long scan time for high-resolution imaging. The speed of acquisition can be increased by ignoring parts of the data (undersampling). Consequently, this leads to the degradation of image quality, such as loss of resolution or introduction of image artefacts. This work aims to reconstruct highly undersampled Cartesian or radial MR acquisitions, with better resolution and with less to no artefact compared to conventional techniques like compressed sensing. In recent times, deep learning has emerged as a very important area of research and has shown immense potential in solving inverse problems, e.g. MR image reconstruction. In this paper, a deep learning based MR image reconstruction framework is proposed, which includes a modified regularised version of ResNet as the network backbone to remove artefacts from the undersampled image, followed by data consistency steps that fusions the network output with the data already available from undersampled k-space in order to further improve reconstruction quality. The performance of this framework for various undersampling patterns has also been tested, and it has been observed that the framework is robust to deal with various sampling patterns, even when mixed together while training, and results in very high quality reconstruction, in terms of high SSIM (highest being 0.990 ± 0.006 for acceleration factor of 3.5), while being compared with the fully sampled reconstruction. It has been shown that the proposed framework can successfully reconstruct even for an acceleration factor of 20 for Cartesian (0.968 ± 0.005) and 17 for radially (0.962 ± 0.012) sampled data. Furthermore, it has been shown that the framework preserves brain pathology during reconstruction while being trained on healthy subjects.

BACKGROUND: An increasing number of wearables are capable of measuring electrocardiograms (ECGs), which may help in early detection of atrial fibrillation (AF). Therefore, many studies focus on automated detection of AF in ECGs. A major obstacle is the required amount of manually labelled data. This study aimed to provide an efficient and reliable method to train a classifier for AF detection using large datasets of real-life ECGs. METHOD: Human-controlled semi-supervised learning was applied, consisting of two phases: the pre-training phase and the semi-automated training phase. During pre-training, an initial classifier was trained, which was used to predict the classes of new ECG segments in the semi-automated training phase. Based on the degree of certainty, segments were added to the training dataset automatically or after human validation. Thereafter, the classifier was retrained and this procedure was repeated. To test the model performance, a real-life telemetry dataset containing 3,846,564 30-s ECG segments of hospitalized patients (n = 476) and the CinC Challenge 2017 database were used. RESULTS: After pre-training, the average F1-score on a hidden testing dataset was 89.0%. Furthermore, after the pre-training phase 68.0% of all segments in the hidden test set could be classified with an estimated probability of successful classification of 99%, providing an F1-score of 97.9% for these segments. During the semi-automated training phase, this F1-score showed little variation (97.3%-97.9% in the hidden test set), whilst the number of segments which could be automatically classified increased from 68.0% to 75.8% due to the enhanced training dataset. At the same time, the overall F1-score increased from 89.0% to 91.4%. CONCLUSIONS: Human-validated semi-supervised learning makes training a classifier more time efficient without compromising on accuracy, hence this method might be valuable in the automated detection of AF in real-life ECGs.

BACKGROUND AND AIMS: Machine Learning is transforming data processing in medical research and clinical practice. Missing data labels are a common limitation to training Machine Learning models. To overcome missing labels in a large dataset of microneurography recordings, a novel autoencoder based semi-supervised, iterative group-labelling methodology was developed. METHODS: Autoencoders were systematically optimised to extract features from a dataset of 478621 signal excerpts from human microneurography recordings. Selected features were clusters with k-means and randomly selected representations of the corresponding original signals labelled as valid or non-valid muscle sympathetic nerve activity (MSNA) bursts in an iterative, purifying procedure by an expert rater. A deep neural network was trained based on the fully labelled dataset. RESULTS: Three autoencoders, two based on fully connected neural networks and one based on convolutional neural network, were chosen for feature learning. Iterative clustering followed by labelling of complete clusters resulted in all 478621 signal peak excerpts being labelled as valid or non-valid within 13 iterations. Neural networks trained with the labelled dataset achieved, in a cross validation step with a testing dataset not included in training, on average 93.13% accuracy and 91% area under the receiver operating curve (AUC ROC). DISCUSSION: The described labelling procedure enabled efficient labelling of a large dataset of physiological signal based on expert ratings. The procedure based on autoencoders may be broadly applicable to a wide range of datasets without labels that require expert input and may be utilised for Machine Learning applications if weak-labels were available.

This paper reviews some basic principles of Quantum Mechanics, Quantum Computing, and Artificial Intelligence in terms of a specific unifying theme. This theme relates to the hyperbolic or split-complex imaginary numbers and their equivalent matrices, rediscovered by Dirac, and the underlying mathematics of the previously described Q-UEL language based on them. Hyperbolic imaginary numbers h have the property hh = +1: contrast the more familiar i such that ii = -1. Examples of analogous matrices include that for the Hadamard gate as used in quantum computing and the Pauli spin matrices, and all Hermitian matrices of interest in quantum computing can readily be derived from these. They also relate to Dirac dualization, spinor projectors of Quantum Field Theory, the non-wave-like part of quantum theory, collapse of the wave function, and a dualized form of classical probability theory that has advantages in automated reasoning for medicine.

Diabetic retinopathy is an increasingly prevalent eye disorder that can lead to severe vision impairment. The severity grading of the disease using retinal images is key to provide an adequate treatment. However, in order to learn the diverse patterns and complex relations that are required for the grading, deep neural networks require very large annotated datasets that are not always available. This has been typically addressed by reusing networks that were pre-trained for natural image classification, hence relying on additional annotated data from a different domain. In contrast, we propose a novel pre-training approach that takes advantage of unlabeled multimodal visual data commonly available in ophthalmology. The use of multimodal visual data for pre-training purposes has been previously explored by training a network in the prediction of one image modality from another. However, that approach does not ensure a broad understanding of the retinal images, given that the network may exclusively focus on the similarities between modalities while ignoring the differences. Thus, we propose a novel self-supervised pre-training that explicitly teaches the networks to learn the common characteristics between modalities as well as the characteristics that are exclusive to the input modality. This provides a complete comprehension of the input domain and facilitates the training of downstream tasks that require a broad understanding of the retinal images, such as the grading of diabetic retinopathy. To validate and analyze the proposed approach, we performed an exhaustive experimentation on different public datasets. The transfer learning performance for the grading of diabetic retinopathy is evaluated under different settings while also comparing against previous state-of-the-art pre-training approaches. Additionally, a comparison against relevant state-of-the-art works for the detection and grading of diabetic retinopathy is also provided. The results show a satisfactory performance of the proposed approach, which outperforms previous pre-training alternatives in the grading of diabetic retinopathy.

We created a deep learning model, trained on text classified by natural language processing (NLP), to assess right ventricular (RV) size and function from echocardiographic images. We included 12,684 examinations with corresponding written reports for text classification. After manual annotation of 1489 reports, we trained an NLP model to classify the remaining 10,651 reports. A view classifier was developed to select the 4-chamber or RV-focused view from an echocardiographic examination (n = 539). The final models were two image classification models trained on the predicted labels from the combined manual annotation and NLP models and the corresponding echocardiographic view to assess RV function (training set n = 11,008) and size (training set n = 9951. The text classifier identified impaired RV function with 99% sensitivity and 98% specificity and RV enlargement with 98% sensitivity and 98% specificity. The view classification model identified the 4-chamber view with 92% accuracy and the RV-focused view with 73% accuracy. The image classification models identified impaired RV function with 93% sensitivity and 72% specificity and an enlarged RV with 80% sensitivity and 85% specificity; agreement with the written reports was substantial (both κ = 0.65). Our findings show that models for automatic image assessment can be trained to classify RV size and function by using model-annotated data from written echocardiography reports. This pipeline for auto-annotation of the echocardiographic images, using a NLP model with medical reports as input, can be used to train an image-assessment model without manual annotation of images and enables fast and inexpensive expansion of the training dataset when needed.

Pulse diagnosis (PD) plays an indispensable role in healthcare in China, India, Korea, and other Orient countries. It requires considerable training and experience to master. The results of pulse diagnosis rely heavily on the practitioner's subjective analysis, which means that the results from different physicians may be inconsistent. To overcome these drawbacks, computational pulse diagnosis (CPD) is used with advanced sensing techniques and analytical methods. Focusing on the main processes of CPD, this paper provides a systematic review of the latest advances in pulse signal acquisition, signal preprocessing, feature extraction, and signal recognition. The most relevant principles and applications are presented along with current progress. Extensive comparisons and analyses are conducted to evaluate the merits of different methods employed in CPD. While much progress has been made, a lack of datasets and benchmarks has limited the development of CPD. To address this gap and facilitate further research, we present a benchmark to evaluate different methods. We conclude with observations of the status and prospects of CPD.

BACKGROUND: This study aims to achieve an automatic differential diagnosis between two types of retinal pathologies with similar pathological features - Polypoidal choroidal vasculopathy (PCV) and wet age-related macular degeneration (AMD) from volumetric optical coherence tomography (OCT) images, and identify clinically-relevant pathological features, using an explainable deep-learning-based framework. METHODS: This is a retrospective study with data from a cross-sectional cohort. The OCT volume of 73 eyes from 59 patients was included in this study. Disease differentiation was achieved through single-B-scan-based classification followed by a volumetric probability prediction aggregation step. We compared different labeling strategies with and without identifying pathological B-scans within each OCT volume. Clinical interpretability was achieved through normalized aggregation of B-scan-based saliency maps followed by maximum-intensity-projection onto the en face plane. We derived the PCV score from the proposed differential diagnosis framework with different labeling strategies. The en face projection of saliency map was validated with the pathologies identified in Indocyanine green angiography (ICGA). RESULTS: Model trained with both labeling strategies achieved similar level differentiation power (>90%), with good correspondence between pathological features detected from the projected en face saliency map and ICGA. CONCLUSIONS: This study demonstrated the potential clinical application of non-invasive differential diagnosis using AI-driven OCT-based analysis, with minimal requirement of labeling efforts, along with clinical explainability achieved through automatically detected disease-related pathologies.

Biomechanical changes at the adjacent segments after interbody fusion are common instigators of adjacent segment degeneration (ASD). This study aims to investigate how the presence of a lordotic porous cage affects the biomechanical performance of the adjacent segments. A finite element model (FEM) of a lumbar spine implanted with a lordotic cage at L3-L4 was validated by in-vitro testing. The stress distribution on the cage and range of motion (ROM) of L3-L4 were used to assess the stability of the implant. Three angles of cage (0° = non-restoration, 7° = normal restoration and 11° = over-restoration) were modelled with different porosities (0%, 30% and 60%) and evaluated in the motions of flexion, extension, lateral bending and rotation. The ROM, intervertebral disc pressure (IDP) and facet joint force (FJF) were used to evaluate biomechanical changes at the adjacent segments in each model. The results indicated that porous cages produced more uniform stress distribution, but cage porosity did not influence the ROM, IDP and FJF at L2-L3 and L4-L5. Increasing the cage lordotic angle acted to decrease the ROM and IDP, and increase the FJF of L4-L5, but did not alter the ROM of L2-L3. In conclusion, changes in ROM, IDP and FJF at the adjacent segments were mainly influenced by the lordotic angle of the cage and not by the porosity. A larger angle of lordotic cage was shown to reduce the ROM and IDP, and increase the FJF of the lower segment (L4-L5), but had little effect on the ROM of the upper segment (L2-L3).

As continuous glucose monitoring (CGM) sensors generate ever increasing amounts of CGM data, the need for methods to simplify the storage and analysis of this data becomes increasingly important. Lobo et al. developed a classifier of daily CGM profiles as an initial step in addressing this need. The classifier has several important applications including, but not limited to, data compression, data encryption, and indexing of databases. While the classifier has already successfully classified 99.0% of the 42,595 daily CGM profiles in a Test Set, this work presents an external validation using an external validation set (EVal Set) derived from 8 publicly available data sets. The Test Set and the EVal Set differ in terms of (but not limited to) demographics, data collection time periods, and data collection geographies. The classifier successfully classified 98.2% of the 137,030 daily CGM profiles in the EVal Set. Furthermore, each of the 483 distinct groups of classified daily CGM profiles from the EVal Set retains the same clinical characteristics as the corresponding group from the Test Set, as desired. Finally, the set of unclassified daily CGM profiles from the EVal Set retains the same statistical characteristics as the set of unclassified daily CGM profiles from the Test Set, as desired. These results establish the robustness and generalizability of the classifier: the performance of the classifier is unchanged despite the marked differences between the Test Set and the EVal Set.

The reverse transcription-polymerase chain reaction (RT-PCR) test is considered the current gold standard for the detection of coronavirus disease (COVID-19), although it suffers from some shortcomings, namely comparatively longer turnaround time, higher false-negative rates around 20-25%, and higher cost equipment. Therefore, finding an efficient, robust, accurate, and widely available, and accessible alternative to RT-PCR for COVID-19 diagnosis is a matter of utmost importance. This study proposes a complete blood count (CBC) biomarkers-based COVID-19 detection system using a stacking machine learning (SML) model, which could be a fast and less expensive alternative. This study used seven different publicly available datasets, where the largest one consisting of fifteen CBC biomarkers collected from 1624 patients (52% COVID-19 positive) admitted at San Raphael Hospital, Italy from February to May 2020 was used to train and validate the proposed model. White blood cell count, monocytes (%), lymphocyte (%), and age parameters collected from the patients during hospital admission were found to be important biomarkers for COVID-19 disease prediction using five different feature selection techniques. Our stacking model produced the best performance with weighted precision, sensitivity, specificity, overall accuracy, and F1-score of 91.44%, 91.44%, 91.44%, 91.45%, and 91.45%, respectively. The stacking machine learning model improved the performance in comparison to other state-of-the-art machine learning classifiers. Finally, a nomogram-based scoring system (QCovSML) was constructed using this stacking approach to predict the COVID-19 patients. The cut-off value of the QCovSML system for classifying COVID-19 and Non-COVID patients was 4.8. Six datasets from three different countries were used to externally validate the proposed model to evaluate its generalizability and robustness. The nomogram demonstrated good calibration and discrimination with the area under the curve (AUC) of 0.961 for the internal cohort and average AUC of 0.967 for all external validation cohort, respectively. The external validation shows an average weighted precision, sensitivity, F1-score, specificity, and overall accuracy of 92.02%, 95.59%, 93.73%, 90.54%, and 93.34%, respectively.

In the Motor Imagery (MI)-based Brain Computer Interface (BCI), users' intention is converted into a control signal through processing a specific pattern in brain signals reflecting motor characteristics. There are such restrictions as the limited size of the existing datasets and low signal to noise ratio in the classification of MI Electroencephalogram (EEG) signals. Machine learning (ML) methods, particularly Deep Learning (DL), have overcome these limitations relatively. In this study, three hybrid models were proposed to classify the EEG signal in the MI-based BCI. The proposed hybrid models consist of the convolutional neural networks (CNN) and the Long-Short Term Memory (LSTM). In the first model, the CNN with different number of convolutional-pooling blocks (from shallow to deep CNN) was examined; a two-block CNN model not affected by the vanishing gradient descent and yet able to extract desirable features employed; the second and third models contained pre-trained CNNs conducing to the exploration of more complex features. The transfer learning strategy and data augmentation methods were applied to overcome the limited size of the datasets by transferring learning from one model to another. This was achieved by employing two powerful pre-trained convolutional neural networks namely ResNet-50 and Inception-v3. The continuous wavelet transform (CWT) was used to generate images for the CNN. The performance of the proposed models was evaluated on the BCI Competition IV dataset 2a. The mean accuracy vlaues of 86%, 90%, and 92%, and mean Kappa values of 81%, 86%, and 88% were obtained for the hybrid neural network with the customized CNN, the hybrid neural network with ResNet-50 and the hybrid neural network with Inception-v3, respectively. Despite the promising performance of the three proposed models, the hybrid neural network with Inception-v3 outperformed the two other models. The best obtained result in the present study improved the previous best result in the literature by 7% in terms of classification accuracy. From the findings, it can be concluded that transfer learning based on a pre-trained CNN in combination with LSTM is a novel method in MI-based BCI. The study also has implications for the discrimination of motor imagery tasks in each EEG recording channel and in different brain regions which can reduce computational time in future works by only selecting the most effective channels.

Atrial fibrillation (AF) is the most sustained arrhythmia in the heart and also the most common complication developed after cardiac surgery. Due to its progressive nature, timely detection of AF is important. Currently, physicians use a surface electrocardiogram (ECG) for AF diagnosis. However, when the patient develops AF, its various development stages are not distinguishable for cardiologists based on visual inspection of the surface ECG signals. Therefore, severity detection of AF could start from differentiating between short-lasting AF and long-lasting AF. Here, de novo post-operative AF (POAF) is a good model for short-lasting AF while long-lasting AF can be represented by persistent AF. Therefore, we address in this paper a binary severity detection of AF for two specific types of AF. We focus on the differentiation of these two types as de novo POAF is the first time that a patient develops AF. Hence, comparing its development to a more severe stage of AF (e.g., persistent AF) could be beneficial in unveiling the electrical changes in the atrium. To the best of our knowledge, this is the first paper that aims to differentiate these different AF stages. We propose a method that consists of three sets of discriminative features based on fundamentally different aspects of the multi-channel ECG data, namely based on the analysis of RR intervals, a greyscale image representation of the vectorcardiogram, and the frequency domain representation of the ECG. Due to the nature of AF, these features are able to capture both morphological and rhythmic changes in the ECGs. Our classification system consists of a random forest classifier, after a feature selection stage using the ReliefF method. The detection efficiency is tested on 151 patients using 5-fold cross-validation. We achieved 89.07% accuracy in the classification of de novo POAF and persistent AF. The results show that the features are discriminative to reveal the severity of AF. Moreover, inspection of the most important features sheds light on the different characteristics of de novo post-operative and persistent AF.

The L4-L5 spinal segment is mostly associated with the development of lumbar back pain (LBP). Lumbar disc herniation (LDH), intervertebral disc degeneration (IVDD), or degeneration of the facet joints (FJs) can lead to LBP. Although the surgical gold standard for treating LDH is well established, consequences from this surgery on the biomechanics of the spine are still a matter of discussion. Using a finite element model of the L4-L5 spinal segment, this study aimed (1) to determine the changes in FJ distance during physiological motions of a lumbar spine in a healthy-normal condition, after conservative and aggressive percutaneous transforaminal endoscopic discectomy (PTED) to correct LDH, and during mild and severe IVDD; (2) to determine spine instability and endplate stresses under various physiological motions. Aggressive-PTED in a healthy disc decreased facet distances in axial rotation, lateral bending, and flexion by ∼25%, ∼10%, and 8%, respectively. Mild and severe disc degeneration increased the stiffness of the spine, resulting in a decrease in the range of motion (ROM) for all conditions. Severe disc degeneration decreased ROM as high as 57% for lateral bending, while a 13% decrease was observed for mild degeneration. High and abnormal endplate stress distributions were observed due to PTED and IVDD. PTED and IVDD, individually and collectively, change spine kinematics potentially leading to LBP and other associated negative outcomes. An increase in spine instability and a decrease in distance between superior and inferior facets resulting from PTED might lead to facet degeneration.