Machine learning for prediction of in-hospital mortality in coronavirus disease 2019 patients: results from an Italian multicenter study.

BACKGROUND: Several risk factors have been identified to predict worse outcomes in patients affected by SARS-CoV-2 infection. Machine learning algorithms represent a novel approach to identifying a prediction model with a good discriminatory capacity to be easily used in clinical practice. The aim of this study was to obtain a risk score for in-hospital mortality in patients with coronavirus disease infection (COVID-19) based on a limited number of features collected at hospital admission. METHODS AND RESULTS: We studied an Italian cohort of consecutive adult Caucasian patients with laboratory-confirmed COVID-19 who were hospitalized in 13 cardiology units during Spring 2020. The Lasso procedure was used to select the most relevant covariates. The dataset was randomly divided into a training set containing 80% of the data, used for estimating the model, and a test set with the remaining 20%. A Random Forest modeled in-hospital mortality with the selected set of covariates: its accuracy was measured by means of the ROC curve, obtaining AUC, sensitivity, specificity and related 95% confidence interval (CI). This model was then compared with the one obtained by the Gradient Boosting Machine (GBM) and with logistic regression. Finally, to understand if each model has the same performance in the training and test set, the two AUCs were compared using the DeLong's test. Among 701 patients enrolled (mean age 67.2 ±â€Š13.2 years, 69.5% male individuals), 165 (23.5%) died during a median hospitalization of 15 (IQR, 9-24) days. Variables selected by the Lasso procedure were: age, oxygen saturation, PaO2/FiO2, creatinine clearance and elevated troponin. Compared with those who survived, deceased patients were older, had a lower blood oxygenation, lower creatinine clearance levels and higher prevalence of elevated troponin (all P < 0.001). The best performance out of the samples was provided by Random Forest with an AUC of 0.78 (95% CI: 0.68-0.88) and a sensitivity of 0.88 (95% CI: 0.58-1.00). Moreover, Random Forest was the unique model that provided similar performance in sample and out of sample (DeLong test P = 0.78). CONCLUSION: In a large COVID-19 population, we showed that a customizable machine learning-based score derived from clinical variables is feasible and effective for the prediction of in-hospital mortality.

Prevalence of Psychopathological Symptoms and Their Determinants in Four Healthcare Workers' Categories during the Second Year of COVID-19 Pandemic.

Highly stressful situations, such as the current COVID-19 pandemic, induce constant changes in the mental state of people who experience them. In the present study, we analyzed the prevalence of some psychological symptoms and their determinants in four different categories of healthcare workers during the second year of the pandemic. A total of 265 physicians, 176 nurses, 184 other healthcare professionals, and 48 administrative employees, working in different Italian healthcare contexts, answered a questionnaire including variables about their mental status and experience with the pandemic. The mean scores for anxiety and depressive symptoms measured more than one year after the onset of the pandemic did not reach the pathological threshold. In contrast, post-traumatic and burnout symptoms tended toward the critical threshold, especially in physicians. The main determinant of psychological distress was perceived stress, followed by job satisfaction, the impact of COVID-19 on daily work, and a lack of recreational activities. These results increase the knowledge of which determinants of mental distress would be important to act on when particularly stressful conditions exist in the workplace that persist over time. If well-implemented, specific interventions focused on these determinants could lead to an improvement in employee well-being and in the quality of care provided.

When Outcomes Diverge: Age and Cardiovascular Risk as Determinants of Mortality and ICU Admission in COVID-19.

BACKGROUND: Hospital mortality and admission to the Intensive Care Unit (ICU) are markers of disease severity in COVID-19 patients. Cardiovascular co-morbidities are one of the main determinants of negative outcomes. In this study we investigated the impact of cardiovascular co-morbidities on mortality and admission to the ICU in first-wave COVID-19 patients. METHODS: A multicenter, retrospective, cohort study. A total of 1077 patients were analyzed for mortality and ICU admission. Cardiovascular risk factors were explored as determinants of the outcomes after correction for other confounders. RESULTS: In the multivariable model, after correction for age, only a history of heart failure remained independently associated (p = 0.0013) with mortality (hazard ratio 2.22, 95% confidence interval 1.37 to 3.62). Age showed a mortality risk increase of 8% per year (hazard ratio 1.08, 95% confidence interval 1.05 to 1.10, p = 0.001). The transition from ward to the ICU had, as a single determinant, the age, but in a reversed fashion (hazard ratio 0.96, 95% confidence interval 0.94 to 0.98, p = 0.0002). CONCLUSIONS: Once adjusted for the main determinant of mortality (age) heart failure only remained independently associated with mortality. Admission to the ICU was less likely for elderly patients. This may reflect the catastrophic impact of the first wave of COVID-19 pandemic in terms of ICU bed availability in Lombardy, leading to a selection process for ICU admission.

Renin Angiotensin System Blockers and Risk of Mortality in Hypertensive Patients Hospitalized for COVID-19: An Italian Registry.

BACKGROUND: It is uncertain whether exposure to renin-angiotensin system (RAS) modifiers affects the severity of the new coronavirus disease 2019 (COVID-19) because most of the available studies are retrospective. METHODS: We tested the prognostic value of exposure to RAS modifiers (either angiotensin-converting enzyme inhibitors [ACE-Is] or angiotensin receptor blockers [ARBs]) in a prospective study of hypertensive patients with COVID-19. We analyzed data from 566 patients (mean age 75 years, 54% males, 162 ACE-Is users, and 147 ARBs users) hospitalized in five Italian hospitals. The study used systematic prospective data collection according to a pre-specified protocol. All-cause mortality during hospitalization was the primary outcome. RESULTS: Sixty-six patients died during hospitalization. Exposure to RAS modifiers was associated with a significant reduction in the risk of in-hospital mortality when compared to other BP-lowering strategies (odds ratio [OR]: 0.54, 95% confidence interval [CI]: 0.32 to 0.90, p = 0.019). Exposure to ACE-Is was not significantly associated with a reduced risk of in-hospital mortality when compared with patients not treated with RAS modifiers (OR: 0.66, 95% CI: 0.36 to 1.20, p = 0.172). Conversely, ARBs users showed a 59% lower risk of death (OR: 0.41, 95% CI: 0.20 to 0.84, p = 0.016) even after allowance for several prognostic markers, including age, oxygen saturation, occurrence of severe hypotension during hospitalization, and lymphocyte count (adjusted OR: 0.37, 95% CI: 0.17 to 0.80, p = 0.012). The discontinuation of RAS modifiers during hospitalization did not exert a significant effect (p = 0.515). CONCLUSIONS: This prospective study indicates that exposure to ARBs reduces mortality in hospitalized patients with COVID-19.

Determinants of the protective effect of glucocorticoids on mortality in hospitalized patients with COVID-19: Insights from the Cardio-COVID-Italy multicenter study.

BACKGROUND: Glucocorticoid therapy has emerged as an effective therapeutic option in hospitalized patients with coronavirus disease 2019 (COVID-19). This study aimed to focus on the impact of relevant clinical and laboratory factors on the protective effect of glucocorticoids on mortality. METHODS: A sub-analysis was performed of the multicenter Cardio-COVID-Italy registry, enrolling consecutive patients with COVID-19 admitted to 13 Italian cardiology units between 01 March 2020 and 09 April 2020. The primary endpoint was in-hospital mortality. RESULTS: A total of 706 COVID-19 patients were included (349 treated with glucocorticoids, 357 not treated with glucocorticoids). After adjustment for relevant covariates, use of glucocorticoids was associated with a lower risk of in-hospital mortality (adjusted HR 0.44; 95% CI 0.26-0.72; p = 0.001). A significant interaction was observed between the protective effect of glucocorticoids on mortality and PaO2/FiO2 ratio on admission (p = 0.042), oxygen saturation on admission (p = 0.017), and peak CRP (0.023). Such protective effects of glucocorticoids were mainly observed in patients with lower PaO2/FiO2 ratio (<300), lower oxygen saturation (<90%), and higher CRP (>100 mg/L). CONCLUSIONS: The protective effects of glucocorticoids on mortality in COVID-19 were more evident among patients with worse respiratory parameters and higher systemic inflammation.

Psychological and work-related factors associated with emotional exhaustion among healthcare professionals during the COVID-19 outbreak in Italian hospitals.

The coronavirus disease 2019 (COVID-19) pandemic has induced considerable psychological distress in healthcare workers, increasing the risk of burnout. This research aimed to investigate sociodemographic, work-related, COVID-19-related, and psychological factors associated with emotional exhaustion (the core component of burnout) among healthcare professionals during the first wave of the COVID-19 pandemic in Italy. A cross-sectional study was conducted to assess risk (e.g. perceived risk and fear of contagion, stress) and protective factors (e.g. job satisfaction, resilience) for emotional exhaustion among 616 hospital staff. Women, nurses, shift workers, those with a permanent contract, and frontline workers reported significantly higher levels of emotional exhaustion compared to others. Significant risk factors predicting emotional exhaustion were prolonged use of personal protective equipment, increased work pressure, lack of support, and prolonged working hours; psychologically protective factors were resilience and job satisfaction, while perceived stress was found to be a significant psychological risk factor. Organizational interventions should focus on these factors to prevent the onset of burnout.

Implications of atrial fibrillation on the clinical course and outcomes of hospitalized COVID-19 patients: results of the Cardio-COVID-Italy multicentre study.

AIMS: To assess the clinical relevance of a history of atrial fibrillation (AF) in hospitalized patients with coronavirus disease 2019 (COVID-19). METHODS AND RESULTS: We enrolled 696 consecutive patients (mean age 67.4 ± 13.2 years, 69.7% males) admitted for COVID-19 in 13 Italian cardiology centres between 1 March and 9 April 2020. One hundred and six patients (15%) had a history of AF and the median hospitalization length was 14 days (interquartile range 9-24). Patients with a history of AF were older and with a higher burden of cardiovascular risk factors. Compared to patients without AF, they showed a higher rate of in-hospital death (38.7% vs. 20.8%; P < 0.001). History of AF was associated with an increased risk of death after adjustment for clinical confounders related to COVID-19 severity and cardiovascular comorbidities, including history of heart failure (HF) and increased plasma troponin [adjusted hazard ratio (HR): 1.73; 95% confidence interval (CI) 1.06-2.84; P = 0.029]. Patients with a history of AF also had more in-hospital clinical events including new-onset AF (36.8% vs. 7.9%; P < 0.001), acute HF (25.3% vs. 6.3%; P < 0.001), and multiorgan failure (13.9% vs. 5.8%; P = 0.010). The association between AF and worse outcome was not modified by previous or concomitant use of anticoagulants or steroid therapy (P for interaction >0.05 for both) and was not related to stroke or bleeding events. CONCLUSION: Among hospitalized patients with COVID-19, a history of AF contributes to worse clinical course with a higher mortality and in-hospital events including new-onset AF, acute HF, and multiorgan failure. The mortality risk remains significant after adjustment for variables associated with COVID-19 severity and comorbidities.

The prognostic value of serial troponin measurements in patients admitted for COVID-19.

AIMS: Myocardial injury (MI) in coronavirus disease-19 (COVID-19) is quite prevalent at admission and affects prognosis. Little is known about troponin trajectories and their prognostic role. We aimed to describe the early in-hospital evolution of MI and its prognostic impact. METHODS AND RESULTS: We performed an analysis from an Italian multicentre study enrolling COVID-19 patients, hospitalized from 1 March to 9 April 2020. MI was defined as increased troponin level. The first troponin was tested within 24 h from admission, the second one between 24 and 48 h. Elevated troponin was defined as values above the 99th percentile of normal values. Patients were divided in four groups: normal, normal then elevated, elevated then normal, and elevated. The outcome was in-hospital death. The study population included 197 patients; 41% had normal troponin at both evaluations, 44% had elevated troponin at both assessments, 8% had normal then elevated troponin, and 7% had elevated then normal troponin. During hospitalization, 49 (25%) patients died. Patients with incident MI, with persistent MI, and with MI only at admission had a higher risk of death compared with those with normal troponin at both evaluations (P < 0.001). At multivariable analysis, patients with normal troponin at admission and MI injury on Day 2 had the highest mortality risk (hazard ratio 3.78, 95% confidence interval 1.10-13.09, P = 0.035). CONCLUSIONS: In patients admitted for COVID-19, re-test MI on Day 2 provides a prognostic value. A non-negligible proportion of patients with incident MI on Day 2 is identified at high risk of death only by the second measurement.

Evidence for Biological Age Acceleration and Telomere Shortening in COVID-19 Survivors.

The SARS-CoV-2 infection determines the COVID-19 syndrome characterized, in the worst cases, by severe respiratory distress, pulmonary and cardiac fibrosis, inflammatory cytokine release, and immunosuppression. This condition has led to the death of about 2.15% of the total infected world population so far. Among survivors, the presence of the so-called persistent post-COVID-19 syndrome (PPCS) is a common finding. In COVID-19 survivors, PPCS presents one or more symptoms: fatigue, dyspnea, memory loss, sleep disorders, and difficulty concentrating. In this study, a cohort of 117 COVID-19 survivors (post-COVID-19) and 144 non-infected volunteers (COVID-19-free) was analyzed using pyrosequencing of defined CpG islands previously identified as suitable for biological age determination. The results show a consistent biological age increase in the post-COVID-19 population, determining a DeltaAge acceleration of 10.45 ± 7.29 years (+5.25 years above the range of normality) compared with 3.68 ± 8.17 years for the COVID-19-free population (p < 0.0001). A significant telomere shortening parallels this finding in the post-COVID-19 cohort compared with COVID-19-free subjects (p < 0.0001). Additionally, ACE2 expression was decreased in post-COVID-19 patients, compared with the COVID-19-free population, while DPP-4 did not change. In light of these observations, we hypothesize that some epigenetic alterations are associated with the post-COVID-19 condition, particularly in younger patients (< 60 years).

Joint effect of heart failure and coronary artery disease on the risk of death during hospitalization for COVID-19.

AIMS: heart failure (HF) and coronary artery disease (CAD) are independent predictors of death in patients with COVID-19. The adverse prognostic impact of the combination of HF and CAD in these patients is unclear. METHODS AND RESULTS: we analysed data from 954 consecutive patients hospitalized for SARS-CoV-2 in five Italian Hospitals from February 23 to May 22, 2020. The study was a systematic prospective data collection according to a pre-specified protocol. All-cause mortality during hospitalization was the outcome measure. Mean duration of hospitalization was 33 days. Mortality was 11% in the total population and 7.4% in the group without evidence of HF or CAD (reference group). Mortality was 11.6% in the group with CAD and without HF (odds ratio [OR]: 1.6, p = 0.120), 15.5% in the group with HF and without CAD (OR: 2.3, p = 0.032), and 35.6% in the group with CAD and HF (OR: 6.9, p<0.0001). The risk of mortality in patients with CAD and HF combined was consistently higher than the sum of risks related to either disorder, resulting in a significant synergistic effect (p<0.0001) of the two conditions. Age-adjusted attributable proportion due to interaction was 64%. Adjusting for the simultaneous effects of age, hypotension, and lymphocyte count did not significantly lower attributable proportion which persisted statistically significant (p = 0.0360). CONCLUSION: The combination of HF and CAD exerts a marked detrimental impact on the risk of mortality in hospitalized patients with COVID-19, which is independent on other adverse prognostic markers.

Impact of heart failure on the clinical course and outcomes of patients hospitalized for COVID-19. Results of the Cardio-COVID-Italy multicentre study.

AIMS: To assess the prognostic value of a history of heart failure (HF) in patients with coronavirus disease 2019 (COVID-19). METHODS AND RESULTS: We enrolled 692 consecutive patients admitted for COVID-19 in 13 Italian cardiology centres between 1 March and 9 April 2020. Mean age was 67.4 ± 13.2 years, 69.5% of patients were males, 90 (13.0%) had a history of HF, median hospitalization length was 14 days (interquartile range 9-24). In-hospital death occurred in 37 of 90 patients (41.1%) with HF history vs. 126 of those with no HF history (20.9%). The increased risk of death associated with HF history remained significant after adjustment for clinical variables related to COVID-19 and HF severity, including comorbidities, oxygen saturation, lymphocyte count and plasma troponin [adjusted hazard ratio (HR) for death: 2.25; 95% confidence interval (CI) 1.26-4.02; P = 0.006 at multivariable Cox regression model including 404 patients]. Patients with a history of HF also had more in-hospital complications including acute HF (33.3% vs. 5.1%, P < 0.001), acute renal failure (28.1% vs. 12.9%, P < 0.001), multiorgan failure (15.9% vs. 5.8%, P = 0.004) and sepsis (18.4% vs. 8.9%, P = 0.006). Other independent predictors of outcome were age, sex, oxygen saturation and oxygen partial pressure at arterial gas analysis/fraction of inspired oxygen ratio (PaO2 /FiO2 ). In-hospital treatment with corticosteroids and heparin had beneficial effects (adjusted HR for death: 0.46; 95% CI 0.29-0.74; P = 0.001; n = 404 for corticosteroids, and adjusted HR 0.41; 95% CI 0.25-0.67; P < 0.001; n = 364 for heparin). CONCLUSIONS: Hospitalized patients with COVID-19 and a history of HF have an extremely poor outcome with higher mortality and in-hospital complications. HF history is an independent predictor of increased in-hospital mortality.

Pulmonary embolism in patients with COVID-19: characteristics and outcomes in the Cardio-COVID Italy multicenter study.

BACKGROUND: Pulmonary embolism (PE) has been described in coronavirus disease 2019 (COVID-19) critically ill patients, but the evidence from more heterogeneous cohorts is limited. METHODS: Data were retrospectively obtained from consecutive COVID-19 patients admitted to 13 Cardiology Units in Italy, from March 1st to April 9th, 2020, and followed until in-hospital death, discharge, or April 23rd, 2020. The association of baseline variables with computed tomography-confirmed PE was investigated by Cox hazards regression analysis. The relationship between D-dimer levels and PE incidence was evaluated using restricted cubic splines models. RESULTS: The study included 689 patients (67.3 ± 13.2 year-old, 69.4% males), of whom 43.6% were non-invasively ventilated and 15.8% invasively. 52 (7.5%) had PE over 15 (9-24) days of follow-up. Compared with those without PE, these subjects had younger age, higher BMI, less often heart failure and chronic kidney disease, more severe cardio-pulmonary involvement, and higher admission D-dimer [4344 (1099-15,118) vs. 818.5 (417-1460) ng/mL, p < 0.001]. They also received more frequently darunavir/ritonavir, tocilizumab and ventilation support. Furthermore, they faced more bleeding episodes requiring transfusion (15.6% vs. 5.1%, p < 0.001) and non-significantly higher in-hospital mortality (34.6% vs. 22.9%, p = 0.06). In multivariate regression, only D-dimer was associated with PE (HR 1.72, 95% CI 1.13-2.62; p = 0.01). The relation between D-dimer concentrations and PE incidence was linear, without inflection point. Only two subjects had a baseline D-dimer < 500 ng/mL. CONCLUSIONS: PE occurs in a sizable proportion of hospitalized COVID-19 patients. The implications of bleeding events and the role of D-dimer in this population need to be clarified.

Mental health and risk perception among Italian healthcare workers during the second month of the Covid-19 pandemic.

A multicentre cross-sectional study was conducted to assess perceived risk and fear of contagion, as well as mental health outcomes among 650 Italian healthcare workers during the COVID-19 outbreak. A relevant proportion of the sample reported symptoms of anxiety, depression, and distress. Female sex, nursing profession, fear of being infected, as well as the time of exposure to the COVID-19 spread and the fact of directly attending infected patients were the main risk factors for developing mental health disturbances. Tailored interventions need to be implemented to reduce psychological burden in healthcare workers, with a particular attention to nurses.

Association of Troponin Levels With Mortality in Italian Patients Hospitalized With Coronavirus Disease 2019: Results of a Multicenter Study.

IMPORTANCE: Myocardial injury, detected by elevated plasma troponin levels, has been associated with mortality in patients hospitalized with coronavirus disease 2019 (COVID-19). However, the initial data were reported from single-center or 2-center studies in Chinese populations. Compared with these patients, European and US patients are older, with more comorbidities and higher mortality rates. OBJECTIVE: To evaluate the prevalence and prognostic value of myocardial injury, detected by elevated plasma troponin levels, in a large population of White Italian patients with COVID-19. DESIGN, SETTING, AND PARTICIPANTS: This is a multicenter, cross-sectional study enrolling consecutive patients with laboratory-confirmed COVID-19 who were hospitalized in 13 Italian cardiology units from March 1 to April 9, 2020. Patients admitted for acute coronary syndrome were excluded. Elevated troponin levels were defined as values greater than the 99th percentile of normal values. MAIN OUTCOMES AND MEASURES: Clinical characteristics and outcomes stratified as elevated or normal cardiac troponin levels at admission, defined as troponin T or troponin I at a level greater than the 99th percentile of normal values. RESULTS: A total of 614 patients with COVID-19 were included in this study (mean age [SD], 67 [13] years; 70.8% male), of whom 148 patients (24.1%) died during the hospitalization. Elevated troponin levels were found in 278 patients (45.3%). These patients were older (mean [SD] age, 64.0 [13.6] years vs 71.3 [12.0] years; P < .001) and had higher prevalence of hypertension (168 patients [50.5%] vs 182 patients [65.9%]; P < .001), heart failure (24 [7.2%]; 63 [22.8%]; P < .001), coronary artery disease (50 [15.0%] vs 87 [31.5%]; P < .001), and atrial fibrillation (33 [9.9%] vs 67 [24.3%]; P < .001). Elevated troponin levels were associated with an increased in-hospital mortality (37% vs 13%; HR, 1.71 [95% CI, 1.13-2.59]; P = .01 via multivariable Cox regression analysis), and this was independent from concomitant cardiac disease. Elevated troponin levels were also associated with a higher risk of in-hospital complications: heart failure (44 patients [19.2%] vs 7 patients [2.9%]; P < .001), sepsis (31 [11.7%] vs 21 [6.4%]; P = .03), acute kidney failure (41 [20.8%] vs 13 [6.2%]; P < .001), multiorgan failure (21 [10.9%] vs 6 [2.9%]; P = .003), pulmonary embolism (27 [9.9%] vs 17 [5.2%]; P = .04), delirium (13 [6.8%] vs 3 [1.5%]; P = .02), and major bleeding (16 [7.0%] vs 4 [1.6%]; P = .008). CONCLUSIONS AND RELEVANCE: In this multicenter, cross-sectional study of Italian patients with COVID-19, elevated troponin was an independent variable associated with in-hospital mortality and a greater risk of cardiovascular and noncardiovascular complications during a hospitalization for COVID-19.

Cardiac rehabilitation activities during the COVID-19 pandemic in Italy. Position Paper of the AICPR (Italian Association of Clinical Cardiology, Prevention and Rehabilitation).

The COVID-19 outbreak is having a significant impact on both cardiac rehabilitation (CR) inpatient and outpatient healthcare organization. The variety of clinical and care scenarios we are observing in Italy depends on the region, the organization of local services and the hospital involved. Some hospital wards have been closed to make room to dedicated beds or to quarantine the exposed health personnel. In other cases, CR units have been converted or transformed into COVID-19 units.  The present document aims at defining the state of the art of CR during COVID-19 pandemic, through the description of the clinical and management scenarios frequently observed during this period and the exploration of the future frontiers in the management of cardiac rehabilitation programs after the COVID-19 outbreak.