Home monitoring with connected mobile devices for asthma attack prediction with machine learning.

Monitoring asthma is essential for self-management. However, traditional monitoring methods require high levels of active engagement, and some patients may find this tedious. Passive monitoring with mobile-health devices, especially when combined with machine-learning, provides an avenue to reduce management burden. Data for developing machine-learning algorithms are scarce, and gathering new data is expensive. A few datasets, such as the Asthma Mobile Health Study, are publicly available, but they only consist of self-reported diaries and lack any objective and passively collected data. To fill this gap, we carried out a 2-phase, 7-month AAMOS-00 observational study to monitor asthma using three smart-monitoring devices (smart-peak-flow-meter/smart-inhaler/smartwatch), and daily symptom questionnaires. Combined with localised weather, pollen, and air-quality reports, we collected a rich longitudinal dataset to explore the feasibility of passive monitoring and asthma attack prediction. This valuable anonymised dataset for phase-2 of the study (device monitoring) has been made publicly available. Between June-2021 and June-2022, in the midst of UK's COVID-19 lockdowns, 22 participants across the UK provided 2,054 unique patient-days of data.

FAIR in action - a flexible framework to guide FAIRification.

The COVID-19 pandemic has highlighted the need for FAIR (Findable, Accessible, Interoperable, and Reusable) data more than any other scientific challenge to date. We developed a flexible, multi-level, domain-agnostic FAIRification framework, providing practical guidance to improve the FAIRness for both existing and future clinical and molecular datasets. We validated the framework in collaboration with several major public-private partnership projects, demonstrating and delivering improvements across all aspects of FAIR and across a variety of datasets and their contexts. We therefore managed to establish the reproducibility and far-reaching applicability of our approach to FAIRification tasks.

COVID-19 amplified racial disparities in the US criminal legal system.

The criminal legal system in the USA drives an incarceration rate that is the highest on the planet, with disparities by class and race among its signature features1-3. During the first year of the coronavirus disease 2019 (COVID-19) pandemic, the number of incarcerated people in the USA decreased by at least 17%-the largest, fastest reduction in prison population in American history4. Here we ask how this reduction influenced the racial composition of US prisons and consider possible mechanisms for these dynamics. Using an original dataset curated from public sources on prison demographics across all 50 states and the District of Columbia, we show that incarcerated white people benefited disproportionately from the decrease in the US prison population and that the fraction of incarcerated Black and Latino people sharply increased. This pattern of increased racial disparity exists across prison systems in nearly every state and reverses a decade-long trend before 2020 and the onset of COVID-19, when the proportion of incarcerated white people was increasing amid declining numbers of incarcerated Black people5. Although a variety of factors underlie these trends, we find that racial inequities in average sentence length are a major contributor. Ultimately, this study reveals how disruptions caused by COVID-19 exacerbated racial inequalities in the criminal legal system, and highlights key forces that sustain mass incarceration. To advance opportunities for data-driven social science, we publicly released the data associated with this study at Zenodo6.

Mental health concerns during the COVID-19 pandemic as revealed by helpline calls.

Mental health is an important component of public health, especially in times of crisis. However, monitoring public mental health is difficult because data are often patchy and low-frequency1-3. Here we complement established approaches by using data from helplines, which offer a real-time measure of 'revealed' distress and mental health concerns across a range of topics4-9. We collected data on 8 million calls from 19 countries, focusing on the COVID-19 crisis. Call volumes peaked six weeks after the initial outbreak, at 35% above pre-pandemic levels. The increase was driven mainly by fear (including fear of infection), loneliness and, later in the pandemic, concerns about physical health. Relationship issues, economic problems, violence and suicidal ideation, however, were less prevalent than before the pandemic. This pattern was apparent both during the first wave and during subsequent COVID-19 waves. Issues linked directly to the pandemic therefore seem to have replaced rather than exacerbated underlying anxieties. Conditional on infection rates, suicide-related calls increased when containment policies became more stringent and decreased when income support was extended. This implies that financial relief can allay the distress triggered by lockdown measures and illustrates the insights that can be gleaned from the statistical analysis of helpline data.

Deep Learning Algorithms with LIME and Similarity Distance Analysis on COVID-19 Chest X-ray Dataset.

In the last few years, many types of research have been conducted on the most harmful pandemic, COVID-19. Machine learning approaches have been applied to investigate chest X-rays of COVID-19 patients in many respects. This study focuses on the deep learning algorithm from the standpoint of feature space and similarity analysis. Firstly, we utilized Local Interpretable Model-agnostic Explanations (LIME) to justify the necessity of the region of interest (ROI) process and further prepared ROI via U-Net segmentation that masked out non-lung areas of images to prevent the classifier from being distracted by irrelevant features. The experimental results were promising, with detection performance reaching an overall accuracy of 95.5%, a sensitivity of 98.4%, a precision of 94.7%, and an F1 score of 96.5% on the COVID-19 category. Secondly, we applied similarity analysis to identify outliers and further provided an objective confidence reference specific to the similarity distance to centers or boundaries of clusters while inferring. Finally, the experimental results suggested putting more effort into enhancing the low-accuracy subspace locally, which is identified by the similarity distance to the centers. The experimental results were promising, and based on those perspectives, our approach could be more flexible to deploy dedicated classifiers specific to different subspaces instead of one rigid end-to-end black box model for all feature space.

Statistical biases due to anonymization evaluated in an open clinical dataset from COVID-19 patients.

Anonymization has the potential to foster the sharing of medical data. State-of-the-art methods use mathematical models to modify data to reduce privacy risks. However, the degree of protection must be balanced against the impact on statistical properties. We studied an extreme case of this trade-off: the statistical validity of an open medical dataset based on the German National Pandemic Cohort Network (NAPKON), which was prepared for publication using a strong anonymization procedure. Descriptive statistics and results of regression analyses were compared before and after anonymization of multiple variants of the original dataset. Despite significant differences in value distributions, the statistical bias was found to be small in all cases. In the regression analyses, the median absolute deviations of the estimated adjusted odds ratios for different sample sizes ranged from 0.01 [minimum = 0, maximum = 0.58] to 0.52 [minimum = 0.25, maximum = 0.91]. Disproportionate impact on the statistical properties of data is a common argument against the use of anonymization. Our analysis demonstrates that anonymization can actually preserve validity of statistical results in relatively low-dimensional data.

Systematic comparison of published host gene expression signatures for bacterial/viral discrimination.

BACKGROUND: Measuring host gene expression is a promising diagnostic strategy to discriminate bacterial and viral infections. Multiple signatures of varying size, complexity, and target populations have been described. However, there is little information to indicate how the performance of various published signatures compare to one another. METHODS: This systematic comparison of host gene expression signatures evaluated the performance of 28 signatures, validating them in 4589 subjects from 51 publicly available datasets. Thirteen COVID-specific datasets with 1416 subjects were included in a separate analysis. Individual signature performance was evaluated using the area under the receiving operating characteristic curve (AUC) value. Overall signature performance was evaluated using median AUCs and accuracies. RESULTS: Signature performance varied widely, with median AUCs ranging from 0.55 to 0.96 for bacterial classification and 0.69-0.97 for viral classification. Signature size varied (1-398 genes), with smaller signatures generally performing more poorly (P < 0.04). Viral infection was easier to diagnose than bacterial infection (84% vs. 79% overall accuracy, respectively; P < .001). Host gene expression classifiers performed more poorly in some pediatric populations (3 months-1 year and 2-11 years) compared to the adult population for both bacterial infection (73% and 70% vs. 82%, respectively; P < .001) and viral infection (80% and 79% vs. 88%, respectively; P < .001). We did not observe classification differences based on illness severity as defined by ICU admission for bacterial or viral infections. The median AUC across all signatures for COVID-19 classification was 0.80 compared to 0.83 for viral classification in the same datasets. CONCLUSIONS: In this systematic comparison of 28 host gene expression signatures, we observed differences based on a signature's size and characteristics of the validation population, including age and infection type. However, populations used for signature discovery did not impact performance, underscoring the redundancy among many of these signatures. Furthermore, differential performance in specific populations may only be observable through this type of large-scale validation.

Clinical utility of breast pathology data: implications for practising pathologists.

In breast cancer, the quality of the pathology services is of paramount importance as inevitably, the pathologist makes the confirmatory diagnosis and provides prognostic and predictive information, informing treatment plans directly. Various national and international organisations provide a pathology reporting minimum dataset (MDS) to ensure consistency in reporting. While the use of MDS promotes clarity, there may be specific areas requiring the pathologist's input for individual patients and hence pathologists need to be aware of the clinical utility of pathology data to help tailor individualised patient treatment. In this article, we provide numerous examples of the role of pathology data in determining next steps in the patient pathway that are applicable to both the diagnostic and treatment pathways, including neoadjuvant treatment pathways. We also briefly discuss the important role and thereby the clinical utility of pathology data during the COVID-19 pandemic providing a template for the similar scenarios in the future if required.

Multisite learning of high-dimensional heterogeneous data with applications to opioid use disorder study of 15,000 patients across 5 clinical sites.

Integrating data across institutions can improve learning efficiency. To integrate data efficiently while protecting privacy, we propose A one-shot, summary-statistics-based, Distributed Algorithm for fitting Penalized (ADAP) regression models across multiple datasets. ADAP utilizes patient-level data from a lead site and incorporates the first-order (ADAP1) and second-order gradients (ADAP2) of the objective function from collaborating sites to construct a surrogate objective function at the lead site, where model fitting is then completed with proper regularizations applied. We evaluate the performance of the proposed method using both simulation and a real-world application to study risk factors for opioid use disorder (OUD) using 15,000 patient data from the OneFlorida Clinical Research Consortium. Our results show that ADAP performs nearly the same as the pooled estimator but achieves higher estimation accuracy and better variable selection than the local and average estimators. Moreover, ADAP2 successfully handles heterogeneity in covariate distributions.

CoV2K model, a comprehensive representation of SARS-CoV-2 knowledge and data interplay.

Since the outbreak of the COVID-19 pandemic, many research organizations have studied the genome of the SARS-CoV-2 virus; a body of public resources have been published for monitoring its evolution. While we experience an unprecedented richness of information in this domain, we also ascertained the presence of several information quality issues. We hereby propose CoV2K, an abstract model for explaining SARS-CoV-2-related concepts and interactions, focusing on viral mutations, their co-occurrence within variants, and their effects. CoV2K provides a clear and concise route map for understanding different connected types of information related to the virus; it thus drives a process of data and knowledge integration that aggregates information from several current resources, harmonizing their content and overcoming incompleteness and inconsistency issues. CoV2K is available for exploration as a graph that can be queried through a RESTful API addressing single entities or paths through their relationships. Practical use cases demonstrate its application to current knowledge inquiries.

Specialized interferon action in COVID-19.

The impacts of interferon (IFN) signaling on COVID-19 pathology are multiple, with both protective and harmful effects being documented. We report here a multiomics investigation of systemic IFN signaling in hospitalized COVID-19 patients, defining the multiomics biosignatures associated with varying levels of 12 different type I, II, and III IFNs. The antiviral transcriptional response in circulating immune cells is strongly associated with a specific subset of IFNs, most prominently IFNA2 and IFNG. In contrast, proteomics signatures indicative of endothelial damage and platelet activation associate with high levels of IFNB1 and IFNA6. Seroconversion and time since hospitalization associate with a significant decrease in a specific subset of IFNs. Additionally, differential IFN subtype production is linked to distinct constellations of circulating myeloid and lymphoid immune cell types. Each IFN has a unique metabolic signature, with IFNG being the most associated with activation of the kynurenine pathway. IFNs also show differential relationships with clinical markers of poor prognosis and disease severity. For example, whereas IFNG has the strongest association with C-reactive protein and other immune markers of poor prognosis, IFNB1 associates with increased neutrophil to lymphocyte ratio, a marker of late severe disease. Altogether, these results reveal specialized IFN action in COVID-19, with potential diagnostic and therapeutic implications.

COVID-rate: an automated framework for segmentation of COVID-19 lesions from chest CT images.

Novel Coronavirus disease (COVID-19) is a highly contagious respiratory infection that has had devastating effects on the world. Recently, new COVID-19 variants are emerging making the situation more challenging and threatening. Evaluation and quantification of COVID-19 lung abnormalities based on chest Computed Tomography (CT) images can help determining the disease stage, efficiently allocating limited healthcare resources, and making informed treatment decisions. During pandemic era, however, visual assessment and quantification of COVID-19 lung lesions by expert radiologists become expensive and prone to error, which raises an urgent quest to develop practical autonomous solutions. In this context, first, the paper introduces an open-access COVID-19 CT segmentation dataset containing 433 CT images from 82 patients that have been annotated by an expert radiologist. Second, a Deep Neural Network (DNN)-based framework is proposed, referred to as the [Formula: see text], that autonomously segments lung abnormalities associated with COVID-19 from chest CT images. Performance of the proposed [Formula: see text] framework is evaluated through several experiments based on the introduced and external datasets. Third, an unsupervised enhancement approach is introduced that can reduce the gap between the training set and test set and improve the model generalization. The enhanced results show a dice score of 0.8069 and specificity and sensitivity of 0.9969 and 0.8354, respectively. Furthermore, the results indicate that the [Formula: see text] model can efficiently segment COVID-19 lesions in both 2D CT images and whole lung volumes. Results on the external dataset illustrate generalization capabilities of the [Formula: see text] model to CT images obtained from a different scanner.

29 m6A-RNA Methylation (Epitranscriptomic) Regulators Are Regulated in 41 Diseases including Atherosclerosis and Tumors Potentially via ROS Regulation - 102 Transcriptomic Dataset Analyses.

We performed a database mining on 102 transcriptomic datasets for the expressions of 29 m6A-RNA methylation (epitranscriptomic) regulators (m6A-RMRs) in 41 diseases and cancers and made significant findings: (1) a few m6A-RMRs were upregulated; and most m6A-RMRs were downregulated in sepsis, acute respiratory distress syndrome, shock, and trauma; (2) half of 29 m6A-RMRs were downregulated in atherosclerosis; (3) inflammatory bowel disease and rheumatoid arthritis modulated m6A-RMRs more than lupus and psoriasis; (4) some organ failures shared eight upregulated m6A-RMRs; end-stage renal failure (ESRF) downregulated 85% of m6A-RMRs; (5) Middle-East respiratory syndrome coronavirus infections modulated m6A-RMRs the most among viral infections; (6) proinflammatory oxPAPC modulated m6A-RMRs more than DAMP stimulation including LPS and oxLDL; (7) upregulated m6A-RMRs were more than downregulated m6A-RMRs in cancer types; five types of cancers upregulated ≥10 m6A-RMRs; (8) proinflammatory M1 macrophages upregulated seven m6A-RMRs; (9) 86% of m6A-RMRs were differentially expressed in the six clusters of CD4+Foxp3+ immunosuppressive Treg, and 8 out of 12 Treg signatures regulated m6A-RMRs; (10) immune checkpoint receptors TIM3, TIGIT, PD-L2, and CTLA4 modulated m6A-RMRs, and inhibition of CD40 upregulated m6A-RMRs; (11) cytokines and interferons modulated m6A-RMRs; (12) NF-κB and JAK/STAT pathways upregulated more than downregulated m6A-RMRs whereas TP53, PTEN, and APC did the opposite; (13) methionine-homocysteine-methyl cycle enzyme Mthfd1 downregulated more than upregulated m6A-RMRs; (14) m6A writer RBM15 and one m6A eraser FTO, H3K4 methyltransferase MLL1, and DNA methyltransferase, DNMT1, regulated m6A-RMRs; and (15) 40 out of 165 ROS regulators were modulated by m6A eraser FTO and two m6A writers METTL3 and WTAP. Our findings shed new light on the functions of upregulated m6A-RMRs in 41 diseases and cancers, nine cellular and molecular mechanisms, novel therapeutic targets for inflammatory disorders, metabolic cardiovascular diseases, autoimmune diseases, organ failures, and cancers.

Spatiotemporal sentiment variation analysis of geotagged COVID-19 tweets from India using a hybrid deep learning model.

India is a hotspot of the COVID-19 crisis. During the first wave, several lockdowns (L) and gradual unlock (UL) phases were implemented by the government of India (GOI) to curb the virus spread. These phases witnessed many challenges and various day-to-day developments such as virus spread and resource management. Twitter, a social media platform, was extensively used by citizens to react to these events and related topics that varied temporally and geographically. Analyzing these variations can be a potent tool for informed decision-making. This paper attempts to capture these spatiotemporal variations of citizen reactions by predicting and analyzing the sentiments of geotagged tweets during L and UL phases. Various sentiment analysis based studies on the related subject have been done; however, its integration with location intelligence for decision making remains a research gap. The sentiments were predicted through a proposed hybrid Deep Learning (DL) model which leverages the strengths of BiLSTM and CNN model classes. The model was trained on a freely available Sentiment140 dataset and was tested over manually annotated COVID-19 related tweets from India. The model classified the tweets with high accuracy of around 90%, and analysis of geotagged tweets during L and UL phases reveal significant geographical variations. The findings as a decision support system can aid in analyzing citizen reactions toward the resources and events during an ongoing pandemic. The system can have various applications such as resource planning, crowd management, policy formulation, vaccination, prompt response, etc.

Semantic segmentation of COVID-19 lesions with a multiscale dilated convolutional network.

Automatic segmentation of infected lesions from computed tomography (CT) of COVID-19 patients is crucial for accurate diagnosis and follow-up assessment. The remaining challenges are the obvious scale difference between different types of COVID-19 lesions and the similarity between the lesions and normal tissues. This work aims to segment lesions of different scales and lesion boundaries correctly by utilizing multiscale and multilevel features. A novel multiscale dilated convolutional network (MSDC-Net) is proposed against the scale difference of lesions and the low contrast between lesions and normal tissues in CT images. In our MSDC-Net, we propose a multiscale feature capture block (MSFCB) to effectively capture multiscale features for better segmentation of lesions at different scales. Furthermore, a multilevel feature aggregate (MLFA) module is proposed to reduce the information loss in the downsampling process. Experiments on the publicly available COVID-19 CT Segmentation dataset demonstrate that the proposed MSDC-Net is superior to other existing methods in segmenting lesion boundaries and large, medium, and small lesions, and achieves the best results in Dice similarity coefficient, sensitivity and mean intersection-over-union (mIoU) scores of 82.4%, 81.1% and 78.2%, respectively. Compared with other methods, the proposed model has an average improvement of 10.6% and 11.8% on Dice and mIoU. Compared with the existing methods, our network achieves more accurate segmentation of lesions at various scales and lesion boundaries, which will facilitate further clinical analysis. In the future, we consider integrating the automatic detection and segmentation of COVID-19, and conduct research on the automatic diagnosis system of COVID-19.

COVID-19 Detection Based on Lung Ct Scan Using Deep Learning Techniques.

SARS-CoV-2 is a novel virus, responsible for causing the COVID-19 pandemic that has emerged as a pandemic in recent years. Humans are becoming infected with the virus. In 2019, the city of Wuhan reported the first-ever incidence of COVID-19. COVID-19 infected people have symptoms that are related to pneumonia, and the virus affects the body's respiratory organs, making breathing difficult. A real-time reverse transcriptase-polymerase chain reaction (RT-PCR) kit is used to diagnose the disease. Due to a shortage of kits, suspected patients cannot be treated promptly, resulting in disease spread. To develop an alternative, radiologists looked at the changes in radiological imaging, like CT scans, that produce comprehensive pictures of the body of excellent quality. The suspected patient's computed tomography (CT) scan is used to distinguish between a healthy individual and a COVID-19 patient using deep learning algorithms. A lot of deep learning methods have been proposed for COVID-19. The proposed work utilizes CNN architectures like VGG16, DeseNet121, MobileNet, NASNet, Xception, and EfficientNet. The dataset contains 3873 total CT scan images with "COVID" and "Non-COVID." The dataset is divided into train, test, and validation. Accuracies obtained for VGG16 are 97.68%, DenseNet121 is 97.53%, MobileNet is 96.38%, NASNet is 89.51%, Xception is 92.47%, and EfficientNet is 80.19%, respectively. From the obtained analysis, the results show that the VGG16 architecture gives better accuracy compared to other architectures.