Search

Abstract COVID-19 has resulted in significant morbidity and mortality globally. We develop a model that uses data from thirty days before a fixed time point to forecast the daily number of new COVID-19 cases fourteen days later in the early stages of the pandemic. Various time-dependent factors including the number of daily confirmed cases, reproduction number, policy measures, mobility and flight numbers were collected. A deep-learning model using Bidirectional Long-Short Term Memory (Bi-LSTM) architecture was trained on data from 22nd Jan 2020 to 8 Jan 2021 to forecast the new daily number of COVID-19 cases 14 days in advance across 190 countries, from 9 to 31 Jan 2021. A second model with fewer variables but similar architecture was developed. Results were summarised by mean absolute error (MAE), root mean squared error (RMSE), mean absolute percentage error (MAPE), and total absolute percentage error and compared against results from a classical ARIMA model. Median MAE was 157 daily cases (IQR: 26–666) under the first model, and 150 (IQR: 26–716) under the second. Countries with more accurate forecasts had more daily cases and experienced more waves of COVID-19 infections. Among countries with over 10,000 cases over the prediction period, median total absolute percentage error was 33% (IQR: 18–59%) and 34% (IQR: 16–66%) for the first and second models respectively. Both models had comparable median total absolute percentage errors but lower maximum total absolute percentage errors as compared to the classical ARIMA model. A deep-learning approach using Bi-LSTM architecture and open-source data was validated on 190 countries to forecast the daily number of cases in the early stages of the COVID-19 outbreak. Fewer variables could potentially be used without impacting prediction accuracy.

Boltzmann Machines offer the potential of more efficient solutions to combinatorial problems compared to von Neumann computing architectures. Here, Yan et al introduce a stochastic memristor with dynamically tunable properties, a vital feature for the efficient implementation of a Boltzmann Machine.

BackgroundAs the COVID-19 pandemic evolves, challenges in frontline work continue to impose a significant psychological impact on nurses. However, there is a lack of data on how nurses fared compared to other health care workers in the Asia-Pacific region. ObjectiveThis study aims to investigate (1) the psychological outcome characteristics of nurses in different Asia-Pacific countries and (2) psychological differences between nurses, doctors, and nonmedical health care workers. MethodsExploratory data analysis and visualization were conducted on the data collected through surveys. A machine learning modeling approach was adopted to further discern the key psychological characteristics differentiating nurses from other health care workers. Decision tree–based machine learning models (Light Gradient Boosting Machine, GradientBoost, and RandomForest) were built to predict whether a set of psychological distress characteristics (ie, depression, anxiety, stress, intrusion, avoidance, and hyperarousal) belong to a nurse. Shapley Additive Explanation (SHAP) values were extracted to identify the prominent characteristics of each of these models. The common prominent characteristic among these models is akin to the most distinctive psychological characteristic that differentiates nurses from other health care workers. ResultsNurses had relatively higher percentages of having normal or unchanged psychological distress symptoms relative to other health care workers (n=233-260 [86.0%-95.9%] vs n=187-199 [74.8%-91.7%]). Among those without psychological symptoms, nurses constituted a higher proportion than doctors and nonmedical health care workers (n=194 [40.2%], n=142 [29.5%], and n=146 [30.3%], respectively). Nurses in Vietnam showed the highest level of depression, stress, intrusion, avoidance, and hyperarousal symptoms compared to those in Singapore, Malaysia, and Indonesia. Nurses in Singapore had the highest level of anxiety. In addition, nurses had the lowest level of stress, which is the most distinctive psychological outcome characteristic derived from machine learning models, compared to other health care workers. Data for India were excluded from the analysis due to the differing psychological response pattern observed in nurses in India. A large number of female nurses emigrating from South India could not have psychologically coped well without the support from family members while living alone in other states. ConclusionsNurses were least psychologically affected compared to doctors and other health care workers. Different contexts, cultures, and points in the pandemic curve may have contributed to differing patterns of psychological outcomes amongst nurses in various Asia-Pacific countries. It is important that all health care workers practice self-care and render peer support to bolster psychological resilience for effective coping. In addition, this study also demonstrated the potential use of decision tree–based machine learning models and SHAP value plots in identifying contributing factors of sophisticated problems in the health care industry.

Scene perception involves extracting the identities of the objects comprising a scene in conjunction with their configuration (the spatial layout of the objects in the scene). How object identity and configuration information is weighted during scene processing and how this weighting evolves over the course of scene processing however, is not fully understood. Recent developments in convolutional neural networks (CNNs) have demonstrated their aptitude at scene processing tasks and identified correlations between processing in CNNs and in the human brain. Here we examined four CNN architectures (Alexnet, Resnet18, Resnet50, Densenet161) and their sensitivity to changes in object and configuration information over the course of scene processing. Despite differences among the four CNN architectures, across all CNNs, we observed a common pattern in the CNN's response to object identity and configuration changes. Each CNN demonstrated greater sensitivity to configuration changes in early stages of processing and stronger sensitivity to object identity changes in later stages. This pattern persists regardless of the spatial structure present in the image background, the accuracy of the CNN in classifying the scene, and even the task used to train the CNN. Importantly, CNNs' sensitivity to a configuration change is not the same as their sensitivity to any type of position change, such as that induced by a uniform translation of the objects without a configuration change. These results provide one of the first documentations of how object identity and configuration information are weighted in CNNs during scene processing.

BackgroundElective colorectal cancer (CRC) surgeries offer enhanced surgical outcomes but demand high self-efficacy in prehabilitation and competency in self-care and disease management postsurgery. Conventional strategies to meet perioperative needs have not been pragmatic, and there remains a pressing need for novel technologies that could improve health outcomes. ObjectiveThe aim of this paper was to describe the development of a smartphone-based interactive CRC self-management enhancement psychosocial program (iCanManage) in order to improve health outcomes among patients who undergo elective CRC surgeries and their family caregivers. MethodsA multidisciplinary international team comprising physicians, specialist nurses, a psychologist, software engineers, academic researchers, cancer survivors, patient ambassadors, and ostomy care medical equipment suppliers was formed to facilitate the development of this patient-centric digital solution. The process occurred in several stages: (1) review of current practice through clinic visits and on-site observations; (2) review of literature and findings from preliminary studies; (3) content development grounded in an underpinning theory; (4) integration of support services; and (5) optimizing user experience through improving interface aesthetics and customization. In our study, 5 participants with CRC performed preliminary assessments on the quality of the developed solution using the 20-item user version of the Mobile App Rating Scale (uMARS), which had good psychometric properties. ResultsBased on the collected uMARS data, the smartphone app was rated highly for functionality, aesthetics, information quality, and perceived impact, and moderately for engagement and subjective quality. Several limiting factors such as poor agility in the adoption of digital technology and low eHealth literacy were identified despite efforts to promote engagement and ensure ease of use of the mobile app. To overcome such barriers, additional app-training sessions, an instruction manual, and regular telephone calls will be incorporated into the iCanManage program during the trial period. ConclusionsThis form of multidisciplinary collaboration is advantageous as it can potentially streamline existing care paths and allow the delivery of more holistic care to the CRC population during the perioperative period. Should the program be found to be effective and sustainable, hospitals adopting this digital solution may achieve better resource allocation and reduce overall health care costs in the long run. Trial RegistrationClinicalTrials.gov NCT04159363; https://clinicaltrials.gov/ct2/show/NCT04159363

There is a lack of quantitative research examining how the pandemic has affected individuals at different income levels. The Asian American population has the highest level of income inequality and serves as an excellent case study for examining differences in experience between income groups. A non-probability sample of 3084 Asian American adults living in the US was surveyed in June 2020, examining health-related behaviors and outcomes. Descriptive analyses and chi-squared statistics were conducted to identify differences in income groups (low, medium, high) among Asian Americans across regional subgroups (East, South, Southeast, Multiethnic) and disaggregated ethnicities (Chinese, Asian Indian, Japanese, and Filipino). In bivariable analyses, a significantly (p

Protein function prediction is one of the most well-studied topics, attracting attention from countless researchers in the field of computational biology. Implementing deep neural networks that help improve the prediction of protein function, however, is still a major challenge. In this research, we suggested a new strategy that includes gated recurrent units and position-specific scoring matrix profiles to predict vesicular transportation proteins, a biological function of great importance. Although it is difficult to discover its function, our model is able to achieve accuracies of 82.3% and 85.8% in the cross-validation and independent dataset, respectively. We also solve the problem of imbalance in the dataset via tuning class weight in the deep learning model. The results generated showed sensitivity, specificity, MCC, and AUC to have values of 79.2%, 82.9%, 0.52, and 0.861, respectively. Our strategy shows superiority in results on the same dataset against all other state-of-the-art algorithms. In our suggested research, we have suggested a technique for the discovery of more proteins, particularly proteins connected with vesicular transport. In addition, our accomplishment could encourage the use of gated recurrent units architecture in protein function prediction. Keywords: Vesicular trafficking model, Protein function prediction, Transport proteins, Recurrent neural network, Deep learning, Membrane proteins

Background: There is a variety of mortality prediction models for patients in intensive care units (ICU) to guide appropriate clinical management. Advances in machine learning methodologies typically employ classifiers such as Neural Network and Random Forest which are often regarded by healthcare professionals as black boxes. These models often do not provide clear links between the input model features and output clinical event. We investigate whether features identified by Cox-Proportional Hazards (CPH) model can be used for ICU mortality prediction. Methods: We employ the PhysioNet Challenge 2012 dataset, a subset of MIMIC-II Clinical Database data of ICU patients admitted to Boston's Beth Israel Deaconess Medical Center from 2001 to 2008. The dataset is split into train set A, test set B and unseen set C, with 4000 patients each. Python is the programming language used alongside scikit-learn, and lifelines packages. Besides white-box feature selection methods (logistic regression and decision tree), we also explore using Cox-Proportional Hazards model for feature selection. We then trained the machine learning model using classifiers such as logistic regression and variants of decision tree. Extreme gradient boosted trees models performed better than other classifiers. The model is validated using 5-fold cross-validation and evaluated against unseen set C. The model performance is assessed using area under the precision-recall curve (AUC-PR) as the main metric. Findings: The data of about 12,000 patients is used, providing a high degree of generalizability. The number of statistically significant features identified by CPH (n = 16) is significantly smaller than logistic regression (n = 36), decision tree (n = 26) and all features (n = 42). With only 16 features used, the model achieves a performance of AUC-PR 0·438 on test set B, which is close to decision tree (AUC-PR 0·442) and logistic regression (AUC-PR 0·446) and all features (AUC-PR 0·446). Interpretation: The significantly fewer features identified by CPH allows the building of a model that is easily interpretable by clinicians whilst still achieving comparable results to other models. This finding allows clinicians to use CPH as an alternative method to determine and act on features that need to be closely monitored for ICU patients.

Background and study aims This preliminary study was conducted to determine the feasibility and safety of endoscopic augmentation of the gastroesophageal junction (GEJ) using the Apollo OverStitch endoscopic suturing system in patients with gastroesophageal reflux disease (GERD) symptoms. Patients and methods Endoscopic augmentation of GEJ was performed on 10 consecutive patients and the data were analyzed retrospectively. Using a double-channel gastroscope affixed to the endoscopic suturing platform, interrupted sutures were placed on the gastric side of the GEJ in 2 layers in order to create a narrowed and elongated GEJ. Results Technical success was achieved in all patients, including those with a history of previous antireflux procedures (n = 7) and those with a hiatal hernia (n = 6). The median follow-up duration was 5 mo (range: 2 – 12). The median pre-procedure GERD-Health Related Quality of Life Questionnaire improved from 20 (range: 11 – 45) to a post-procedure score of 6 (range: 3 – 25) (P = 0.001). The median duration of GERD symptom improvement after the procedure was 1 mo (range: 0.5 – 4). Adverse events were limited to 1 patient who developed nausea and vomiting, which was self-limited. Conclusions The use of a novel endoscopic suturing technique for the treatment of GERD is feasible and safe. The procedure resulted in short-term GERD symptom improvement. Further prospective studies using refined techniques are currently underway to improve durability and to prove efficacy.

PurposeIt is postulated that ILD causes PA dilatation independent of the presence of pulmonary hypertension (PH), so the use of PA size to screen for PH is not recommended. The aims of this study were to investigate the association of PA size with the presence and severity of ILD and to assess the diagnostic accuracy of PA size for detecting PH.MethodsIncident patients referred to a tertiary PH centre underwent baseline thoracic CT, MRI and right heart catheterisation (RHC). Pulmonary artery diameter was measured on CT pulmonary angiography and pulmonary arterial areas on MRI. A thoracic radiologist scored the severity of ILD on CT from 0 to 4, 0 = absent, 1 = 1–25%, 2 = 26–50%, 3 = 51–75%, and 4 = 76–100% extent of involvement. Receiver operating characteristic analysis and linear regression were employed to assess diagnostic accuracy and independent associations of PA size.Results110 had suspected PH due to ILD (age 65 years (SD 13), M:F 37:73) and 379 had suspected PH without ILD (age 64 years (SD 13), M:F 161:218). CT derived main PA diameter was accurate for detection of PH in patients both with and without ILD - AUC 0.873, p =< 0.001, and AUC 0.835, p =< 0.001, respectively, as was MRI diastolic PA area, AUC 0.897, p =< 0.001, and AUC 0.857, p =< 0.001, respectively Significant correlations were identified between mean pulmonary arterial pressure (mPAP) and PA diameter in ILD (r = 0.608, p < 0.001), and non-ILD cohort (r = 0.426, p < 0.001). PA size was independently associated with mPAP (p < 0.001) and BSA (p = 0.001), but not with forced vital capacity % predicted (p = 0.597), Transfer factor of the lungs for carbon monoxide (TLCO) % predicted (p = 0.321) or the presence of ILD on CT (p = 0.905). The severity of ILD was not associated with pulmonary artery dilatation (r = 0.071, p = 0.459).ConclusionsPulmonary arterial pressure elevation leads to pulmonary arterial dilation, which is not independently influenced by the presence or severity of ILD measured by FVC, TLCO, or disease severity on CT. Pulmonary arterial diameter has diagnostic value in patients with or without ILD and suspected PH.

The International Space Station (ISS) National Laboratory is dedicated to studying the effects of space on life and physical systems, and to developing new science and technologies for space exploration. A key aspect of achieving these goals is to operate the ISS National Lab more like an Earth-based laboratory, conducting complex end-to-end experimentation, not limited to simple microgravity exposure. Towards that end NASA developed a novel suite of molecular biology laboratory tools, reagents, and methods, named WetLab-2, uniquely designed to operate in microgravity, and to process biological samples for real-time gene expression analysis on-orbit. This includes a novel fluidic RNA Sample Preparation Module and fluid transfer devices, all-in-one lyophilized PCR assays, centrifuge, and a real-time PCR thermal cycler. Here we describe the results from the WetLab-2 validation experiments conducted in microgravity during ISS increment 47/SPX-8. Specifically, quantitative PCR was performed on a concentration series of DNA calibration standards, and Reverse Transcriptase-quantitative PCR was conducted on RNA extracted and purified on-orbit from frozen Escherichia coli and mouse liver tissue. Cycle threshold (Ct) values and PCR efficiencies obtained on-orbit from DNA standards were similar to Earth (1 g) controls. Also, on-orbit multiplex analysis of gene expression from bacterial cells and mammalian tissue RNA samples was successfully conducted in about 3 h, with data transmitted within 2 h of experiment completion. Thermal cycling in microgravity resulted in the trapping of gas bubbles inside septa cap assay tubes, causing small but measurable increases in Ct curve noise and variability. Bubble formation was successfully suppressed in a rapid follow-up on-orbit experiment using standard caps to pressurize PCR tubes and reduce gas release during heating cycles. The WetLab-2 facility now provides a novel operational on-orbit research capability for molecular biology and demonstrates the feasibility of more complex wet bench experiments in the ISS National Lab environment.

Enhancers are short deoxyribonucleic acid fragments that assume an important part in the genetic process of gene expression. Due to their possibly distant location relative to the gene that is acted upon, the identification of enhancers is difficult. There are many published works focused on identifying enhancers based on their sequence information, however, the resulting performance still requires improvements. Using deep learning methods, this study proposes a model ensemble of classifiers for predicting enhancers based on deep recurrent neural networks. The input features of deep ensemble networks were generated from six types of dinucleotide physicochemical properties, which had outperformed the other features. In summary, our model which used this ensemble approach could identify enhancers with achieved sensitivity of 75.5%, specificity of 76%, accuracy of 75.5%, and MCC of 0.51. For classifying enhancers into strong or weak sequences, our model reached sensitivity of 83.15%, specificity of 45.61%, accuracy of 68.49%, and MCC of 0.312. Compared to the benchmark result, our results had higher performance in term of most measurement metrics. The results showed that deep model ensembles hold the potential for improving on the best results achieved to date using shallow machine learning methods.

l-Dopa-induced dyskinesias (LIDs) are abnormal involuntary movements that develop with long term l-dopa therapy for Parkinson's disease. Studies show that nicotine administration reduced LIDs in several parkinsonian animal models. The present work was done to understand the factors that regulate the nicotine-mediated reduction in LIDs in MPTP-lesioned nonhuman primates. To approach this, we used two groups of monkeys, one with mild-moderate and the other with more severe parkinsonism rendered dyskinetic using l-dopa. In mild-moderately parkinsonian monkeys, nicotine pretreatment (300 μg/ml via drinking water) prevented the development of LIDs by ~75%. This improvement was maintained when the nicotine dose was lowered to 50 μg/ml but was lost with nicotine removal. Nicotine re-exposure again decreased LIDs. By contrast, nicotine treatment did not reduce LIDs in monkeys with more severe parkinsonism. We next determined how nicotine's ability to reduce LIDs correlated with lesion-induced changes in the striatal dopamine transporter and 3H-dopamine release in these two groups of monkeys. The striatal dopamine transporter was reduced to 54% and 28% of control in mild-moderately and more severely parkinsonian monkeys, respectively. However, basal, K+, α4β2* and α6β2* nAChR-evoked 3H-dopamine release were near control levels in striatum of mild-moderately parkinsonian monkeys. By contrast, these same release measures were reduced to a significantly greater extent in striatum of more severely parkinsonian monkeys. Thus, nicotine best improves LIDs in lesioned monkeys in which striatal dopamine transmission is still relatively intact. These data suggest that nicotine treatment would most effectively reduce LIDs in patients with mild to moderate Parkinson's disease.

The motion mimicry ability of patients facilitates execution of therapy moves based on visual observation of rehabilitation exercise videos, which can help speed up the recovery process. This study investigates the effects of visual feedback on the mimicking ability of human subjects in video-based rehabilitation. Inertial Measurement Unit (IMU) sensors was used, which provide a portable system to detect human motion tracking, allowing for experiments to be conducted without space restrictions and provide a greater variety of actions that can be tested. In the experiment, healthy subjects were shown a video of an instructor performing a certain movement task and had to mimic actions to the best of their ability. A real-time visual feedback system, based on input data from IMU sensors, was introduced to inform subjects of the accuracy of their mimicking actions. Subjects were tested with and without feedback and the relevant joint angle data was collected to determine the individual’s mimicking ability. Our results showed a significant improvement in subject’s mimicking ability from “no feedback” to “feedback” condition. The key implication of the findings is that visual feedback provides an extrinsic source that allows patients to better synchronize their hand-eye coordination during mimicry. Potential prospective works will investigate the relevance of motion mimicry mechanism in home-based rehabilitation.

The use of air propulsion to drive limb motion in soft robotics has been a largely untapped field even though the technology has been around since the 1700s. Air propulsion can generate greater degrees of motion in limb actuators compared to widely-experimented pneumatic actuators operating on expandable air channels, which are limited by air pressure input, minimum size and cyclic fatigue. To demonstrate the application of air propulsion in soft robotics motion, we developed a 3D-printed, tri-pedal, soft, air-driven robot that can perform biomimetic motions such as flexion and extension of limbs, crawling, rotation, grasping, kicking and picking of objects. To accomplish air-propelled actuation, milli-scale channels are incorporated throughout each limb that guides the pressurized air inflow to outlets of different directions. A Finite Element Model (FEM) approach to simulate the bending response of the limb due to varying pressure is proposed and evaluated. This study introduces the potential of using air propulsion as an alternate form of soft body actuation for longer cyclic lifespan and increased maximum air pressure input.