Search

BackgroundThe number of deaths from COVID-19 continues to surge worldwide. In particular, if a patient’s condition is sufficiently severe to require invasive ventilation, it is more likely to lead to death than to recovery. ObjectiveThe goal of our study was to analyze the factors related to COVID-19 severity in patients and to develop an artificial intelligence (AI) model to predict the severity of COVID-19 at an early stage. MethodsWe developed an AI model that predicts severity based on data from 5601 COVID-19 patients from all national and regional hospitals across South Korea as of April 2020. The clinical severity of COVID-19 was divided into two categories: low and high severity. The condition of patients in the low-severity group corresponded to no limit of activity, oxygen support with nasal prong or facial mask, and noninvasive ventilation. The condition of patients in the high-severity group corresponded to invasive ventilation, multi-organ failure with extracorporeal membrane oxygenation required, and death. For the AI model input, we used 37 variables from the medical records, including basic patient information, a physical index, initial examination findings, clinical findings, comorbid diseases, and general blood test results at an early stage. Feature importance analysis was performed with AdaBoost, random forest, and eXtreme Gradient Boosting (XGBoost); the AI model for predicting COVID-19 severity among patients was developed with a 5-layer deep neural network (DNN) with the 20 most important features, which were selected based on ranked feature importance analysis of 37 features from the comprehensive data set. The selection procedure was performed using sensitivity, specificity, accuracy, balanced accuracy, and area under the curve (AUC). ResultsWe found that age was the most important factor for predicting disease severity, followed by lymphocyte level, platelet count, and shortness of breath or dyspnea. Our proposed 5-layer DNN with the 20 most important features provided high sensitivity (90.2%), specificity (90.4%), accuracy (90.4%), balanced accuracy (90.3%), and AUC (0.96). ConclusionsOur proposed AI model with the selected features was able to predict the severity of COVID-19 accurately. We also made a web application so that anyone can access the model. We believe that sharing the AI model with the public will be helpful in validating and improving its performance.

BackgroundCOVID-19, which is accompanied by acute respiratory distress, multiple organ failure, and death, has spread worldwide much faster than previously thought. However, at present, it has limited treatments. ObjectiveTo overcome this issue, we developed an artificial intelligence (AI) model of COVID-19, named EDRnet (ensemble learning model based on deep neural network and random forest models), to predict in-hospital mortality using a routine blood sample at the time of hospital admission. MethodsWe selected 28 blood biomarkers and used the age and gender information of patients as model inputs. To improve the mortality prediction, we adopted an ensemble approach combining deep neural network and random forest models. We trained our model with a database of blood samples from 361 COVID-19 patients in Wuhan, China, and applied it to 106 COVID-19 patients in three Korean medical institutions. ResultsIn the testing data sets, EDRnet provided high sensitivity (100%), specificity (91%), and accuracy (92%). To extend the number of patient data points, we developed a web application (BeatCOVID19) where anyone can access the model to predict mortality and can register his or her own blood laboratory results. ConclusionsOur new AI model, EDRnet, accurately predicts the mortality rate for COVID-19. It is publicly available and aims to help health care providers fight COVID-19 and improve patients’ outcomes.

BackgroundMuscle quality is associated with fatty degeneration or infiltration of the muscle, which may be associated with decreased muscle function and increased disability. ObjectiveThe aim of this study is to evaluate the feasibility of automated quantitative measurements of the skeletal muscle on computed tomography (CT) images to assess normal-attenuation muscle and myosteatosis. MethodsWe developed a web-based toolkit to generate a muscle quality map by categorizing muscle components. First, automatic segmentation of the total abdominal muscle area (TAMA), visceral fat area, and subcutaneous fat area was performed using a predeveloped deep learning model on a single axial CT image at the L3 vertebral level. Second, the Hounsfield unit of each pixel in the TAMA was measured and categorized into 3 components: normal-attenuation muscle area (NAMA), low-attenuation muscle area (LAMA), and inter/intramuscular adipose tissue (IMAT) area. The myosteatosis area was derived by adding the LAMA and IMAT area. We tested the feasibility of the toolkit using randomly selected healthy participants, comprising 6 different age groups (20 to 79 years). With stratification by sex, these indices were compared between age groups using 1-way analysis of variance (ANOVA). Correlations between the myosteatosis area or muscle densities and fat areas were analyzed using Pearson correlation coefficient r. ResultsA total of 240 healthy participants (135 men and 105 women) with 40 participants per age group were included in the study. In the 1-way ANOVA, the NAMA, LAMA, and IMAT were significantly different between the age groups in both male and female participants (P≤.004), whereas the TAMA showed a significant difference only in male participants (male, P

BackgroundCoronavirus disease (COVID-19) has spread explosively worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) is a relevant screening tool due to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely occupied fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. ObjectiveWe aimed to rapidly develop an AI technique to diagnose COVID-19 pneumonia in CT images and differentiate it from non–COVID-19 pneumonia and nonpneumonia diseases. MethodsA simple 2D deep learning framework, named the fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning using one of four state-of-the-art pretrained deep learning models (VGG16, ResNet-50, Inception-v3, or Xception) as a backbone. For training and testing of FCONet, we collected 3993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and nonpneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training set and a testing set at a ratio of 8:2. For the testing data set, the diagnostic performance of the four pretrained FCONet models to diagnose COVID-19 pneumonia was compared. In addition, we tested the FCONet models on an external testing data set extracted from embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. ResultsAmong the four pretrained models of FCONet, ResNet-50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100.00%, and accuracy 99.87%) and outperformed the other three pretrained models in the testing data set. In the additional external testing data set using low-quality CT images, the detection accuracy of the ResNet-50 model was the highest (96.97%), followed by Xception, Inception-v3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). ConclusionsFCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing data set, the FCONet model based on ResNet-50 appears to be the best model, as it outperformed other FCONet models based on VGG16, Xception, and Inception-v3.

Coordinating the balance between development and stress responses is critical for organismal survival. However, the cellular signaling controlling this mechanism is not well understood. In Caenorhabditis elegans, it has been hypothesized that a genetic network regulated by NIPI-3/Tibbles may control the balance between animal development and immune response. Using a nipi-3(0) lethality suppressor screen in C. elegans, we reveal a novel role for N-terminal acetyltransferase C complex natc-1/2/3 and histone deacetylase hda-4, in the control of animal development. These signaling proteins act, at least in part, through a PMK-1 p38 MAP kinase pathway (TIR-1-NSY-1-SEK-1-PMK-1), which plays a critical role in the innate immunity against infection. Additionally, using a transcriptional reporter of SEK-1, a signaling molecule within this p38 MAP kinase system that acts directly downstream of C/EBP bZip transcription factor CEBP-1, we find unexpected positive control of sek-1 transcription by SEK-1 along with several other p38 MAP kinase pathway components. Together, these data demonstrate a role for NIPI-3 regulators in animal development, operating, at least in part through a PMK-1 p38 MAPK pathway. Because the C. elegans p38 MAP kinase pathway is well known for its role in cellular stress responses, the novel biological components and mechanisms pertaining to development identified here may also contribute to the balance between stress response and development.

mRNA decay factors regulate mRNA turnover by recruiting non-translating mRNAs and targeting them for translational repression and mRNA degradation. How mRNA decay pathways regulate cellular function in vivo with specificity is poorly understood. Here, we show that C. elegans mRNA decay factors, including the translational repressors CAR-1/LSM14 and CGH-1/DDX6, and the decapping enzymes DCAP-1/DCP1, function in neurons to differentially regulate axon development, maintenance, and regrowth following injury. In neuronal cell bodies, CAR-1 fully colocalizes with CGH-1 and partially colocalizes with DCAP-1, suggesting that mRNA decay components form at least two types of cytoplasmic granules. Following axon injury in adult neurons, loss of CAR-1 or CGH-1 results in increased axon regrowth and growth cone formation, whereas loss of DCAP-1 or DCAP-2 results in reduced regrowth. To determine how CAR-1 inhibits regrowth, we analyzed mRNAs bound to pan-neuronally expressed GFP::CAR-1 using a crosslinking and immunoprecipitation-based approach. Among the putative mRNA targets of CAR-1, we characterized the roles of micu-1, a regulator of the mitochondrial calcium uniporter MCU-1, in axon injury. We show that loss of car-1 results increased MICU-1 protein levels, and that enhanced axon regrowth in car-1 mutants is dependent on micu-1 and mcu-1. Moreover, axon injury induces transient calcium influx into axonal mitochondria, dependent on MCU-1. In car-1 loss-of-function mutants and in micu-1 overexpressing animals, the axonal mitochondrial calcium influx is more sustained, which likely underlies enhanced axon regrowth. Our data uncover a novel pathway that controls axon regrowth through axonal mitochondrial calcium uptake.

The basic leucine-zipper (bZIP) domain transcription factors CCAAT/enhancer-binding proteins (C/EBP) have a variety of roles in cell proliferation, differentiation, and stress response. In the nervous system, several isoforms of C/EBP function in learning and memory, neuronal plasticity, neuroinflammation, and axon regeneration. We previously reported that the Caenorhabditis elegans C/EBP homolog, CEBP-1, is essential for axon regeneration. CEBP-1 consists of 319 amino acids, with its bZIP domain at the C-terminus and a long N-terminal fragment with no known protein motifs. Here, using forward genetic screening with targeted genome editing, we have identified a unique domain in the N-terminus that is critical for its in vivo function. Additionally, we characterized three nuclear localization signals (NLS) in CEBP-1 that act together to mediate CEBP-1's nuclear import. Moreover, the Importin-α, IMA-3, can bind to CEBP-1 via one of the NLS. ima-3 is ubiquitously expressed in all somatic cells, and ima-3 null mutants are larval lethal. Using Cre-lox dependent neuron-specific deletion strategy, we show that ima-3 is not critical for axon development, but is required for axon regeneration in adults. Together, these data advance our understanding of CEBP-1's function, and suggest new regulators that remain to be identified to expand the CEBP-1 protein interactome.