Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 8 de 8
Filter
1.
Comput Biol Med ; 145: 105467, 2022 06.
Article in English | MEDLINE | ID: covidwho-1763671

ABSTRACT

BACKGROUND: We aimed to analyze the prognostic power of CT-based radiomics models using data of 14,339 COVID-19 patients. METHODS: Whole lung segmentations were performed automatically using a deep learning-based model to extract 107 intensity and texture radiomics features. We used four feature selection algorithms and seven classifiers. We evaluated the models using ten different splitting and cross-validation strategies, including non-harmonized and ComBat-harmonized datasets. The sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were reported. RESULTS: In the test dataset (4,301) 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 + Random Forest (RF) classifier. Similar results were achieved in RT-PCR-only positive test sets (3,644). In ComBat harmonized dataset, Relief feature selector + RF classifier resulted in the highest performance of AUC, reaching 0.83 ± 0.01 (CI95%: 0.81-0.85), with a sensitivity and specificity of 0.77 and 0.74, respectively. ComBat harmonization did not depict statistically significant improvement compared to a non-harmonized dataset. In leave-one-center-out, the combination of ANOVA feature selector and RF classifier resulted in the highest performance. CONCLUSION: Lung CT radiomics features can be used for robust prognostic modeling of COVID-19. The predictive power of the proposed CT radiomics model is more reliable when using a large multicentric heterogeneous dataset, and may be used prospectively in clinical setting to manage COVID-19 patients.


Subject(s)
COVID-19 , Lung Neoplasms , Algorithms , COVID-19/diagnostic imaging , Humans , Machine Learning , Prognosis , Retrospective Studies , Tomography, X-Ray Computed/methods
2.
Phytother Res ; 36(2): 891-898, 2022 Feb.
Article in English | MEDLINE | ID: covidwho-1694652

ABSTRACT

Colchicine has shown clinical benefits in the management of COVID-19 via its anti-inflammatory effect. However, the exact role of colchicine in COVID-19 patients is unknown. The current clinical trial was performed on 202 patients with moderate to severe COVID-19. Patients were randomly assigned in a 1:1 ratio to receive up to a 3-day course of 0.5 mg colchicine followed by a 12-day course of 1 mg colchicine in combination with standard care or a 15-day course of standard care. Among 202 randomized patients, 153 completed the study and received colchicine/standard care or continued standard care (M age, 54.72 [SD, 15.03] years; 93 [63.1%] men). On day 14, patients in the colchicine/standard care group had significantly higher odds of a better clinical status distribution on chest CT evaluation (p = .048). Based on NYHA classification, the percentage change of dyspnea on day 14 between groups was statistically significant (p = .026), indicating a mean of 31.94% change in the intervention group when compared with 19.95% in the control group. According to this study, colchicine can improve clinical outcomes and reduce pulmonary infiltration in COVID-19 patients if contraindications and precautions are considered and it is prescribed at the right time and in appropriate cases.


Subject(s)
COVID-19 , Colchicine/adverse effects , Humans , Male , Middle Aged , Prospective Studies , SARS-CoV-2 , Treatment Outcome
3.
EuropePMC; 2020.
Preprint in English | EuropePMC | ID: ppcovidwho-306118

ABSTRACT

Background: The outbreak of coronavirus disease 2019 (COVID-19) becomes an enormous threat to all human beings. Via this retrospective study conducted on medical records of confirmed COVID-19 pneumonia patients on admission, we investigate the CT manifestation and clinical and laboratory risk factors associated with progression to severe COVID-19 pneumonia and assessed the association among clinical and laboratory records, CT findings, and epidemiological features. The medical records and radiological CT Features of 236 confirmed COVID-19 patients were reviewed at one public hospital and one respiratory clinic in Quom, from 1 August to 30 September 2020. Results: : Among a total of 236 confirmed Covid-19 cases, 62 were infected with moderate to severe COVID-19 disease and required hospital admission, and 174 were followed up on outpatient bases. A significant difference was verified in the mean age between outpatients and hospitalized groups. The incidences of bilateral lung involvement, consolidation, linear opacities, crazy-paving pattern, air bronchogram sign, and the number of lobe involvement were significantly higher in hospitalized groups. However, only the crazy-paving pattern was significantly associated with an SpO2 level lower than 90%, with clinical sign of cough severity. Our data indicate that this pattern is also significantly associated with inflammatory levels and the presence of this pattern along with SpO2 level lower than 90%, older age, diabetes, on admission are independent risk factors for COVID-19 progression to severe level. Conclusions: : The crazy-paving pattern can predict the severity of COVID-19, which is of great significance for the management and follow-up of COVID-19 pneumonia patients. The clinical factors of aging, male gender, and diabetes, may be risk factors for the crazy-paving pattern, whereas severe coughing is considered to be the most important clinical symptom related to this pattern, and SpO2 level lower than 90%, which is a matter of more severity.

4.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-296988

ABSTRACT

Purpose: To derive and validate an effective radiomics-based model for differentiation of COVID-19 pneumonia from other lung diseases using a very large cohort of patients. Methods: We collected 19 private and 5 public datasets, accumulating to 26,307 individual patient images (15,148 COVID-19;9,657 with other lung diseases e.g. non-COVID-19 pneumonia, lung cancer, pulmonary embolism;1502 normal cases). Images were automatically segmented using a validated deep learning (DL) model and the results carefully reviewed. Images were first cropped into lung-only region boxes, then resized to 296 by 216 voxels. Voxel dimensions was resized to 1mm3 followed by 64-bin discretization. The 108 extracted features included shape, first-order histogram and texture features. Univariate analysis was first performed using simple logistic regression. The thresholds were fixed in the training set and then evaluation performed on the test set. False discovery rate (FDR) correction was applied to the p-values. Z-Score normalization was applied to all features. For multivariate analysis, features with high correlation (R2>0.99) were eliminated first using Pearson correlation. We tested 96 different machine learning strategies through cross-combining 4 feature selectors or 8 dimensionality reduction techniques with 8 classifiers. We trained and evaluated our models using 3 different datasets: 1) the entire dataset (26,307 patients: 15,148 COVID-19;11,159 non-COVID-19);2) excluding normal patients in non-COVID-19, and including only RT-PCR positive COVID-19 cases in the COVID-19 class (20,697 patients including 12,419 COVID-19, and 8,278 non-COVID-19));3) including only non-COVID-19 pneumonia patients and a random sample of COVID-19 patients (5,582 patients: 3,000 COVID-19, and 2,582 non-COVID-19) to provide balanced classes. Subsequently, each of these 3 datasets were randomly split into 70% and 30% for training and testing, respectively. All various steps, including feature preprocessing, feature selection, and classification, were performed separately in each dataset. Classification algorithms were optimized during training using grid search algorithms. The best models were chosen by a one-standard-deviation rule in 10-fold cross-validation and then were evaluated on the test sets. Results: In dataset #1, Relief feature selection and RF classifier combination resulted in the highest performance (Area under the receiver operating characteristic curve (AUC) = 0.99, sensitivity = 0.98, specificity = 0.94, accuracy = 0.96, positive predictive value (PPV) = 0.96, and negative predicted value (NPV) = 0.96). In dataset #2, Recursive Feature Elimination (RFE) feature selection and Random Forest (RF) classifier combination resulted in the highest performance (AUC = 0.99, sensitivity = 0.98, specificity = 0.95, accuracy = 0.97, PPV = 0.96, and NPV = 0.98). In dataset #3, the ANOVA feature selection and RF classifier combination resulted in the highest performance (AUC = 0.98, sensitivity = 0.96, specificity = 0.93, accuracy = 0.94, PPV = 0.93, NPV = 0.96). Conclusion: Radiomic features extracted from entire lung combined with machine learning algorithms can enable very effective, routine diagnosis of COVID-19 pneumonia from CT images without the use of any other diagnostic test.

5.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-296987

ABSTRACT

Objective In this large multi-institutional study, we aimed to analyze the prognostic power of computed tomography (CT)-based radiomics models in COVID-19 patients. Methods CT 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 (R 2 >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. Results In 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. Conclusion Lung 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.

6.
Thromb Res ; 198: 135-138, 2021 02.
Article in English | MEDLINE | ID: covidwho-971736

ABSTRACT

BACKGROUND: Thrombosis and pulmonary embolism appear to be major causes of mortality in hospitalized coronavirus disease 2019 (COVID-19) patients. However, few studies have focused on the incidence of venous thromboembolism (VTE) after hospitalization for COVID-19. METHODS: In this multi-center study, we followed 1529 COVID-19 patients for at least 45 days after hospital discharge, who underwent routine telephone follow-up. In case of signs or symptoms of pulmonary embolism (PE) or deep vein thrombosis (DVT), they were invited for an in-hospital visit with a pulmonologist. The primary outcome was symptomatic VTE within 45 days of hospital discharge. RESULTS: Of 1529 COVID-19 patients discharged from hospital, a total of 228 (14.9%) reported potential signs or symptoms of PE or DVT and were seen for an in-hospital visit. Of these, 13 and 12 received Doppler ultrasounds or pulmonary CT angiography, respectively, of whom only one patient was diagnosed with symptomatic PE. Of 51 (3.3%) patients who died after discharge, two deaths were attributed to VTE corresponding to a 45-day cumulative rate of symptomatic VTE of 0.2% (95%CI 0.1%-0.6%; n = 3). There was no evidence of acute respiratory distress syndrome (ARDS) in these patients. Other deaths after hospital discharge included myocardial infarction (n = 13), heart failure (n = 9), and stroke (n = 9). CONCLUSIONS: We did not observe a high rate of symptomatic VTE in COVID-19 patients after hospital discharge. Routine extended thromboprophylaxis after hospitalization for COVID-19 may not have a net clinical benefit. Randomized trials may be warranted.


Subject(s)
COVID-19/epidemiology , Patient Discharge , Pulmonary Embolism/epidemiology , Venous Thromboembolism/epidemiology , Venous Thrombosis/epidemiology , Adult , Aged , Aged, 80 and over , COVID-19/diagnosis , COVID-19/mortality , COVID-19/therapy , Female , Humans , Incidence , Iran/epidemiology , Male , Middle Aged , Prospective Studies , Pulmonary Embolism/diagnosis , Pulmonary Embolism/mortality , Risk Factors , Time Factors , Venous Thromboembolism/diagnosis , Venous Thromboembolism/mortality , Venous Thrombosis/diagnosis , Venous Thrombosis/mortality
7.
Clin Epidemiol Glob Health ; 10: 100673, 2021.
Article in English | MEDLINE | ID: covidwho-956963

ABSTRACT

BACKGROUND/OBJECTIVE: It is important to predict the COVID-19 patient's prognosis, particularly in countries with lack or deficiency of medical resource for patient's triage management. Currently, WHO guideline suggests using chest imaging in addition to clinicolaboratory evaluation to decide on triage between home-discharge versus hospitalization. We designed our study to validate this recommendation to guide clinicians. This study providing some suggestions to guide clinicians for better decision making in 2020. METHODS: In this retrospective study, patients with RT-PCR confirmed COVID-19 (N = 213) were divided in different clinical and management scenarios: home-discharge, ward hospitalization and ICU admission. We reviewed the patient's initial chest CT if available. We evaluated quantitative and qualitative characteristics of CT as well as relevant available clinicolaboratory data. Chi-square, One-Way ANOVA and Paired t-test were used for analysis. RESULTS: The finding showed that most patients with mixed patterns, pleural effusion, 5 lobes involved, total score ≥10, SpO2% ≤ 90, ESR (mm/h) ≥ 60 and WBC (103/µL) ≥ 8000 were hospitalized. Most patients with Ground-glass opacities only, ≤3 lobes involvement, peripheral distribution, SpO2% ≥ 95, ESR (mm/h) < 30 and WBC(103/µL) < 6000 were home-discharged. CONCLUSIONS: This study suggests the use of initial chest CT (qualitative and quantitative evaluation) in addition to initial clinicolaboratory data could be a useful supplementary method for clinical management and it is an excellent decision making tool (home-discharge versus ICU/Ward admission) for clinicians.

8.
Daru ; 28(2): 507-516, 2020 Dec.
Article in English | MEDLINE | ID: covidwho-608004

ABSTRACT

BACKGROUND: There is no identified pharmacological therapy for COVID-19 patients, where potential therapeutic strategies are underway to determine effective therapy under such unprecedented pandemic. Therefore, combination therapies may have the potential of alleviating the patient's outcome. This study aimed at comparing the efficacy of two different combination regimens in improving outcomes of patients infected by novel coronavirus (COVID-19). METHODS: This is a single centered, retrospective, observational study of 60 laboratory-confirmed COVID-19 positive inpatients (≥18 years old) at two wards of the Baqiyatallah Hospital, Tehran, Iran. Patient's data including clinical and laboratory parameters were recorded. According to the drug regimen, the patients were divided into two groups; group I who received regimen I consisting azithromycin, prednisolone, naproxen, and lopinavir/ritonavir and group II who received regimen II including meropenem, levofloxacin, vancomycin, hydroxychloroquine, and oseltamivir. RESULTS: The oxygen saturation (SpO2) and temperature were positively changed in patients receiving regimen I compared to regimen II (P = 0.013 and P = 0.012, respectively). The serum level of C-reactive protein (CRP) changed positively in group I (P < 0.001). Although there was a significant difference in platelets between both groups (75.44 vs 51.62, P < 0.001), their change did not clinically differ between two groups. The findings indicated a significant difference of the average length of stay in hospitals (ALOS) between two groups, where the patients under regimen I showed a shorter ALOS (6.97 vs 9.93, P = 0.001). CONCLUSION: This study revealed the beneficial effect of the short-term use of low-dose prednisolone in combination with azithromycin, naproxen and lopinavir/ritonavir (regimen I), in decreasing ALOS compared to regimen II. Since there is still lack of evidence for safety of this regimen, further investigation in our ongoing follow-up to deal with COVID-19 pneumonia is underway. Graphical abstract.


Subject(s)
COVID-19/drug therapy , Hospitalization/statistics & numerical data , Pneumonia, Viral/drug therapy , Adult , Aged , Azithromycin/administration & dosage , COVID-19/complications , Drug Combinations , Drug Therapy, Combination , Female , Humans , Hydroxychloroquine/administration & dosage , Iran , Length of Stay , Levofloxacin/administration & dosage , Lopinavir/administration & dosage , Male , Meropenem/administration & dosage , Middle Aged , Naproxen/administration & dosage , Oseltamivir/administration & dosage , Pneumonia, Viral/virology , Prednisolone/administration & dosage , Retrospective Studies , Ritonavir/administration & dosage , Treatment Outcome , Vancomycin/administration & dosage
SELECTION OF CITATIONS
SEARCH DETAIL