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.

Sex-related differences in patients with coronavirus disease 2019: results of the Cardio-COVID-Italy multicentre study.

INTRODUCTION: The role of sex compared to comorbidities and other prognostic variables in patients with coronavirus disease (COVID-19) is unclear. METHODS: This is a retrospective observational study on patients with COVID-19 infection, referred to 13 cardiology units. The primary objective was to assess the difference in risk of death between the sexes. The secondary objective was to explore sex-based heterogeneity in the association between demographic, clinical and laboratory variables, and patients' risk of death. RESULTS: Seven hundred and one patients were included: 214 (30.5%) women and 487 (69.5%) men. During a median follow-up of 15 days, deaths occurred in 39 (18.2%) women and 126 (25.9%) men. In a multivariable Cox regression model, men had a nonsignificantly higher risk of death vs. women (P = 0.07).The risk of death was more than double in men with a low lymphocytes count as compared with men with a high lymphocytes count [overall survival hazard ratio (OS-HR) 2.56, 95% confidence interval (CI) 1.72-3.81]. In contrast, lymphocytes count was not related to death in women (P = 0.03).Platelets count was associated with better outcome in men (OS-HR for increase of 50 × 103 units: 0.88 95% CI 0.78-1.00) but not in women. The strength of association between higher PaO2/FiO2 ratio and lower risk of death was larger in women (OS-HR for increase of 50 mmHg/%: 0.72, 95% CI 0.59-0.89) vs. men (OS-HR: 0.88, 95% CI 0.80-0.98; P = 0.05). CONCLUSIONS: Patients' sex is a relevant variable that should be taken into account when evaluating risk of death from COVID-19. There is a sex-based heterogeneity in the association between baseline variables and patients' risk of death.

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.

Satisfaction with online teaching of medical statistics during the COVID-19 pandemic: A survey by the Education Committee of the Italian Society of Medical Statistics and Clinical Epidemiology.

On May 2020, after 2 months of online teaching with no face-to-face lectures, the Education Committee of the Italian scientific Society of Medical Statistics and Clinical Epidemiology conceived an online survey to assess satisfaction of Italian academics of medical statistics with online teaching and remote exams. This survey highlighted teachers' perceptions as well as opportunities and limitations of online teaching of medical statistics, biostatistics, and epidemiology. Although 61% of Italian academics of medical statistics declared to be favorable to provide online teaching of medical statistics, biostatistics, and epidemiology in the future, we recognize that distance education cannot substitute the unique value of teaching and knowledge exchange that could only be transmitted through a personal interaction between students and teachers. These indications may be useful to improve the quality of the teaching process in the future.

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.

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.

Characteristics and outcomes of patients hospitalized for COVID-19 and cardiac disease in Northern Italy.

AIMS: To compare demographic characteristics, clinical presentation, and outcomes of patients with and without concomitant cardiac disease, hospitalized for COVID-19 in Brescia, Lombardy, Italy. METHODS AND RESULTS: The study population includes 99 consecutive patients with COVID-19 pneumonia admitted to our hospital between 4 March and 25 March 2020. Fifty-three patients with a history of cardiac disease were compared with 46 without cardiac disease. Among cardiac patients, 40% had a history of heart failure, 36% had atrial fibrillation, and 30% had coronary artery disease. Mean age was 67 ± 12 years, and 80 (81%) patients were males. No differences were found between cardiac and non-cardiac patients except for higher values of serum creatinine, N-terminal probrain natriuretic peptide, and high sensitivity troponin T in cardiac patients. During hospitalization, 26% patients died, 15% developed thrombo-embolic events, 19% had acute respiratory distress syndrome, and 6% had septic shock. Mortality was higher in patients with cardiac disease compared with the others (36% vs. 15%, log-rank P = 0.019; relative risk 2.35; 95% confidence interval 1.08-5.09). The rate of thrombo-embolic events and septic shock during the hospitalization was also higher in cardiac patients (23% vs. 6% and 11% vs. 0%, respectively). CONCLUSIONS: Hospitalized patients with concomitant cardiac disease and COVID-19 have an extremely poor prognosis compared with subjects without a history of cardiac disease, with higher mortality, thrombo-embolic events, and septic shock rates.