Time-series analysis of multidimensional clinical-laboratory data by dynamic Bayesian networks reveals trajectories of COVID-19 outcomes.

BACKGROUND AND OBJECTIVE: COVID-19 severity spans an entire clinical spectrum from asymptomatic to fatal. Most patients who require in-hospital care are admitted to non-intensive wards, but their clinical conditions can deteriorate suddenly and some eventually die. Clinical data from patients' case series have identified pre-hospital and in-hospital risk factors for adverse COVID-19 outcomes. However, most prior studies used static variables or dynamic changes of a few selected variables of interest. In this study, we aimed at integrating the analysis of time-varying multidimensional clinical-laboratory data to describe the pathways leading to COVID-19 outcomes among patients initially hospitalised in a non-intensive care setting. METHODS: We collected the longitudinal retrospective data of 394 patients admitted to non-intensive care units at the University Hospital of Padova (Padova, Italy) due to COVID-19. We trained a dynamic Bayesian network (DBN) to encode the conditional probability relationships over time between death and all available demographics, pre-existing conditions, and clinical laboratory variables. We applied resampling, dynamic time warping, and prototyping to describe the typical trajectories of patients who died vs. those who survived. RESULTS: The DBN revealed that the trajectory linking demographics and pre-existing clinical conditions to death passed directly through kidney dysfunction or, more indirectly, through cardiac damage. As expected, admittance to the intensive care unit was linked to markers of respiratory function. Notably, death was linked to elevation in procalcitonin and D-dimer levels. Death was associated with persistently high levels of procalcitonin from admission and throughout the hospital stay, likely reflecting bacterial superinfection. A sudden raise in D-dimer levels 3-6 days after admission was also associated with subsequent death, possibly reflecting a worsening thrombotic microangiopathy. CONCLUSIONS: This innovative application of DBNs and prototyping to integrated data analysis enables visualising the patient's trajectories to COVID-19 outcomes and may instruct timely and appropriate clinical decisions.

A Circadian Hygiene Education Initiative Covering the Pre-pandemic and Pandemic Period Resulted in Earlier Get-Up Times in Italian University Students: An Ecological Study.

The aims of the present study were to obtain sleep quality and sleep timing information in a group of university students and to evaluate the effects of a circadian hygiene education initiative. All students of the University of Padova (approximately 64,000) were contacted by e-mail (major campaigns in October 2019 and October 2020) and directed to an ad hoc website for collection of demographics and sleep quality/timing information. Participants (n = 5,740) received one of two sets of circadian hygiene advice ("A regular life" or "Bright days and dark nights"). Every month, they were then asked how easy it had been to comply and provided with the advice again. At any even month from joining, they completed the sleep quality/timing questionnaires again. Information on academic performance was obtained post hoc, together with representative samples of lecture (n = 5,972) and examination (n = 1,800) timings, plus lecture attendances (n = 25,302). Fifty-two percent of students had poor sleep quality, and 82% showed signs of social jetlag. Those who joined in October 2020, after several months of lockdown and distance learning, had better sleep quality, less social jetlag, and later sleep habits. Over approximately a year, the "Bright days and dark nights" advice resulted in significantly earlier get-up times compared with the "A regular life" advice. Similarly, it also resulted in a trend toward earlier midsleep (i.e., the midpoint, expressed as clock time, between sleep onset and sleep offset) and toward a decrease in the latency between wake-up and get-up time, with no impact on sleep duration. Significant changes in most sleep quality and sleep timing variables (i.e., fewer night awakenings, less social jetlag, and delayed sleep timing during lock-down) were observed in both advice groups over approximately a year, mostly in association with pandemic-related events characterizing 2020. Early chronotype students had better academic performances compared with their later chronotype counterparts. In a multivariate model, sleep quality, chronotype and study subject (science and technology, health and medical, or social and humanities) were independent predictors of academic performance. Taken together, these results underlie the importance of designing circadian-friendly university timetables.

More severe hypercoagulable state in acute COVID-19 pneumonia as compared to other pneumonia.

OBJECTIVE: To conduct a comprehensive evaluation of coagulation profiles - via traditional and whole blood thromboelastometry tests - in COVID-19 positive vs. COVID-19 negative patients admitted to medical wards for acute pneumonia. PATIENTS AND METHODS: We enrolled all consecutive patients admitted to Internal Medicine wards of Padova University Hospital between 7 March and 30 April 2020 for COVID-19-related pneumonia (cases) vs. non-COVID-19 pneumonia (controls). A group of healthy subjects acted as baseline for thromboelastometry parameters. RESULTS: Fifty-six cases (mean age 64±15 yrs, M/F 37/19) and 56 controls (mean age 76±11 yrs, M/F 35/21) were enrolled. Cases and controls showed markedly hypercoagulable thromboelastometry profiles vs. healthy subjects, mainly characterized by a significantly shorter propagation phase of coagulation (Clot Formation Time, CFT) and significantly increased maximum clot firmness (MCF) (p <0.001 in all comparisons). COVID-19 patients with pneumonia had significantly shorter CFT and higher MCF (p <0.01 and <0.05, respectively in all comparisons) vs. controls. CONCLUSION: Patients admitted to internal medicine wards for COVID-19 pneumonia presented a markedly prothrombotic state, which seems peculiar to COVID-19 rather than pneumonia itself.

Chest X-ray Does Not Predict the Risk of Endotracheal Intubation and Escalation of Treatment in COVID-19 Patients Requiring Noninvasive Respiratory Support.

Forms of noninvasive respiratory support (NIRS) have been widely used to avoid endotracheal intubation in patients with coronavirus disease-19 (COVID-19). However, inappropriate prolongation of NIRS may delay endotracheal intubation and worsen patient outcomes. The aim of this retrospective study was to assess whether the CARE score, a chest X-ray score previously validated in COVID-19 patients, may predict the need for endotracheal intubation and escalation of respiratory support in COVID-19 patients requiring NIRS. From December 2020 to May 2021, we included 142 patients receiving NIRS who had a first chest X-ray available at NIRS initiation and a second one after 48-72 h. In 94 (66%) patients, the level of respiratory support was increased, while endotracheal intubation was required in 83 (58%) patients. The CARE score at NIRS initiation was not predictive of the need for endotracheal intubation (odds ratio (OR) 1.01, 95% confidence interval (CI) 0.96-1.06) or escalation of treatment (OR 1.01, 95% CI 0.96-1.07). In conclusion, chest X-ray severity, as assessed by the CARE score, did not allow predicting endotracheal intubation or escalation of respiratory support in COVID-19 patients undergoing NIRS.

In hospital risk factors for acute kidney injury and its burden in patients with Sars-Cov-2 infection: a longitudinal multinational study.

Acute kidney injury (AKI) is associated with increased mortality in most critical settings. However, it is unclear whether its mild form (i.e. AKI stage 1) is associated with increased mortality also in non-critical settings. Here we conducted an international study in patients hospitalized with SARS-CoV-2 infection aiming 1. to estimate the incidence of AKI at each stage and its impact on mortality 2. to identify AKI risk factors at admission (susceptibility) and during hospitalization (exposures) and factors contributing to AKI-associated mortality. We included 939 patients from medical departments in Moscow (Russia) and Padua (Italy). In-hospital AKI onset was identified in 140 (14.9%) patients, mainly with stage 1 (65%). Mortality was remarkably higher in patients with AKI compared to those without AKI (55 [39.3%] vs. 34 [4.3%], respectively). Such association remained significant after adjustment for other clinical conditions at admission (relative risk [RR] 5.6; CI 3.5- 8.8) or restricting to AKI stage 1 (RR 3.2; CI 1.8-5.5) or to subjects with AKI onset preceding deterioration of clinical conditions. After hospital admission, worsening of hypoxic damage, inflammation, hyperglycemia, and coagulopathy were identified as hospital-acquired risk factors predicting AKI onset. Following AKI onset, the AKI-associated worsening of respiratory function was identified as the main contributor to AKI-induced increase in mortality risk. In conclusion, AKI is a common complication of Sars-CoV2 infection in non-intensive care settings where it markedly increases mortality risk also at stage 1. The identification of hospital-acquired risk factors and exposures might help prevention of AKI onset and of its complications.

Performance of non-invasive respiratory function indices in predicting clinical outcomes in patients hospitalized for COVID-19 pneumonia in medical and sub-intensive wards: a retrospective cohort study.

Coronavirus disease 2019 (COVID-19) is a newly recognized infectious disease which can lead to acute respiratory distress syndrome requiring ventilatory support and intensive care unit admission. The aim of our study is to evaluate the performance of two non-invasive respiratory function indices (the ROX index and the SatO2/FiO2 ratio), as compared to the traditional PaO2/FiO2 ratio, in predicting a clinically relevant composite outcome (death or intubation) in hospitalized patients for COVID-19 pneumonia. Four hospital centers in Northern Italy conducted an observational retrospective cohort study during the first wave of COVID-19 pandemic. Four hundred and fifty-six patients with COVID-19 pneumonia admitted to medical or sub-intensive wards were enrolled. Clinical, laboratory, and respiratory parameters, for the calculation of different indices, were measured at hospital admission. In medical wards (Verona and Padua) the PaO2/FiO2 ratio, ROX index and SatO2/FiO2 ratio were able to predict intubation or death with good accuracy (AUROC for the PaO2/FiO2 ratio, ROX index and SatO2/FiO2 ratio of 75%, 75% and 74%, respectively). Regarding sub-intensive wards (Milan and Mantua), none of the three respiratory function indices was significantly associated with the composite outcome. In patients admitted to medical wards for COVID-19 pneumonia, the ROX index and the SatO2/FiO2 ratio demonstrated not only good performance in predicting intubation or death, but their accuracy was comparable to that of the PaO2/FiO2 ratio. In this setting, where repeated arterial blood gas tests are not always feasible, they could be considered a reliable alternative to the invasive PaO2/FiO2 ratio.

Cardiac injury and COVID-19 associated coagulopathy in patients with acute SARS-CoV-2 pneumonia: A rotational thromboelastometry study.

PURPOSE: Coronavirus disease 2019 (COVID-19) is a systemic inflammatory condition associated with coagulopathy which may result in severe thromboembolic complications. Cardiac injury is not uncommon in hospitalized COVID-19 patients and therefore we aimed to investigate whether it stems from an abnormal coagulative state. MATERIALS AND METHODS: We conducted a retrospective cross-sectional study on consecutive patients hospitalized due to COVID-19. Traditional coagulation and whole blood rotational thromboelastometry tests were compared between patients with and without cardiac injury. Cardiac injury was defined by increased levels of high-sensitivity cardiac troponin I (hs-cTnI). RESULTS: The study population consisted of 104 patients (67% males, median age 65 years), of whom 40 (38%) developed cardiac injury. No clinical differences in the traditional coagulation parameters were observed between patients with and without cardiac injury. Thromboelastometry analysis revealed abnormal maximum clot firmness (MCF) levels in FIBTEM assay in 80 (77%) patients. No significant differences in MCF values (p â€‹= â€‹0.450) and percentage of abnormal MCF (p â€‹= â€‹0.290) were detected between patients with and without cardiac injury. Cardiac injury - not hypercoagulability - was associated with mortality (p â€‹= â€‹0.016). CONCLUSIONS: No differences in traditional coagulation and rotational thromboelastometry parameters were found among hospitalized COVID-19 patients with and without cardiac injury. Other mechanisms besides hypercoagulability may be a main culprit for cardiac injury in COVID-19 patients.

Haemophilus parainfluenzae endocarditis in a low-risk woman: a case report.

Haemophilus parainfluenzae endocarditis is a rare but dangerous disease. With this work, we intend to show the importance of early diagnosis and appropriate treatment in order to avoid complications. We also highlight the importance of local epidemiology to choose antibiotic prophylaxis for high-risk procedures in selected predisposed patients.

Higher Levels of C-Reactive Protein and Ferritin in Patients with Overweight and Obesity and SARS-CoV-2-Related Pneumonia.

INTRODUCTION: Overweight and obesity are associated with a more severe COronaVirus Disease 19 (COVID-19). Adipose tissue-related chronic inflammation could be a promoter for the occurrence of the cytokine storm that predicts aggravation of COVID-19. The primary aim was to investigate if this increased risk for more severe COVID-19 was associated with a higher inflammatory response. METHODS: We enrolled patients <75 years old hospitalized in a medical COVID-19 ward with SARS-CoV-2-related pneumonia. Patients were classified according to BMI as normal weight, overweight, and obesity. Laboratory parameters were measured at admission and every second day during the hospital stay. RESULTS: Ninety patients (64.4% males; median age 61 years) were enrolled. Invasive mechanical ventilation (IMV) was needed in 9% of the patients with normal weight, in 32.4% of the patients with overweight, and in 12.9% of the patients with obesity (p = 0.045). Maximal C-reactive protein (CRP) level during hospital stay was 92 (48-122) mg/L in patients with normal weight, 140 (82-265) mg/L in patients with overweight, and 117 (67-160) mg/L in patients with obesity (p = 0.037). Maximal ferritin values were 564 (403-1,379) µg/L in patients with a normal weight, 1,253 (754-2,532) µg/L in patients with overweight, and 828 (279-1,582) µg/L in patients with obesity (p = 0.015). CONCLUSION: Patients with overweight and obesity required more IMV and had higher peaks of CRP and ferritin than patients with normal weight during COVID-19.

Lower Gene Expression of Angiotensin Converting Enzyme 2 Receptor in Lung Tissues of Smokers with COVID-19 Pneumonia.

Angiotensin-converting enzyme 2 (ACE-2) is the main cell entry receptor for severe acute respiratory syndrome-Coronavirus-2 (SARS-CoV-2), thus playing a critical role in causing Coronavirus disease 2019 (COVID-19). The role of smoking habit in the susceptibility to infection is still controversial. In this study we correlated lung ACE-2 gene expression with several clinical/pathological data to explore susceptibility to infection. This is a retrospective observational study on 29 consecutive COVID-19 autopsies. SARS-CoV-2 genome and ACE-2 mRNA expression were evaluated by real-time polymerase chain reaction in lung tissue samples and correlated with several data with focus on smoking habit. Smoking was less frequent in high than low ACE-2 expressors (p = 0.014). A Bayesian regression also including age, gender, hypertension, and virus quantity confirmed that smoking was the most probable risk factor associated with low ACE-2 expression in the model. A direct relation was found between viral quantity and ACE-2 expression (p = 0.028). Finally, high ACE-2 expressors more frequently showed a prevalent pattern of vascular injury than low expressors (p = 0.049). In conclusion, ACE-2 levels were decreased in the lung tissue of smokers with severe COVID-19 pneumonia. These results point out complex biological interactions between SARS-CoV-2 and ACE-2 particularly concerning the aspect of smoking habit and need larger prospective case series and translational studies.

Proven COVID-19-associated pulmonary aspergillosis in patients with severe respiratory failure.

BACKGROUND: An increasing number of reports have described the COVID-19-associated pulmonary aspergillosis (CAPA) as being a further contributing factor to mortality. Based on a recent consensus statement supported by international medical mycology societies, it has been proposed to define CAPA as possible, probable, or proven on the basis of sample validity and thus diagnostic certainty. Considering current challenges associated with proven diagnoses, there is pressing need to study the epidemiology of proven CAPA. METHODS: We report the incidence of histologically diagnosed CAPA in a series of 45 consecutive COVID-19 laboratory-confirmed autopsies, performed at Padova University Hospital during the first and second wave of the pandemic. Clinical data, laboratory data and radiological features were also collected for each case. RESULTS: Proven CAPA was detected in 9 (20%) cases, mainly in the second wave of the pandemic (7/17 vs. 2/28 of the first wave). The population of CAPA patients consisted of seven males and two females, with a median age of 74 years. Seven patients were admitted to the intensive care unit. All patients had at least two comorbidities, and concomitant lung diseases were detected in three cases. CONCLUSION: We found a high frequency of proven CAPA among patients with severe COVID-19 thus confirming at least in part the alarming epidemiological data of this important complication recently reported as probable CAPA.

Reduced muscle mass as predictor of intensive care unit hospitalization in COVID-19 patients.

PURPOSE: To evaluate if reduced muscle mass, assessed with Computed Tomography (CT), is a predictor of intensive care unit (ICU) hospitalization in COVID-19 patients. METHODS: In this Institution Review Board approved study, we retrospectively evaluated COVID-19 patients treated in our tertiary center from March to November 2020 who underwent an unenhanced chest CT scan within three weeks from hospitalization.We recorded the mean Hounsfield Unit (Hu) value of the right paravertebral muscle at the level of the 12th thoracic vertebra, the hospitalization unit (ICU and COVID-19 wards), clinical symptoms, Barthel Index, and laboratory findings.Logistic regression analysis was applied to assess if muscle loss (Hu<30) is a predictor of ICU admission and outcome.Fisher's exact and Student's tests were applied to evaluate if differences between patients with and without muscle loss occurred (p<0.05). RESULTS: One-hundred-fifty patients matched the inclusion criteria (46 females; mean age±SD 61.3±15 years-old), 36 treated in ICU. Patients in ICU showed significantly lower Hu values (29±24 vs 39.4±12, p = 0.001). Muscle loss was a predictor of ICU admission (p = 0.004).Patients with muscle loss were significantly older (73.4±10 vs 56.4±14 years), had lower Barthel Index scores (54.4±33 vs 85.1±26), red blood-cell count (3.9±1 vs 4.6±1×1012L-1), and Hb levels (11.5±2 vs 13.2±2g/l) as well as higher white blood-cell count (9.4±7 vs 7.2±4×109L-1), C-reactive protein (71.5±71 vs 44±48U/L), and lactate dehydrogenase levels (335±163 vs 265.8±116U/L) (p<0.05, each). CONCLUSIONS: Muscle loss seems to be a predictor of ICU hospitalization in COVID-19 patients and radiologists reporting chest CT at admission should note this finding in their reports.

Liver histopathology in COVID-19 patients: A mono-Institutional series of liver biopsies and autopsy specimens.

Few studies have focused on COVID-19 patients' hepatic histopathological features. Many of the described morphological landscapes are non-specific and possibly due to other comorbidities or to Sars-CoV-2-related therapies. We describe the hepatic histopathological findings of 3 liver biopsies obtained from living COVID-19 patients in which active SARS-CoV-2 infection was molecularly confirmed and biopsied because of significant alterations of liver function tests and 25 livers analyzed during COVID-19-related autopsies. Main histopathological findings were (i) the absence of significant biliary tree or vascular damages, (ii) mild/absent lymphocytic hepatitis; (iii) activation of (pigmented) Kupffer cells, (iv) hepatocellular regenerative changes, (v) the presence of steatosis, (vi) sinusoidal ectasia, micro-thrombosis and acinar atrophy in autopsy specimens No viral particle actively infecting the hepatic or endothelial cells was detected at in situ hybridization. The morphological features observed within the hepatic parenchyma are not specific and should be considered as the result of an indirect insult resulting from the viral infection or the adopted therapeutic protocols.

Clinical factors associated with death in 3044 COVID-19 patients managed in internal medicine wards in Italy: results from the SIMI-COVID-19 study of the Italian Society of Internal Medicine (SIMI).

During the COVID-19 2020 outbreak, a large body of data has been provided on general management and outcomes of hospitalized COVID-19 patients. Yet, relatively little is known on characteristics and outcome of patients managed in Internal Medicine Units (IMU). To address this gap, the Italian Society of Internal Medicine has conducted a nationwide cohort multicentre study on death outcome in adult COVID-19 patients admitted and managed in IMU. This study assessed 3044 COVID-19 patients at 41 referral hospitals across Italy from February 3rd to May 8th 2020. Demographics, comorbidities, organ dysfunction, treatment, and outcomes including death were assessed. During the study period, 697 patients (22.9%) were transferred to intensive care units, and 351 died in IMU (death rate 14.9%). At admission, factors independently associated with in-hospital mortality were age (OR 2.46, p = 0.000), productive cough (OR 2.04, p = 0.000), pre-existing chronic heart failure (OR 1.58, p = 0.017) and chronic obstructive pulmonary disease (OR 1.17, p = 0.048), the number of comorbidities (OR 1.34, p = 0.000) and polypharmacy (OR 1.20, p = 0.000). Of note, up to 40% of elderly patients did not report fever at admission. Decreasing PaO2/FiO2 ratio at admission was strongly inversely associated with survival. The use of conventional oxygen supplementation increased with the number of pre-existing comorbidities, but it did not associate with better survival in patients with PaO2/FiO2 ratio < 100. The latter, significantly benefited by the early use of non-invasive mechanical ventilation. Our study identified PaO2/FiO2 ratio at admission and comorbidity as the main alert signs to inform clinical decisions and resource allocation in non-critically ill COVID-19 patients admitted to IMU.

Use of low-molecular weight heparin, transfusion and mortality in COVID-19 patients not requiring ventilation.

It is still debated whether prophylactic doses of low-molecular- weight heparin (LMWH) are always effective in preventing Venous Thromboembolism (VTE) and mortality in COVID-19. Furthermore, there is paucity of data for those patients not requiring ventilation. We explored mortality and the safety/efficacy profile of LMWH in a cohort of Italian patients with COVID-19 who did not undergo ventilation. From the initial cohort of 422 patients, 264 were enrolled. Most (n = 156, 87.7%) received standard LMWH prophylaxis during hospitalization, with no significant difference between medical wards and Intensive Care Unit (ICU). Major or not major but clinically relevant hemorrhages were recorded in 13 (4.9%) patients: twelve in those taking prophylactic LMWH and one in a patient taking oral anticoagulants (p: n.s.). Thirty-nine patients (14.8%) with median age 75 years. were transfused. Hemoglobin (Hb) at admission was significantly lower in transfused patients and Hb at admission inversely correlated with the number of red blood cells units transfused (p < 0.001). In-hospital mortality occurred in 76 (28.8%) patients, 46 (24.3%) of whom admitted to medical wards. Furthermore, Hb levels at admittance were significantly lower in fatalities (g/dl 12.3; IQR 2.4 vs. 13.3; IQR 2.8; Mann-Whitney U-test; p = 0.001). After the exclusion of patients treated by LMWH intermediate or therapeutic doses (n = 32), the logistic regression showed that prophylaxis significantly and independently reduced mortality (OR 0.31, 95% CI 0.13-0.85). Present data show that COVID-19 patients who do not require ventilation benefit from prophylactic doses of LMWH.

Lung Ultrasound Patterns and Clinical-Laboratory Correlates during COVID-19 Pneumonia: A Retrospective Study from North East Italy.

BACKGROUND AND AIM: Lung ultrasound (LUS) is a convenient imaging modality in the setting of coronavirus disease-19 (COVID-19) because it is easily available, can be performed bedside and repeated over time. We herein examined LUS patterns in relation to disease severity and disease stage among patients with COVID-19 pneumonia. METHODS: We performed a retrospective case series analysis of patients with confirmed SARS-CoV-2 infection who were admitted to the hospital because of pneumonia. We recorded history, clinical parameters and medications. LUS was performed and scored in a standardized fashion by experienced operators, with evaluation of up to 12 lung fields, reporting especially on B-lines and consolidations. RESULTS: We included 96 patients, 58.3% men, with a mean age of 65.9 years. Patients with a high-risk quick COVID-19 severity index (qCSI) were older and had worse outcomes, especially for the need for high-flow oxygen. B-lines and consolidations were located mainly in the lower posterior lung fields. LUS patterns for B-lines and consolidations were significantly worse in all lung fields among patients with high versus low qCSI. B-lines and consolidations were worse in the intermediate disease stage, from day 7 to 13 after onset of symptoms. While consolidations correlated more with inflammatory biomarkers, B-lines correlated more with end-organ damage, including extrapulmonary involvement. CONCLUSIONS: LUS patterns provide a comprehensive evaluation of patients with COVID-19 pneumonia that correlated with severity and dynamically reflect disease stage. LUS patterns may reflect different pathophysiological processes related to inflammation or tissue damage; consolidations may represent a more specific sign of localized disease, whereas B-lines seem to be also dependent upon generalized illness due to SARS-CoV-2 infection.

Machine learning-based analysis of alveolar and vascular injury in SARS-CoV-2 acute respiratory failure.

Severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) pneumopathy is characterized by a complex clinical picture and heterogeneous pathological lesions, both involving alveolar and vascular components. The severity and distribution of morphological lesions associated with SARS-CoV-2 and how they relate to clinical, laboratory, and radiological data have not yet been studied systematically. The main goals of the present study were to objectively identify pathological phenotypes and factors that, in addition to SARS-CoV-2, may influence their occurrence. Lungs from 26 patients who died from SARS-CoV-2 acute respiratory failure were comprehensively analysed. Robust machine learning techniques were implemented to obtain a global pathological score to distinguish phenotypes with prevalent vascular or alveolar injury. The score was then analysed to assess its possible correlation with clinical, laboratory, radiological, and tissue viral data. Furthermore, an exploratory random forest algorithm was developed to identify the most discriminative clinical characteristics at hospital admission that might predict pathological phenotypes of SARS-CoV-2. Vascular injury phenotype was observed in most cases being consistently present as pure form or in combination with alveolar injury. Phenotypes with more severe alveolar injury showed significantly more frequent tracheal intubation; longer invasive mechanical ventilation, illness duration, intensive care unit or hospital ward stay; and lower tissue viral quantity (p < 0.001). Furthermore, in this phenotype, superimposed infections, tumours, and aspiration pneumonia were also more frequent (p < 0.001). Random forest algorithm identified some clinical features at admission (body mass index, white blood cells, D-dimer, lymphocyte and platelet counts, fever, respiratory rate, and PaCO2 ) to stratify patients into different clinical clusters and potential pathological phenotypes (a web-app for score assessment has also been developed; https://r-ubesp.dctv.unipd.it/shiny/AVI-Score/). In SARS-CoV-2 positive patients, alveolar injury is often associated with other factors in addition to viral infection. Identifying phenotypical patterns at admission may enable a better stratification of patients, ultimately favouring the most appropriate management. © 2021 The Pathological Society of Great Britain and Ireland. Published by John Wiley & Sons, Ltd.