A hybrid machine learning/deep learning COVID-19 severity predictive model from CT images and clinical data.

COVID-19 clinical presentation and prognosis are highly variable, ranging from asymptomatic and paucisymptomatic cases to acute respiratory distress syndrome and multi-organ involvement. We developed a hybrid machine learning/deep learning model to classify patients in two outcome categories, non-ICU and ICU (intensive care admission or death), using 558 patients admitted in a northern Italy hospital in February/May of 2020. A fully 3D patient-level CNN classifier on baseline CT images is used as feature extractor. Features extracted, alongside with laboratory and clinical data, are fed for selection in a Boruta algorithm with SHAP game theoretical values. A classifier is built on the reduced feature space using CatBoost gradient boosting algorithm and reaching a probabilistic AUC of 0.949 on holdout test set. The model aims to provide clinical decision support to medical doctors, with the probability score of belonging to an outcome class and with case-based SHAP interpretation of features importance.

Delirium in Patients with SARS-CoV-2 Infection: A Multicenter Study.

OBJECTIVES: The aims of this study are to report the prevalence of delirium on admission to the unit in patients hospitalized with SARS-CoV-2 infection, to identify the factors associated with delirium, and to evaluate the association between delirium and in-hospital mortality. DESIGN: Multicenter observational cohort study. SETTINGS: Acute medical units in four Italian hospitals. PARTICIPANTS: A total of 516 patients (median age 78 years) admitted to the participating centers with SARS-CoV-2 infection from February 22 to May 17, 2020. MEASUREMENTS: Comprehensive medical assessment with detailed history, physical examinations, functional status, laboratory and imaging procedures. On admission, delirium was determined by the Diagnostic and Statistical Manual of Mental Disorders (5th edition) criteria, 4AT, m-Richmond Agitation Sedation Scale, or clinical impression depending on the site. The primary outcomes were delirium rates and in-hospital mortality. RESULTS: Overall, 73 (14.1%, 95% confidence interval (CI) = 11.0-17.3%) patients presented delirium on admission. Factors significantly associated with delirium were dementia (odds ratio, OR = 4.66, 95% CI = 2.03-10.69), the number of chronic diseases (OR = 1.20, 95% CI = 1.03; 1.40), and chest X-ray or CT opacity (OR = 3.29, 95% CI = 1.12-9.64 and 3.35, 95% CI = 1.07-10.47, for multiple or bilateral opacities and single opacity vs no opacity, respectively). There were 148 (33.4%) in-hospital deaths in the no-delirium group and 43 (58.9%) in the delirium group (P-value assessed using the Gray test <.001). As assessed by a multivariable Cox model, patients with delirium on admission showed an almost twofold increased hazard ratio for in-hospital mortality with respect to patients without delirium (hazard ratio = 1.88, 95% CI = 1.25-2.83). CONCLUSION: Delirium is prevalent and associated with in-hospital mortality among older patients hospitalized with SARS-CoV-2 infection.

[Pulmonary embolism and SARS-CoV-2: analysis of patients hospitalized for pulmonary embolism and COVID-19 in a Northern Italian center]. / Embolia polmonare e SARS-CoV-2: analisi delle caratteristiche dei pazienti ricoverati presso un centro nel nord Italia per embolia polmonare associata a COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has shown high morbidity and mortality and the relationship between pulmonary embolism (PE) and COVID-19 is well established in the literature. METHODS: We describe the characteristics of a cohort of COVID-19 patients (EP-COV) hospitalized at our Centre with PE, investigating how COVID-19 may have influenced their outcomes, as compared to patients without COVID-19 hospitalized for PE in the same months of 2020 (EP-2020) and 2019 (EP-2019). RESULTS: EP-COV patients (n=25) were younger (60.5 ± 8.5 vs 71.4 ± 14.5 vs 70.9 ± 11.8 years, p=0.003), more frequently male (76% vs 48% vs 35%, p=0.016), with a lower history of neoplasia (12% vs 47% vs 40%, p=0.028) and more clinically severe (SOFA score 3.4 ± 1.4 vs 2.2 ± 1.4 vs 1 ± 1.1, p<0.001 and PaO2/FiO2 ratio 223.8 ± 75.5 vs 306.5 ± 49.3 vs 311.8 ± 107.5) than EP-2020 (n=17) and EP-2019 patients (n=20). D-dimer and C-reactive protein were higher in EP-COV (p=0.038 e p<0.001, respectively). The rate of concomitant deep vein thrombosis associated with PE did not differ significantly between the three groups. EP-COV patients developed PE more frequently during in-hospital stay than non-COVID-19 patients (p = 0.016). The mortality rate was higher in EP-COV than in EP-2020 and EP-2019 patients (36% vs 0% vs 5%, p=0.019). CONCLUSIONS: In our study, the risk factors for PE in COVID-19 patients seem to differ from the traditional risk factors for venous thromboembolism; EP-COV patients are clinically more severe and display a higher mortality rate than EP-2020 and EP-2019 patients.

Machine Learning to Predict In-Hospital Mortality in COVID-19 Patients Using Computed Tomography-Derived Pulmonary and Vascular Features.

Pulmonary parenchymal and vascular damage are frequently reported in COVID-19 patients and can be assessed with unenhanced chest computed tomography (CT), widely used as a triaging exam. Integrating clinical data, chest CT features, and CT-derived vascular metrics, we aimed to build a predictive model of in-hospital mortality using univariate analysis (Mann-Whitney U test) and machine learning models (support vectors machines (SVM) and multilayer perceptrons (MLP)). Patients with RT-PCR-confirmed SARS-CoV-2 infection and unenhanced chest CT performed on emergency department admission were included after retrieving their outcome (discharge or death), with an 85/15% training/test dataset split. Out of 897 patients, the 229 (26%) patients who died during hospitalization had higher median pulmonary artery diameter (29.0 mm) than patients who survived (27.0 mm, p < 0.001) and higher median ascending aortic diameter (36.6 mm versus 34.0 mm, p < 0.001). SVM and MLP best models considered the same ten input features, yielding a 0.747 (precision 0.522, recall 0.800) and 0.844 (precision 0.680, recall 0.567) area under the curve, respectively. In this model integrating clinical and radiological data, pulmonary artery diameter was the third most important predictor after age and parenchymal involvement extent, contributing to reliable in-hospital mortality prediction, highlighting the value of vascular metrics in improving patient stratification.

CT-derived Chest Muscle Metrics for Outcome Prediction in Patients with COVID-19.

Background Lower muscle mass is a known predictor of unfavorable outcomes, but its prognostic impact on patients with COVID-19 is unknown. Purpose To investigate the contribution of CT-derived muscle status in predicting clinical outcomes in patients with COVID-19. Materials and Methods Clinical or laboratory data and outcomes (intensive care unit [ICU] admission and death) were retrospectively retrieved for patients with reverse transcriptase polymerase chain reaction-confirmed SARS-CoV-2 infection, who underwent chest CT on admission in four hospitals in Northern Italy from February 21 to April 30, 2020. The extent and type of pulmonary involvement, mediastinal lymphadenopathy, and pleural effusion were assessed. Cross-sectional areas and attenuation by paravertebral muscles were measured on axial CT images at the T5 and T12 vertebral level. Multivariable linear and binary logistic regression, including calculation of odds ratios (ORs) with 95% CIs, were used to build four models to predict ICU admission and death, which were tested and compared by using receiver operating characteristic curve analysis. Results A total of 552 patients (364 men and 188 women; median age, 65 years [interquartile range, 54-75 years]) were included. In a CT-based model, lower-than-median T5 paravertebral muscle areas showed the highest ORs for ICU admission (OR, 4.8; 95% CI: 2.7, 8.5; P < .001) and death (OR, 2.3; 95% CI: 1.0, 2.9; P = .03). When clinical variables were included in the model, lower-than-median T5 paravertebral muscle areas still showed the highest ORs for both ICU admission (OR, 4.3; 95%: CI: 2.5, 7.7; P < .001) and death (OR, 2.3; 95% CI: 1.3, 3.7; P = .001). At receiver operating characteristic analysis, the CT-based model and the model including clinical variables showed the same area under the receiver operating characteristic curve (AUC) for ICU admission prediction (AUC, 0.83; P = .38) and were not different in terms of predicting death (AUC, 0.86 vs AUC, 0.87, respectively; P = .28). Conclusion In hospitalized patients with COVID-19, lower muscle mass on CT images was independently associated with intensive care unit admission and in-hospital mortality. © RSNA, 2021 Online supplemental material is available for this article.

Drug-Related Pneumonitis in Cancer Treatment during the COVID-19 Era.

Interstitial lung disease is recognized as a group of diseases with a different etiopathogenesis characterized by chronic lung inflammation with the accumulation of inflammatory cells, lymphocytes and macrophages, and the consequent release of proinflammatory cytokines. Various degrees of pulmonary fibrosis can be associated with this inflammatory condition. Interstitial lung disease related to oncological drugs is a relevant problem in clinical practice. The etiopathogenetic mechanisms underlying this adverse event are not completely known but can be partly explained by the mechanism of action of the drug involved. Therefore, knowledge of the relevance of this potentially fatal adverse event supported by the reported safety data of pivotal studies becomes fundamental in the management of patients. The prompt diagnosis of drug-related pneumonia and the consequent differential diagnosis with other forms of pneumonia allow a rapid suspension of treatment and the establishment of an immunosuppressive treatment if necessary. In the context of the health emergency related to SARS CoV2 infection and COVID-19-related interstitial lung disease, such knowledge holds decisive relevance in the conscious choice of cancer treatments. Our intent was to describe the oncological drugs most correlated with this adverse event by reporting, where possible, the percentages of insurgency in pivotal studies to provide an overview and therefore promote greater awareness of this important toxicity related to oncological treatment.

Stroke in patients with COVID-19: Clinical and neuroimaging characteristics.

Acute cerebrovascular disease, particularly ischemic stroke, has emerged as a serious complication of infection by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the etiologic agent of the Coronavirus disease-2019 (COVID-19). Accumulating data on patients with COVID-19-associated stroke have shed light on specificities concerning clinical presentation, neuroimaging findings, and outcome. Such specificities include a propensity towards large vessel occlusion, multi-territory stroke, and involvement of otherwise uncommonly affected vessels. Conversely, small-vessel brain disease, cerebral venous thrombosis, and intracerebral hemorrhage appear to be less frequent. Atypical neurovascular presentations were also described, ranging from bilateral carotid artery dissection to posterior reversible encephalopathy syndrome (PRES), and vasculitis. Cases presenting with encephalopathy or encephalitis with seizures heralding stroke were particularly challenging. The pathogenesis and optimal management of ischemic stroke associated with COVID-19 still remain uncertain, but emerging evidence suggest that cytokine storm-triggered coagulopathy and endotheliopathy represent possible targetable mechanisms. Some specific management issues in this population include the difficulty in identifying clinical signs of stroke in critically ill patients in the intensive care unit, as well as the need for a protected pathway for brain imaging, intravenous thrombolysis, and mechanical thrombectomy, keeping in mind that "time is brain" also for COVID-19 patients. In this review, we discuss the novel developments and challenges for the diagnosis and treatment of stroke in patients with COVID-19, and delineate the principles for a rational approach toward precision medicine in this emerging field.

COVID-19 acute respiratory distress syndrome: can iloprost have a role for the treatment?

Pulmonary infection of 2019-nCoV can frequently induce acute respiratory distress syndrome (ARDS) with partial pressure of arterial oxygen/fraction of inspired oxygen ratio (pO2/FiO2) of less than 300 mmHg. Moreover, it can be complicated with cardiac injury or arrhythmia, microvascular and large-vessel thrombosis. We describe a case of a patient with COVID19-ARDS and concomitant critical ischemia of the limbs. Iloprost treatment, an analogue of a prostacyclin PGI2, was started for residual left forefoot ischemia after surgical thromboembolectomy. Unexpectedly, we documented improvement of respiratory performance and lung high resolution computed tomography (HRCT) showed significant regression of the diffuse pulmonary ground-glass opacity. The hypothetical mechanism is that iloprost can enhance perfusion preferentially to well-ventilated lung regions, reduce pressures of peripheral pulmonary vessels and induce reduction of lung interstitial edema. In addition, iloprost antithrombotic effect, endothelial damage repairing and neo-angiogenesis activity could play a relevant role.

Preliminary Analysis of Relationships between COVID19 and Climate, Morphology, and Urbanization in the Lombardy Region (Northern Italy).

The coronavirus disease 2019 (COVID-19) pandemic is the most severe global health and socioeconomic crisis of our time, and represents the greatest challenge faced by the world since the end of the Second World War. The academic literature indicates that climatic features, specifically temperature and absolute humidity, are very important factors affecting infectious pulmonary disease epidemics - such as severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS); however, the influence of climatic parameters on COVID-19 remains extremely controversial. The goal of this study is to individuate relationships between several climate parameters (temperature, relative humidity, accumulated precipitation, solar radiation, evaporation, and wind direction and intensity), local morphological parameters, and new daily positive swabs for COVID-19, which represents the only parameter that can be statistically used to quantify the pandemic. The daily deaths parameter was not considered, because it is not reliable, due to frequent administrative errors. Daily data on meteorological conditions and new cases of COVID-19 were collected for the Lombardy Region (Northern Italy) from 1 March, 2020 to 20 April, 2020. This region exhibited the largest rate of official deaths in the world, with a value of approximately 1700 per million on 30 June 2020. Moreover, the apparent lethality was approximately 17% in this area, mainly due to the considerable housing density and the extensive presence of industrial and craft areas. Both the Mann-Kendall test and multivariate statistical analysis showed that none of the considered climatic variables exhibited statistically significant relationships with the epidemiological evolution of COVID-19, at least during spring months in temperate subcontinental climate areas, with the exception of solar radiation, which was directly related and showed an otherwise low explained variability of approximately 20%. Furthermore, the average temperatures of two highly representative meteorological stations of Molise and Lucania (Southern Italy), the most weakly affected by the pandemic, were approximately 1.5 °C lower than those in Bergamo and Brescia (Lombardy), again confirming that a significant relationship between the increase in temperature and decrease in virulence from COVID-19 is not evident, at least in Italy.

Pneumomediastinum and subcutaneous emphysema in COVID-19: barotrauma or lung frailty?

BACKGROUND: In mechanically ventilated acute respiratory distress syndrome (ARDS) patients infected with the novel coronavirus disease (COVID-19), we frequently recognised the development of pneumomediastinum and/or subcutaneous emphysema despite employing a protective mechanical ventilation strategy. The purpose of this study was to determine if the incidence of pneumomediastinum/subcutaneous emphysema in COVID-19 patients was higher than in ARDS patients without COVID-19 and if this difference could be attributed to barotrauma or to lung frailty. METHODS: We identified both a cohort of patients with ARDS and COVID-19 (CoV-ARDS), and a cohort of patients with ARDS from other causes (noCoV-ARDS).Patients with CoV-ARDS were admitted to an intensive care unit (ICU) during the COVID-19 pandemic and had microbiologically confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. NoCoV-ARDS was identified by an ARDS diagnosis in the 5 years before the COVID-19 pandemic period. RESULTS: Pneumomediastinum/subcutaneous emphysema occurred in 23 out of 169 (13.6%) patients with CoV-ARDS and in three out of 163 (1.9%) patients with noCoV-ARDS (p<0.001). Mortality was 56.5% in CoV-ARDS patients with pneumomediastinum/subcutaneous emphysema and 50% in patients without pneumomediastinum (p=0.46).CoV-ARDS patients had a high incidence of pneumomediastinum/subcutaneous emphysema despite the use of low tidal volume (5.9±0.8 mL·kg-1 ideal body weight) and low airway pressure (plateau pressure 23±4 cmH2O). CONCLUSIONS: We observed a seven-fold increase in pneumomediastinum/subcutaneous emphysema in CoV-ARDS. An increased lung frailty in CoV-ARDS could explain this finding more than barotrauma, which, according to its etymology, refers to high transpulmonary pressure.

Pulmonary thromboembolism in hospitalised COVID-19 patients at moderate to high risk by Wells score: a report from Lombardy, Italy.

OBJECTIVES: To present a single-centre experience on CT pulmonary angiography (CTPA) for the assessment of hospitalised COVID-19 patients with moderate-to-high risk of pulmonary thromboembolism (PTE). METHODS: We analysed consecutive COVID-19 patients (RT-PCR confirmed) undergoing CTPA in March 2020 for PTE clinical suspicion. Clinical data were retrieved. Two experienced radiologists reviewed CTPAs to assess pulmonary parenchyma and vascular findings. RESULTS: Among 34 patients who underwent CTPA, 26 had PTE (76%, 20 males, median age 61 years, interquartile range 54-70), 20/26 (77%) with comorbidities (mainly hypertension, 44%), and 8 (31%) subsequently dying. Eight PTE patients were under thromboprophylaxis with low-molecular-weight heparin, four PTE patients had lower-limbs deep vein thrombosis at ultrasound examination (performed in 33/34 patients). Bilateral PTE characterised 19/26 cases, with main branches involved in 10/26 cases. Twelve patients had a parenchymal involvement >75%, the predominant pneumonia pattern being consolidation in 10/26 patients, ground glass opacities in 9/26, crazy paving in 5/26, and both ground glass opacities and consolidation in 2/26. CONCLUSION: COVID-19 patients are prone to PTE. ADVANCES IN KNOWLEDGE: PTE, potentially attributable to an underlying thrombophilic status, may be more frequent than expected in COVID-19 patients. Extension of prophylaxis and adaptation of diagnostic criteria should be considered.

CT-derived pulmonary vascular metrics and clinical outcome in COVID-19 patients.

To assess pulmonary vascular metrics on chest CT of COVID-19 patients, and their correlation with pneumonia extent (PnE) and outcome, we analyzed COVID-19 patients with an available previous chest CT, excluding those performed for cardiovascular disease. From February 21 to March 21, 2020, of 672 suspected COVID-19 patients from two centers who underwent CT, 45 RT-PCR-positives (28 males, median age 75, IQR 66-81 years) with previous CTs performed a median 36 months before (IQR 12-72 months) were included. We assessed PnE, pulmonary artery (PA) diameter, ascending aorta (Ao) diameter, and PA/Ao ratio. Most common presentations were fever and dyspnea (15/45) and fever alone (13/45). Outcome was available for 41/45 patients, 15/41 dead and 26/41 discharged. Ground-glass opacities (GGOs) alone were found in 29/45 patients, GGOs with consolidations in 15/45, consolidations alone in 1/45. All but one patient had bilateral pneumonia, 9/45 minimal, 22/45 mild, 9/45 moderate, and 5/45 severe PnE. PA diameter (median 31 mm, IQR 28-33 mm) was larger than before (26 mm, IQR 25-29 mm) (P<0.001), PA/Ao ratio (median 0.83, IQR 0.76-0.92) was higher than before (0.76, IQR 0.72-0.82) (P<0.001). Patients with adverse outcome (death) had higher PA diameter (P=0.001), compared to discharged ones. Only weak correlations were found between ΔPA or ΔPA/Ao and PnE (ρ≤0.453, P≤0.032), with 4/45 cases with moderate-severe PnE and minimal increase in PA metrics. In conclusion, enlarged PA diameter was associated to death in COVID-19 patients, a finding deserving further investigation as a potential driver of therapy decision-making.