Search

ObjectiveIn this large multi-institutional study, we aimed to analyze the prognostic power of computed tomography (CT)-based radiomics models in COVID-19 patients.MethodsCT images of 14,339 COVID-19 patients with overall survival outcome were collected from 19 medical centers. Whole lung segmentations were performed automatically using a previously validated deep learning-based model, and regions of interest were further evaluated and modified by a human observer. All images were resampled to an isotropic voxel size, intensities were discretized into 64-binning size, and 105 radiomics features, including shape, intensity, and texture features were extracted from the lung mask. Radiomics features were normalized using Z-score normalization. High-correlated features using Pearson (R2>0.99) were eliminated. We applied the Synthetic Minority Oversampling Technique (SMOT) algorithm in only the training set for different models to overcome unbalance classes. We used 4 feature selection algorithms, namely Analysis of Variance (ANOVA), Kruskal- Wallis (KW), Recursive Feature Elimination (RFE), and Relief. For the classification task, we used seven classifiers, including Logistic Regression (LR), Least Absolute Shrinkage and Selection Operator (LASSO), Linear Discriminant Analysis (LDA), Random Forest (RF), AdaBoost (AB), Naïve Bayes (NB), and Multilayer Perceptron (MLP). The models were built and evaluated using training and testing sets, respectively. Specifically, we evaluated the models using 10 different splitting and cross-validation strategies, including different types of test datasets (e.g. non-harmonized vs. ComBat-harmonized datasets). The sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were reported for models evaluation.ResultsIn the test dataset (4301) consisting of CT and/or RT-PCR positive cases, AUC, sensitivity, and specificity of 0.83±0.01 (CI95%: 0.81-0.85), 0.81, and 0.72, respectively, were obtained by ANOVA feature selector + RF classifier. In RT-PCR-only positive test sets (3644), similar results were achieved, and there was no statistically significant difference. In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in highest performance of AUC, reaching 0.83±0.01 (CI95%: 0.81-0.85), with sensitivity and specificity of 0.77 and 0.74, respectively. At the same time, ComBat harmonization did not depict statistically significant improvement relevant to non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and LR classifier resulted in the highest performance of AUC (0.80±0.084) with sensitivity and specificity of 0.77 ± 0.11 and 0.76 ± 0.075, respectively.ConclusionLung CT radiomics features can be used towards robust prognostic modeling of COVID-19 in large heterogeneous datasets gathered from multiple centers. As such, CT radiomics-based model has significant potential for use in prospective clinical settings towards improved management of COVID-19 patients.

Background & AimCoronavirus 2019 (COVID-19) outbreak in the Middle East was initially reported in Qom-Iran. Clinical and epidemiologic and mortality risk factors details have not been already fully explained.MethodIn a retrospective study, the hospitalized adult patients with laboratory diagnosed COVID-19 between February 25 to March 20, 2020 were enrolled. A checklist including demographic, clinical, laboratorial, imaging, and treatment data was completed for each of the participant. The data were extracted from electronic medical records. In case of lack of information, a member of the research team contacted them via phone. All the dead patients and the first one hundred survived patients with these criteria were enrolled in the study. Outcome defined as death or discharge of patients.ResultsOf admitted patients, 200 patients who had been discharged or died were involved in this study. The majority of them were male (56%). The mean age of all patients was 62.63 ± 14.9. Co-morbidity was reported in 124 (62%) patients in which hypertension was the most common. The most frequent clinical presentations were dyspnea in 169 (84.5%), cough in 150 (75%), and fatigue/weakness in 123 (61.5%) patients. The main complications were respiratory failure and acute respiratory distress syndrome with prevalence of 143 (71.5%) and 105 (52.5%), accordingly. Multiple logistic models showed that decline of hemoglobin level (OR = 10.09), neutrophilia (OR = 3.48), high blood urea nitrogen (OR = 4.29,), SpO2 ≤ 90% (OR = 3.38), and presence of patchy consolidation (OR = 6.81) were associated with poor outcome.ConclusionCOVID-19 disease has multiple aspects. CT scan findings, complete blood count with differential, high blood urea nitrogen and SpO2 are related to mortality. Hence needs to pay serious attention during admitting and surveillance, particularly among elderly patients and who with preexisting morbidities.

Introduction: Considering the increasing number of patients referred to gastroenterology clinics, we report a suspected case of coronavirus disease 2019 (COVID-19) with only gastrointestinal (GI) presentation in Qom, Iran. Case Presentation: A 74-year-old man with epigastric pain, diarrhea and vomiting for one week was treated, based on the routine abdominal treatment protocol. Since all GI symptoms were resistant to therapy, we decided to perform laboratory assays for a more accurate diagnosis of the disease. Considering the persistence of abdominal pain and nausea, abdominal and pelvic computed tomography (CT) scans, as well as endoscopy and colonoscopy, were performed. After performing the chest CT scan, we noticed the involvement of the lungs. The patient did not have any respiratory symptoms, and at the time of his hospitalization, the COVID-19 epidemic had been reported in Iran. With the progression of the disease, he started to experience mild fever (38°C). Using a specific COVID-19 kit, he was diagnosed with COVID-19 after precise evaluations. However, without any medications, all of his symptoms subsided after 2 - 3 weeks. Conclusions: It is important for all physicians to know that some pure GI symptoms, which are resistant to therapy, may be the only symptoms in suspected COVID-19 patients. Timely diagnosis and isolation of these patients can guarantee population to avoid the spread of this highly contagious infection.

Background: Diabetes is one of the most serious metabolic disorders to affect different organs in the body. Patients with diabetes are hence at risk of developing other problems. Urinary tract infections (UTI) are one of the problems that occur more commonly in diabetic patients than in others. There are several risk factors that lead to the incidence of UTI in diabetic patients. Objectives: We conducted this study to determine the effect of different factors on the incidence of UTI in diabetic patients in order to decrease the incidence of this problem. Patients and Methods: In this cross-sectional study, data concerning 233 patients who were referred to the largest diabetes center in Khorramabad, Lorestan province, Iran, were recorded. The relationships between various factors and the incidence of UTI in these patients were evaluated using SPSS version 16. We used chi-square and logistic regression to analyze the data. A P < 0.05 was considered to be statistically significant. Results: The incidence of UTI increased significantly with increasing age (P = 0.009). The incidence of UTI was higher among females than among males, and it was higher among unemployed people than among those in other occupations. The prevalence of UTI among patients who control their diabetes through diet and exercise was lower than that among those undergoing other types of treatment; however, no significant relationship was found between the different types of oral medication and the incidence of UTI. We did not find any relationship between the incidence of UTI in diabetic patients and other factors such as literacy, marital status, BMI, addiction, history of hospitalization, and level of HbA1c. Conclusions: We found that age, gender, occupation, and the type of medication used are all risk factors for the incidence of UTI in diabetic patients. Other factors such as literacy, marital status, addiction, and history of hospitalization did not have any significant association with the incidence of UTI in diabetic patients.