Background The pneumonia caused by the 2019 novel coronavirus (SARS-CoV-2, also called 2019-nCoV) recently break out in Wuhan, China, and was named as COVID-19. With the spread of the disease, similar cases have also been confirmed in other regions of China. We aimed to report the imaging and clinical characteristics of these patients infected with SARS-CoV-2 in Guangzhou, China. Methods All patients with laboratory-identified SARS-CoV-2 infection by real-time polymerase chain reaction (PCR) were collected between January 23, 2020, and February 4, 2020, in a designated hospital (Guangzhou Eighth People’s Hospital). This analysis included 90 patients (39 men and 51 women; median age, 50 years (age range, 18–86 years). All the included SARS-CoV-2-infected patients underwent non-contrast enhanced chest computed tomography (CT). We analyzed the clinical characteristics of the patients, as well as the distribution characteristics, pattern, morphology, and accompanying manifestations of lung lesions. In addition, after 1–6 days (mean 3.5 days), follow-up chest CT images were evaluated to assess radiological evolution. Findings The majority of infected patients had a history of exposure in Wuhan or to infected patients and mostly presented with fever and cough. More than half of the patients presented bilateral, multifocal lung lesions, with peripheral distribution, and 53 (59%) patients had more than two lobes involved. Of all included patients, COVID-19 pneumonia presented with ground glass opacities in 65 (72%), consolidation in 12 (13%), crazy paving pattern in 11 (12%), interlobular thickening in 33 (37%), adjacent pleura thickening in 50 (56%), and linear opacities combined in 55 (61%). Pleural effusion, pericardial effusion, and lymphadenopathy were uncommon findings. In addition, baseline chest CT did not show any abnormalities in 21 patients (23%), but 3 patients presented bilateral ground glass opacities on the second CT after 3–4 days. Conclusion SARS-CoV-2 infection can be confirmed based on the patient’s history, clinical manifestations, imaging characteristics, and laboratory tests. Chest CT examination plays an important role in the initial diagnosis of the novel coronavirus pneumonia. Multiple patchy ground glass opacities in bilateral multiple lobular with periphery distribution are typical chest CT imaging features of the COVID-19 pneumonia.

Background: Accurate and rapid diagnosis of coronavirus disease (COVID-19) is crucial for timely quarantine and treatment. Purpose: In this study, a deep learning algorithm-based AI model using ResUNet network was developed to evaluate the performance of radiologists with and without AI assistance in distinguishing COVID-19 infected pneumonia patients from other pulmonary infections on CT scans. Methods: For model development and validation, a total number of 694 cases with 111,066 CT slides were retrospectively collected as training data and independent test data in the study. Among them, 118 are confirmed COVID-19 infected pneumonia cases and 576 are other pulmonary infection cases (e.g. tuberculosis cases, common pneumonia cases and non-COVID-19 viral pneumonia cases). The cases were divided into training and testing datasets. The independent test was performed by evaluating and comparing the performance of three radiologists with different years of practice experience in distinguishing COVID-19 infected pneumonia cases with and without the AI assistance. Results: Our final model achieved an overall test accuracy of 0.914 with an area of the receiver operating characteristic (ROC) curve (AUC) of 0.903 in which the sensitivity and specificity are 0.918 and 0.909, respectively. The deep learning-based model then achieved a comparable performance by improving the radiologists’ performance in distinguish COVOD-19 from other pulmonary infections, yielding better average accuracy and sensitivity, from 0.941 to 0.951 and from 0.895 to 0.942, respectively, when compared to radiologists without using AI assistance. Conclusion: A deep learning algorithm-based AI model developed in this study successfully improved radiologists’ performance in distinguishing COVID-19 from other pulmonary infections using chest CT images.

Background: Post-stroke epilepsy (PSE) is a critical complication that worsens both prognosis and quality of life in patients with ischemic stroke. An interpretable machine learning model was developed to predict PSE using medical records from four hospitals in Chongqing.Methods: Medical records, imaging reports, and laboratory test results from 21,459 ischemic stroke patients were collected and analyzed. Univariable and multivariable statistical analyses identified key predictive factors. The dataset was split into a 70% training set and a 30% testing set. To address the class imbalance, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors was employed. Nine widely used machine learning algorithms were evaluated using relevant prediction metrics, with SHAP (SHapley Additive exPlanations) used to interpret the model and assess the contributions of different features.Results: Regression analyses revealed that complications such as hydrocephalus, cerebral hernia, and deep vein thrombosis, as well as specific brain regions (frontal, parietal, and temporal lobes), significantly contributed to PSE. Factors such as age, gender, NIH Stroke Scale (NIHSS) scores, and laboratory results like WBC count and D-dimer levels were associated with increased PSE risk. Tree-based methods like Random Forest, XGBoost, and LightGBM showed strong predictive performance, achieving an AUC of 0.99.Conclusions: The model accurately predicts PSE risk, with tree-based models demonstrating superior performance. NIHSS score, WBC count, and D-dimer were identified as the most crucial predictors.Funding: The research is funded by Central University basic research young teachers and students research ability promotion sub-projec t(2023CDJYGRH-ZD06), and by Emergency Medicine Chongqing Key Laboratory Talent Innovation and development joint fund project (2024RCCX10).