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.

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.

This study presents an innovative approach to enhancing the security of visual medical data in the generative AI environment through the integration of blockchain technology. By combining the strengths of blockchain and generative AI, the research team aimed to address the timely challenge of safeguarding visual medical content. The participating researchers conducted a comprehensive analysis, examining the vulnerabilities of medical AI services, personal information protection issues, and overall security weaknesses. This multifaceted exploration led to an in-depth evaluation of the model's performance and security. Notably, the correlation between accuracy, detection rate, and error rate was scrutinized. This analysis revealed insights into the model's strengths and limitations, while the consideration of standard deviation shed light on the model's stability and performance variability. The study proposed practical improvements, emphasizing the reduction of false negatives to enhance detection rate and leveraging blockchain technology to ensure visual data integrity in medical applications. Applying blockchain to generative AI-created medical content addresses key personal information protection issues. By utilizing the distributed ledger system of blockchain, the research team aimed to protect the privacy and integrity of medical data especially medical images. This approach not only enhances security but also enables transparent and tamper-proof record-keeping. Additionally, the use of generative AI models ensures the creation of novel medical content without compromising personal information, further safeguarding patient privacy. In conclusion, this study showcases the potential of blockchain-based solutions in the medical field, particularly in securing sensitive medical data and protecting patient privacy. The proposed approach, combining blockchain and generative AI, offers a promising direction toward more robust and secure medical content management. Further research and advancements in this area will undoubtedly contribute to the development of robust and privacy-preserving healthcare systems, and visual diagnostic systems. [ABSTRACT FROM AUTHOR]

Background: Despite the development of several imaging modalities for diagnosing Fontan-associated liver disease (FALD), there is no optimal protocol for the follow-up of FALD. We conducted a systematic review and meta-analysis to identify factors related to liver fibrosis using biopsy reports and to identify alternative noninvasive modalities that could better reflect liver histological changes in FALD. Methods: A systematic review and meta-analysis were conducted following the PRISMA guidelines Table S2. We searched Embase, PubMed, and Cochrane databases for studies on FALD, focusing on those assessing clinical factors associated with liver fibrosis severity through liver biopsy and noninvasive imaging techniques. Results: A total of 42 studies were identified, of which 12 conducted meta-analyses and subgroup analyses of the severity of liver fibrosis using liver biopsies. Liver biopsy results showed a weak positive correlation between Fontan duration and fibrosis severity (R = 0.36). Subgroup analyses revealed significant differences in hemodynamic parameters, such as Fontan pressure, between patients with mild and severe fibrosis. Platelet count, aspartate aminotransferase to platelet ratio index, and fibrosis-4 index were significantly associated with fibrosis severity, with severe fibrosis showing lower platelet counts and higher aspartate aminotransferase to platelet ratio index and fibrosis-4 index levels. Noninvasive imaging modalities, particularly magnetic resonance elastography and shear wave elastography, demonstrated strong correlations with biopsy-confirmed fibrosis severity. Conclusions: This study identifies key clinical factors, and noninvasive modalities accurately reflect liver fibrosis severity in patients with FALD. Clinical factors such as platelet count, aspartate aminotransferase to platelet ratio index, and fibrosis-4 index may aid in identifying patients at risk for severe fibrosis. In addition, magnetic resonance elastography and shear wave elastography are promising tools for noninvasive assessment in our study. Further research is needed to refine these diagnostic approaches and improve patient management. [ABSTRACT FROM AUTHOR]

Non-fungible tokens (NFTs) are digital identifiers containing metadata, such as token number, title, content, and image URL, and are linked to digital assets, which are characterized by the fact that, unlike conventional virtual assets, they have their own unique value and cannot be replaced. NFTs cannot be deleted or forged; therefore, they can be used to authenticate the ownership of digital assets. The metadata of the NFTs are uploaded to the interplanetary file system (IPFS), which is a distributed file system, and converted into unique content identifiers (CIDs) that are stored on the blockchain. Digital content (DC) is divided into multiple pieces; it also has its own unique value and is distributed and stored using the IPFS. This study built an NFT-based IPFS testbed and experimented with the process of generating unique values for DC divided into three groups and sharing them. The results confirmed that each DC had a unique hash value and no duplicates existed. [ABSTRACT FROM AUTHOR]