A computational clinical decision-supporting system to suggest effective anti-epileptic drugs for pediatric epilepsy patients based on deep learning models using patient's medical history.

BACKGROUND: Epilepsy, a chronic brain disorder characterized by abnormal brain activity that causes seizures and other symptoms, is typically treated using anti-epileptic drugs (AEDs) as the first-line therapy. However, due to the variations in their modes of action, identification of effective AEDs often relies on ad hoc trials, which is particularly challenging for pediatric patients. Thus, there is significant value in computational methods capable of assisting in the selection of AEDs, aiming to minimize unnecessary medication and improve treatment efficacy. RESULTS: In this study, we collected 7,507 medical records from 1,000 pediatric epilepsy patients and developed a computational clinical decision-supporting system for AED selection. This system leverages three multi-channel convolutional neural network (CNN) models tailored to three specific AEDs (vigabatrin, prednisolone, and clobazam). Each CNN model predicts whether a respective AED is effective on a given patient or not. The CNN models showed AUROCs of 0.90, 0.80, and 0.92 in 10-fold cross-validation, respectively. Evaluation on a hold-out test dataset further revealed positive predictive values (PPVs) of 0.92, 0.97, and 0.91 for the three respective CNN models, representing that suggested AEDs by our models would be effective in controlling epilepsy with a high accuracy and thereby reducing unnecessary medications for pediatric patients. CONCLUSION: Our CNN models in the system demonstrated high PPVs for the three AEDs, which signifies the potential of our approach to support the clinical decision-making by assisting doctors in recommending effective AEDs within the three AEDs for patients based on their medical history. This would result in a reduction in the number of unnecessary ad hoc attempts to find an effective AED for pediatric epilepsy patients.

Exploring the Design of Upper Limb Strength Training Through High-Intensity Interval Training Combined With Exergaming: Usability Study.

Background: High-intensity interval training (HIIT) has become a popular exercise strategy in modern society, with the Tabata training method being the most popular. In the past, these training methods were mostly done without equipment, but incorporating exergaming into the training may provide a new option for muscle training. objectives: The aim of this study was to explore the differences in upper limb muscle activation using an HIIT program combined with exergaming. Methods: A total of 15 healthy male participants were recruited for the study, and the differences in muscle activation were compared between push-ups and exergaming (Nintendo Switch Ring Fit Adventure with the Ring-Con accessory) during HIIT. Prior to the tests, participants underwent pretests, including maximal voluntary contractions of various muscle groups, maximal push-up tests, and maximal movement tests using the exergaming device. The push-up and exergaming tests were conducted on separate days to avoid interference, with a warm-up period of 5 minutes on a treadmill before testing. Muscle activation in the lateral and anterior portions of the deltoid muscle, the sternal and clavicular heads of the pectoralis major muscle, and the latissimus dorsi muscle were measured during the maximal voluntary contractions and single-round tests for each exercise mode. A repeated measures ANOVA was used to assess the variations in muscle activation observed across the 2 distinct modes of exercise, specifically push-ups and exergaming. Results: In exergaming, the number of repetitions for push-ups was significantly fewer than for single-site exercises across both exhaustive (mean 23.13, SD 6.36 vs mean 55.67, SD 17.83; P=.001; effect size [ES]: 2.43) and single-round (mean 21.93, SD 7.67 vs mean 92.40, SD 20.47; P=.001; ES: 4.56) training. Heart rate differences were not significant (all P>.05), yet exergaming led to better muscle activation in specific muscle groups, particularly the right anterior deltoid (mean 48.00%, SD 7.66% vs mean 32.84%, SD 10.27%; P=.001; ES: 1.67) and right pectoralis major (sternal head: mean 38.99%, SD 9.98% vs mean 26.90%, SD 12.97%; P=.001; ES: 1.04; clavicular head: mean 43.54%, SD 9.59% vs mean 30.09%, SD 11.59%; P=.002; ES: 1.26) during exhaustive training. In single-round training, similar patterns were observed with the anterior deltoid (mean 51.37%, SD 11.76% vs mean 35.47%, SD 12.72%; P=.002; ES: 1.30) and pectoralis major (sternal head: mean 53.27%, SD 10.79% vs mean 31.56%, SD 16.92%; P=.001; ES: 1.53; clavicular head: mean 53.75%, SD 13.01% vs mean 37.95%, SD 14.67%; P=.006; ES: 1.14). These results suggest that exergaming may be more effective for targeted muscle activation. Conclusions: In conclusion, HIIT can increase muscle activation in the upper extremities and can be incorporated into exergaming strategies to provide a fun and engaging way to exercise.

Design and Analysis of Reconfigurable Origami-Based Vacuum Pneumatic Artificial Muscles for Versatile Robotic System.

In this study, a vacuum-based modular actuator system named reconfigurable origami-based vacuum pneumatic artificial muscles (ROV-PAMs) is presented. The system consists of six types of actuating modules and three types of fluidic supporting modules each embedded with magnet-based connectors so that the modules can be assembled to modify the system behavior. The module can be used in a myriad of ways, including extending their working range, creating complex geometries upon deformation, and cooperating to improve overall performance. A simple analytical model for the actuating modules is derived based on the law of conservation of energy, and the model is verified experimentally which shows that this intuitive model can provide a reasonable prediction of performance. A block sorting robot is built using three different types of actuating modules with multiple fluidic supporting modules, and the robot shows that it is possible to flexibly and easily assemble modules to build a robot capable of completing diverse tasks. The ROV-PAM module and its concept can be applied to realize robotic designs, which can be altered on-the-fly to adjust its functionality to meet the evolving requirements required for truly flexible automation.

Analysis of the mechanism and clinical classification of thoracolumbar scoliosis using three-dimensional EOS and surface electromyography.

To analyze a thoracolumbar scoliosis group, we analyzed data from the acquired database by groups: the sEMG group (n = 16) and 3D-EOS group (n = 55). The asymmetric hyper/hypoactivation ratio of muscle and LLD (>3 mm) were measured in the sEMG group. In the 3D-EOS group, we recorded the values of parameters including LLD, pelvis rotation, and kyphosis/lordosis. In the sEMG study, sEMG examinations were conducted individually in patients with idiopathic scoliosis to analyze hyper/hypoactivation of the paraspinal muscle. In the three-dimensional EOS study, the Cobb angle, femoral height difference, and thoracic kyphosis and lumbar lordosis angles were measured using 2D images and 3D reconstructed images. Sixteen patients with thoracolumbar scoliosis were classified into asymmetric hyperactivation (A-Hyper) and asymmetric hypoactivation (A-Hypo) groups. The Cobb angle of the A-Hyper subtype was significantly higher than that of the A-Hypo subtype (22.41 versus 15.2, p = 0.023). Coronal deviation (p = 0.028) and the pelvis rotation angle (p = 0.001) were significantly higher in the LLD (+) subtype than in the LLD (-) subtype. When we classified patients cross-sectionally along with A-Hyper/Hypo and LLD (±), A-Hyper elevated the Cobb angle, and LLD (+) was significantly correlated with coronal deviation and pelvis rotation. In the 3D-EOS evaluation, the pelvic height difference (p = 0.043) and coronal deviation (p = 0.001) were significantly higher in the LLD (+) subtype than in the LLD (-) subtype. In conclusions, paraspinal muscular asymmetry and LLD can be strong factors in inducing or progressing thoracolumbar scoliosis.

A machine learning-based quantitative model (LogBB_Pred) to predict the blood-brain barrier permeability (logBB value) of drug compounds.

MOTIVATION: Efficient assessment of the blood-brain barrier (BBB) penetration ability of a drug compound is one of the major hurdles in central nervous system drug discovery since experimental methods are costly and time-consuming. To advance and elevate the success rate of neurotherapeutic drug discovery, it is essential to develop an accurate computational quantitative model to determine the absolute logBB value (a logarithmic ratio of the concentration of a drug in the brain to its concentration in the blood) of a drug candidate. RESULTS: Here, we developed a quantitative model (LogBB_Pred) capable of predicting a logBB value of a query compound. The model achieved an R2 of 0.61 on an independent test dataset and outperformed other publicly available quantitative models. When compared with the available qualitative (classification) models that only classified whether a compound is BBB-permeable or not, our model achieved the same accuracy (0.85) with the best qualitative model and far-outperformed other qualitative models (accuracies between 0.64 and 0.70). For further evaluation, our model, quantitative models, and the qualitative models were evaluated on a real-world central nervous system drug screening library. Our model showed an accuracy of 0.97 while the other models showed an accuracy in the range of 0.29-0.83. Consequently, our model can accurately classify BBB-permeable compounds as well as predict the absolute logBB values of drug candidates. AVAILABILITY AND IMPLEMENTATION: Web server is freely available on the web at http://ssbio.cau.ac.kr/software/logbb_pred/. The data used in this study are available to download at http://ssbio.cau.ac.kr/software/logbb_pred/dataset.zip.

Radius palmar plate removal without carpal tunnel release: Correlation between plate position and median nerve symptoms.

We aimed to report the clinical results of volar plate removal without carpal tunnel release in patients with late-onset median neuropathy and to evaluate the relationship between plate position and median nerve symptoms. Part I. Twelve consecutive patients with late-onset median neuropathy treated with volar plate removal without carpal tunnel release were enrolled for analysis. Pre- and post-operative Tinel sign, Phalen and Ten test, subjective rating of tingling sensation, Mayo wrist score and Disabilities of the Arm, Shoulder and Hand (DASH) score were collected. Part II. 232 consecutive patients underwent volar plating for distal radius fracture. The relationships between median nerve symptoms and volar plate prominence on the Soong classification, fracture classification, gender and age were investigated. All cases except one showed complete symptom resolution at final follow-up, with negative Tinel sign and Ten test score of 10/10. Tingling was rated 0 at final follow-up. Mean Mayo wrist and DASH scores improved to 86.7 and 23.1, respectively. The incidence of the median nerve symptoms in our cohort was 5.6%. Even though the odds ratio in Soong grade 2 was 4.0957 (95% CI, 0.93-16.9) compared to the combination of grades 0 and 1, no statistically significant relationship was found between the median nerve symptoms and volar plate prominence (p > 0.05). Plate removal without carpal tunnel release adequately relieved symptoms of late-onset median neuropathy after volar plating in patients with distal radius fracture. LEVEL OF EVIDENCE: IV; Therapeutic.

Analysis methods for the gut microbiome in neuropsychiatric and neurodegenerative disorders.

For a long time, the central nervous system was believed to be the only regulator of cognitive functions. However, accumulating evidence suggests that the composition of the microbiome is strongly associated with brain functions and diseases. Indeed, the gut microbiome is involved in neuropsychiatric diseases (e.g., depression, autism spectrum disorder, and anxiety) and neurodegenerative diseases (e.g., Parkinson's disease and Alzheimer's disease). In this review, we provide an overview of the link between the gut microbiome and neuropsychiatric or neurodegenerative disorders. We also introduce analytical methods used to assess the connection between the gut microbiome and the brain. The limitations of the methods used at present are also discussed. The accurate translation of the microbiome information to brain disorder could promote better understanding of neuronal diseases and aid in finding alternative and novel therapies.

A vinylogous Norrish reaction as a strategy for light-mediated ring expansion.

The reactions of bicyclic divinyl ketones display wavelength-dependent changes in product formation. UV irradiation results in the formation of competitive [6,3,5] and [7,3,5] tricyclic unsaturated ketones that subsequently undergo ring expansion and reaction with a range of nucleophiles. DFT calculations and transient absorption experiments were completed that are consistent with a vinylogous Type II Norrish pathway.

Armor-Based Stable Force Pneumatic Artificial Muscles for Steady Actuation Properties.

In this article, a novel actuator called armor-based stable force pneumatic artificial muscle (AS-PAM) is presented. AS-PAM has a sealed chamber made of polygonal parts and film, which helps the actuator to be lightweight (∼100 g) and achieve a large contraction ratio (>60%). It has an armor and a constraint to guide its motion, which keeps its force output [6.25 N/(cm2·bar)] stable over its operating range (<10% deviation). An analytical model is presented to predict and control the behavior of the actuator, and various experiments were conducted to show the validity of the model. Afterward, a gripper using the actuators is presented to illustrate how it can be used in real applications. With its characteristics, the actuator shows interesting behaviors that cannot be found in other soft pneumatic actuators, and it would allow AS-PAM to expand the range of applications in which soft robots cooperate with humans.

Sodium-Doped Titania Self-Rectifying Memristors for Crossbar Array Neuromorphic Architectures.

Memristors integrated into a crossbar-array architecture (CAA) are promising candidates for nonvolatile memory elements in artificial neural networks. However, the relatively low reliability of memristors coupled with crosstalk and sneak currents in CAAs have limited the realization of the full potential of this technology. Here, high-reliability Na-doped TiO2  memristors grown in situ by atomic layer deposition (ALD) are demonstrated, where reversible Na migration underlies the resistive-switching mechanism. By employing ALD growth with an aqueous NaOH reactant in deionized water, uniform implantation of Na dopants is achieved in the crystallized TiO2  thin films at 250 °C without post-annealing. The resulting Na-doped TiO2  memristors show electroforming-free and self-rectifying resistive-switching behavior, and they are ideally suited for selectorless CAAs. Effective addressing of selectorless nodes is demonstrated via electrical measurement of individual memristors in a 6 × 6 crossbar using a read current of less than 1 µA with negligible sneak current at or below the noise level of ≈100 pA. Finally, the long-term potentiation and depression synaptic behavior from these Na-doped TiO2  memristors achieves greater than 99.1% accuracy for image-recognition tasks using a convolutional neural network based on the selectorless of crossbar arrays.

Recent Advances in Micro/Nanomaterial-Based Aptamer Selection Strategies.

Aptamers are artificial nucleic acid ligands that have been employed in various fundamental studies and applications, such as biological analyses, disease diagnostics, targeted therapeutics, and environmental pollutant detection. This review focuses on the recent advances in aptamer discovery strategies that have been used to detect various chemicals and biomolecules. Recent examples of the strategies discussed here are based on the classification of these micro/nanomaterial-mediated systematic evolution of ligands by exponential enrichment (SELEX) platforms into three categories: bead-mediated, carbon-based nanomaterial-mediated, and other nanoparticle-mediated strategies. In addition to describing the advantages and limitations of the aforementioned strategies, this review discusses potential strategies to develop high-performance aptamers.

In silico methods and tools for drug discovery.

In the past, conventional drug discovery strategies have been successfully employed to develop new drugs, but the process from lead identification to clinical trials takes more than 12 years and costs approximately $1.8 billion USD on average. Recently, in silico approaches have been attracting considerable interest because of their potential to accelerate drug discovery in terms of time, labor, and costs. Many new drug compounds have been successfully developed using computational methods. In this review, we briefly introduce computational drug discovery strategies and outline up-to-date tools to perform the strategies as well as available knowledge bases for those who develop their own computational models. Finally, we introduce successful examples of anti-bacterial, anti-viral, and anti-cancer drug discoveries that were made using computational methods.

Liver segmentation in abdominal CT images via auto-context neural network and self-supervised contour attention.

OBJECTIVE: Accurate image segmentation of the liver is a challenging problem owing to its large shape variability and unclear boundaries. Although the applications of fully convolutional neural networks (CNNs) have shown groundbreaking results, limited studies have focused on the performance of generalization. In this study, we introduce a CNN for liver segmentation on abdominal computed tomography (CT) images that focus on the performance of generalization and accuracy. METHODS: To improve the generalization performance, we initially propose an auto-context algorithm in a single CNN. The proposed auto-context neural network exploits an effective high-level residual estimation to obtain the shape prior. Identical dual paths are effectively trained to represent mutual complementary features for an accurate posterior analysis of a liver. Further, we extend our network by employing a self-supervised contour scheme. We trained sparse contour features by penalizing the ground-truth contour to focus more contour attentions on the failures. RESULTS: We used 180 abdominal CT images for training and validation. Two-fold cross-validation is presented for a comparison with the state-of-the-art neural networks. The experimental results show that the proposed network results in better accuracy when compared to the state-of-the-art networks by reducing 10.31% of the Hausdorff distance. Novel multiple N-fold cross-validations are conducted to show the best performance of generalization of the proposed network. CONCLUSION AND SIGNIFICANCE: The proposed method minimized the error between training and test images more than any other modern neural networks. Moreover, the contour scheme was successfully employed in the network by introducing a self-supervising metric.

2-D chemical structure image-based in silico model to predict agonist activity for androgen receptor.

BACKGROUND: Abnormal activation of human nuclear hormone receptors disrupts endocrine systems and thereby affects human health. There have been machine learning-based models to predict androgen receptor agonist activity. However, the models were constructed based on limited numerical features such as molecular descriptors and fingerprints. RESULT: In this study, instead of the numerical features, 2-D chemical structure images of compounds were used to build an androgen receptor toxicity prediction model. The images may provide unknown features that were not represented by conventional numerical features. As a result, the new strategy resulted in a construction of highly accurate prediction model: Mathews correlation coefficient (MCC) of 0.688, positive predictive value (PPV) of 0.933, sensitivity of 0.519, specificity of 0.998, and overall accuracy of 0.981 in 10-fold cross-validation. Validation on a test dataset showed MCC of 0.370, sensitivity of 0.211, specificity of 0.991, PPV of 0.882, and overall accuracy of 0.801. Our chemical image-based prediction model outperforms conventional models based on numerical features. CONCLUSION: Our constructed prediction model successfully classified molecular images into androgen receptor agonists or inactive compounds. The result indicates that 2-D molecular mimetic diagram would be used as another feature to construct molecular activity prediction models.

Networks with controlled chirality via self-assembly of chiral triblock terpolymers.

Nanonetwork-structured materials can be found in nature and synthetic materials. A double gyroid (DG) with a pair of chiral networks but opposite chirality can be formed from the self-assembly of diblock copolymers. For triblock terpolymers, an alternating gyroid (GA) with two chiral networks from distinct end blocks can be formed; however, the network chirality could be positive or negative arbitrarily, giving an achiral phase. Here, by taking advantage of chirality transfer at different length scales, GA with controlled chirality can be achieved through the self-assembly of a chiral triblock terpolymer. With the homochiral evolution from monomer to multichain domain morphology through self-assembly, the triblock terpolymer composed of a chiral end block with a single-handed helical polymer chain gives the chiral network from the chiral end block having a particular handed network. Our real-space analyses reveal the preferred chiral sense of the network in the GA, leading to a chiral phase.

Automatic Registration Between Dental Cone-Beam CT and Scanned Surface via Deep Pose Regression Neural Networks and Clustered Similarities.

Computerized registration between maxillofacial cone-beam computed tomography (CT) images and a scanned dental model is an essential prerequisite for surgical planning for dental implants or orthognathic surgery. We propose a novel method that performs fully automatic registration between a cone-beam CT image and an optically scanned model. To build a robust and automatic initial registration method, deep pose regression neural networks are applied in a reduced domain (i.e., two-dimensional image). Subsequently, fine registration is performed using optimal clusters. A majority voting system achieves globally optimal transformations while each cluster attempts to optimize local transformation parameters. The coherency of clusters determines their candidacy for the optimal cluster set. The outlying regions in the iso-surface are effectively removed based on the consensus among the optimal clusters. The accuracy of registration is evaluated based on the Euclidean distance of 10 landmarks on a scanned model, which have been annotated by experts in the field. The experiments show that the registration accuracy of the proposed method, measured based on the landmark distance, outperforms the best performing existing method by 33.09%. In addition to achieving high accuracy, our proposed method neither requires human interactions nor priors (e.g., iso-surface extraction). The primary significance of our study is twofold: 1) the employment of lightweight neural networks, which indicates the applicability of neural networks in extracting pose cues that can be easily obtained and 2) the introduction of an optimal cluster-based registration method that can avoid metal artifacts during the matching procedures.

Pose-aware instance segmentation framework from cone beam CT images for tooth segmentation.

Individual tooth segmentation from cone beam computed tomography (CBCT) images is an essential prerequisite for an anatomical understanding of orthodontic structures in several applications, such as tooth reformation planning and implant guide simulations. However, the presence of severe metal artifacts in CBCT images hinders the accurate segmentation of each individual tooth. In this study, we propose a neural network for pixel-wise labeling to exploit an instance segmentation framework that is robust to metal artifacts. Our method comprises of three steps: 1) image cropping and realignment by pose regressions, 2) metal-robust individual tooth detection, and 3) segmentation. We first extract the alignment information of the patient by pose regression neural networks to attain a volume-of-interest (VOI) region and realign the input image, which reduces the inter-overlapping area between tooth bounding boxes. Then, individual tooth regions are localized within a VOI realigned image using a convolutional detector. We improved the accuracy of the detector by employing non-maximum suppression and multiclass classification metrics in the region proposal network. Finally, we apply a convolutional neural network (CNN) to perform individual tooth segmentation by converting the pixel-wise labeling task to a distance regression task. Metal-intensive image augmentation is also employed for a robust segmentation of metal artifacts. The result shows that our proposed method outperforms other state-of-the-art methods, especially for teeth with metal artifacts. Our method demonstrated 5.68% and 30.30% better accuracy in the F1 score and aggregated Jaccard index, respectively, when compared to the best performing state-of-the-art algorithms. The major implication of the proposed method is two-fold: 1) an introduction of pose-aware VOI realignment followed by a robust tooth detection and 2) a metal-robust CNN framework for accurate tooth segmentation.

Deeply self-supervised contour embedded neural network applied to liver segmentation.

OBJECTIVE: Herein, a neural network-based liver segmentation algorithm is proposed, and its performance was evaluated using abdominal computed tomography (CT) images. METHODS: A fully convolutional network was developed to overcome the volumetric image segmentation problem. To guide a neural network to accurately delineate a target liver object, the network was deeply supervised by applying the adaptive self-supervision scheme to derive the essential contour, which acted as a complement with the global shape. The discriminative contour, shape, and deep features were internally merged for the segmentation results. RESULTS AND CONCLUSION: 160 abdominal CT images were used for training and validation. The quantitative evaluation of the proposed network was performed through an eight-fold cross-validation. The result showed that the method, which uses the contour feature, segmented the liver more accurately than the state-of-the-art with a 2.13% improvement in the dice score. SIGNIFICANCE: In this study, a new framework was introduced to guide a neural network and learn complementary contour features. The proposed neural network demonstrates that the guided contour features can significantly improve the performance of the segmentation task.

User guide for the discovery of potential drugs via protein structure prediction and ligand docking simulation.

Due to accumulating protein structure information and advances in computational methodologies, it has now become possible to predict protein-compound interactions. In biology, the classic strategy for drug discovery has been to manually screen multiple compounds (small scale) to identify potential drug compounds. Recent strategies have utilized computational drug discovery methods that involve predicting target protein structures, identifying active sites, and finding potential inhibitor compounds at large scale. In this protocol article, we introduce an in silico drug discovery protocol. Since multi-drug resistance of pathogenic bacteria remains a challenging problem to address, UDP-N-acetylmuramate-L-alanine ligase (murC) of Acinetobacter baumannii was used as an example, which causes nosocomial infection in hospital setups and is responsible for high mortality worldwide. This protocol should help microbiologists to expand their knowledge and research scope.

Recent advances in genetic engineering tools based on synthetic biology.

Genome-scale engineering is a crucial methodology to rationally regulate microbiological system operations, leading to expected biological behaviors or enhanced bioproduct yields. Over the past decade, innovative genome modification technologies have been developed for effectively regulating and manipulating genes at the genome level. Here, we discuss the current genome-scale engineering technologies used for microbial engineering. Recently developed strategies, such as clustered regularly interspaced short palindromic repeats (CRISPR)-Cas9, multiplex automated genome engineering (MAGE), promoter engineering, CRISPR-based regulations, and synthetic small regulatory RNA (sRNA)-based knockdown, are considered as powerful tools for genome-scale engineering in microbiological systems. MAGE, which modifies specific nucleotides of the genome sequence, is utilized as a genome-editing tool. Contrastingly, synthetic sRNA, CRISPRi, and CRISPRa are mainly used to regulate gene expression without modifying the genome sequence. This review introduces the recent genome-scale editing and regulating technologies and their applications in metabolic engineering.