The novel coronavirus, COVID-19, has caused a crisis that affects all segments of the population. As the knowledge and understanding of COVID-19 evolve, an appropriate response plan for this pandemic is considered one of the most effective methods for controlling the spread of the virus. Recent studies indicate that a city Digital Twin (DT) is beneficial for tackling this health crisis, because it can construct a virtual replica to simulate factors, such as climate conditions, response policies, and people's trajectories, to help plan efficient and inclusive decisions.However, a city DTsystem relies on long-term and high-quality data collection to make appropriate decisions, limiting its advantages when facing urgent crises, such as the COVID-19 pandemic. Federated Learning (FL), in which all clients can learn a shared model while retaining all training data locally, emerges as a promising solution for accumulating the insights from multiple data sources efficiently. Furthermore, the enhanced privacy protection settings removing the privacy barriers lie in this collaboration. In this work, we propose a framework that fused city DT with FL to achieve a novel collaborative paradigm that allows multiple city DTs to share the local strategy and status quickly. In particular, an FL central server manages the local updates of multiple collaborators (city DTs), providing a global model that is trained in multiple iterations at different city DT systems until the model gains the correlations between various response plans and infection trends. This approach means a collaborative city DT paradigm fused with FL techniques can obtain knowledge and patterns from multiple DTs and eventually establish a "global view" of city crisis management. Meanwhile, it also helps improve each city's DT by consolidating other DT's data without violating privacy rules. In this paper, we use the COVID-19 pandemic as the use case of the proposed framework. The experimental results on a real dataset with various response plans validate our proposed solution and demonstrate its superior performance.

Background Sudden unexpected death in epilepsy (SUDEP) is second only to stroke in neurological events resulting in years of potential life lost. Postictal generalized electroencephalogram (EEG) suppression (PGES) is a period of suppressed brain activity often occurring after generalized tonic-clonic seizure, a most significant risk factor for SUDEP. Therefore, PGES has been considered as a potential biomarker for SUDEP risk. Automatic PGES detection tools can address the limitations of labor-intensive, and sometimes inconsistent, visual analysis. A successful approach to automatic PGES detection must overcome computational challenges involved in the detection of subtle amplitude changes in EEG recordings, which may contain physiological and acquisition artifacts. Objective This study aimed to present a random forest approach for automatic PGES detection using multichannel human EEG recordings acquired in epilepsy monitoring units. Methods We used a combination of temporal, frequency, wavelet, and interchannel correlation features derived from EEG signals to train a random forest classifier. We also constructed and applied confidence-based correction rules based on PGES state changes. Motivated by practical utility, we introduced a new, time distance–based evaluation method for assessing the performance of PGES detection algorithms. Results The time distance–based evaluation showed that our approach achieved a 5-second tolerance-based positive prediction rate of 0.95 for artifact-free signals. For signals with different artifact levels, our prediction rates varied from 0.68 to 0.81. Conclusions We introduced a feature-based, random forest approach for automatic PGES detection using multichannel EEG recordings. Our approach achieved increasingly better time distance–based performance with reduced signal artifact levels. Further study is needed for PGES detection algorithms to perform well irrespective of the levels of signal artifacts.

Background Patient verification by unique identification is an important procedure in health care settings. Risks to patient safety occur throughout health care settings by failure to correctly identify patients, resulting in the incorrect patient, incorrect site procedure, incorrect medication, and other errors. To avoid medical malpractice, radio-frequency identification (RFID), fingerprint scanners, iris scanners, and other technologies have been implemented in care settings. The drawbacks of these technologies include the possibility to lose the RFID bracelet, infection transmission, and impracticality when the patient is unconscious. Objective The purpose of this study was to develop a mobile health app for patient identification to overcome the limitations of current patient identification alternatives. The development of this app is expected to provide an easy-to-use alternative method for patient identification. Methods We have developed a facial recognition mobile app for improved patient verification. As an evaluation purpose, a total of 62 pediatric patients, including both outpatient and inpatient, were registered for the facial recognition test and tracked throughout the facilities for patient verification purpose. Results The app was developed to contain 5 main parts: registration, medical records, examinations, prescriptions, and appointments. Among 62 patients, 30 were outpatients visiting plastic surgery department and 32 were inpatients reserved for surgery. Whether patients were under anesthesia or unconscious, facial recognition verified all patients with 99% accuracy even after a surgery. Conclusions It is possible to correctly identify both outpatients and inpatients and also reduce the unnecessary cost of patient verification by using the mobile facial recognition app with great accuracy. Our mobile app can provide valuable aid to patient verification, including when the patient is unconscious, as an alternative identification method.

No abstract

Bond dissociation energy (BDE), an indicator of the strength of chemical bonds, exhibits great potential for evaluating and screening high-performance materials and catalysts, which are of critical importance in industrial applications. However, the measurement or computation of BDE via conventional experimental or theoretical methods is usually costly and involved, substantially preventing the BDE from being applied to large-scale and high-throughput studies. Therefore, a potentially more efficient approach for estimating BDE is highly desirable. To this end, we combined first-principles calculations and machine learning techniques, including neural networks and random forest, to explore the inner relationships between carbonyl structure and its BDE. Results show that machine learning can not only effectively reproduce the computed BDEs of carbonyls but also in turn serve as guidance for the rational design of carbonyl structure aimed at optimizing performance.

BackgroundMyasthenia gravis (MG) is an autoimmune, neuromuscular condition and patients with MG are vulnerable due to immunosuppressant use and disease manifestations of dyspnea and dysphagia during the coronavirus disease 2019 (COVID-19) pandemic.MethodsWe conducted a retrospective cohort study using the Optum® de-identified COVID-19 Electronic Health Record (EHR) dataset. Primary outcomes, such as hospitalization, ventilator use, intensive care unit (ICU) admission, and death in COVID-19 patients with MG, were compared with those of COVID-19 patients without MG: the subgroups of non-MG included those with rheumatoid arthritis (RA), systemic lupus (SLE), and multiple sclerosis (MS). We further analyzed factors affecting mortality, such as age, race/ethnicity, comorbidities, and MG treatments.ResultsAmong 421,086 individuals with COVID-19, there were 377 patients with MG, 7,362 patients with RA, 1,323 patients with SLE, 1,518 patients with MS, and 410,506 patients without MG. Patients with MG were older and had more comorbidities compared with non-MG patients and had the highest rates of hospitalization (38.5%), ICU admission (12.7%), ventilator use (3.7%), and mortality (10.6%) compared with all other groups. After adjusting for risk factors, patients with MG had increased risks for hospitalization and ICU compared with patients with non-MG and with RA but had risks similar to patients with SLE and with MS. The adjusted risk for ventilator use was similar across all groups, but the risk for mortality in patients with MG was lower compared with the SLE and MS groups. Among patients with MG, age over 75 years and dysphagia were predictors for increased COVID-19 mortality, but the recent MG treatment was not associated with COVID-19 mortality.ConclusionsCOVID-19 patients with MG are more likely to be admitted to the hospital and require ICU care. Older age and patients with dysphagia had an increased risk of mortality.

Understanding and reasoning about places and their relationships are critical for many applications. Places are traditionally curated by a small group of people as place gaze eers and are represented by an ID with spatial extent, category, and other descriptions. However, a place context is described to a large extent by movements made from/to other places. Places are linked and related to each other by these movements. is important context is missing from the traditional representation.We present DeepMove, a novel approach for learning latent representations of places. DeepMove advances the current deep learning based place representations by directly model movements between places. We demonstrate DeepMove's latent representations on place categorization and clustering tasks on large place and movement datasets with respect to important parameters. Our results show that DeepMove outperforms state-of-the-art baselines. DeepMove's representations can provide up to 15% higher than competing methods in matching rate of place category and result in up to 39% higher silhoue e coe cient value for place clusters.DeepMove is spatial and temporal context aware. It is scalable. It outperforms competing models using much smaller training dataset (a month or 1/12 of data). ese qualities make it suitable for a broad class of real-world applications.

Background: Risk factors associated with coronavirus disease 2019 (COVID-19) severity in patients with multiple sclerosis (MS) have been described. Recent improvements in supportive care measures and increased testing capacity may modify the risk of severe COVID-19 outcome in MS patients. This retrospective study evaluates the severity and outcome of COVID-19 in MS and characterizes temporal trends over the course of the pandemic in the United States. Methods: We conducted a comparative cohort study using de-identified electronic health record (EHR) claims-based data. MS patients diagnosed with COVID-19 between February 2, 2020 and October 13, 2020 were matched (1:2) to a control group using propensity score analysis. The primary outcome was a composite of intensive care unit (ICU) admission, mechanical ventilation, and/or death. Results: A total of 2,529 patients (843 MS and 1,686 matched controls) were included. Non-ambulatory and pre-existing comorbidities were independent risk factors for COVID-19 severity. The risk for the severe composite outcome was lower in the late cohorts compared with the early cohorts. Conclusions: The majority of MS patients actively treated with a disease-modifying therapy (DMT) had mild disease. The observed trend toward a reduction in severity risk in recent months suggests an improvement in COVID-19 outcome.