COVID-19 prognostic modeling using CT radiomic features and machine learning algorithms: Analysis of a multi-institutional dataset of 14,339 patients.

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.

Incidence of symptomatic venous thromboembolism following hospitalization for coronavirus disease 2019: Prospective results from a multi-center study.

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.

The challenge of deciding between home-discharge versus hospitalization in COVID-19 patients: The role of initial imaging and clinicolaboratory data.

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.

The clinical value of two combination regimens in the Management of Patients Suffering from Covid-19 pneumonia: a single centered, retrospective, observational study.

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.