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


Journal

Journal of cardiovascular medicine (Hagerstown, Md.)
ISSN: 1558-2035
Titre abrégé: J Cardiovasc Med (Hagerstown)
Pays: United States
ID NLM: 101259752

Informations de publication

Date de publication:
01 07 2022
Historique:
entrez: 28 6 2022
pubmed: 29 6 2022
medline: 1 7 2022
Statut: ppublish

Résumé

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. 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 ± 13.2 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). 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.

Sections du résumé

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 ± 13.2 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.

Identifiants

pubmed: 35763764
doi: 10.2459/JCM.0000000000001329
pii: 01244665-202207000-00004
doi:

Substances chimiques

Troponin 0
Creatinine AYI8EX34EU

Types de publication

Journal Article Multicenter Study

Langues

eng

Sous-ensembles de citation

IM

Pagination

439-446

Informations de copyright

Copyright © 2022 Italian Federation of Cardiology - I.F.C. All rights reserved.

Références

Berlin DA, Gulick RM, Martinez FJ. Severe Covid-19. N Engl J Med 2020; 383:2451–2460.
Inciardi RM, Adamo M, Lupi L, et al. Characteristics and outcomes of patients hospitalized for COVID-19 and cardiac disease in Northern Italy. Eur Heart J 2020; 41:1821–1829.
Inciardi RM, Lupi L, Zaccone G, et al. Cardiac involvement in a patient with coronavirus disease 2019 (COVID-19). JAMA Cardiol 2020; 5:819–824.
Lombardi CM, Carubelli V, Iorio A, et al. Association of troponin levels with mortality in Italian patients hospitalized with coronavirus disease 2019: results of a multicenter study. JAMA Cardiol 2020; 5:1274–1280.
Tomasoni D, Inciardi RM, Lombardi CM, et al. Impact of heart failure on the clinical course and outcomes of patients hospitalized for COVID-19: results of the Cardio-COVID-Italy multicentre study. Eur J Heart Fail 2020; 22:2238–2247.
Nuzzi V, Merlo M, Specchia C, et al. The prognostic value of serial troponin measurements in patients admitted for COVID-19. ESC Heart Fail 2021; 8:3504–3511.
Levey AS, Stevens LA, Schmid CH, et al. A new equation to estimate glomerular filtration rate. Ann Intern Med 2009; 150:604–612.
Stekhoven DJ, Bühlmann P. MissForest—nonparametric missing value imputation for mixed-type data. Bioinformatics 2012; 28:112–118.
Dancelli L, Manisera M, Vezzoli M. On two classes of weighted rank correlation measures deriving from the Spearman's ρ. Studies in classification, data analysis, and knowledge organization . New York: Springer; 2013.
Salvi A, Vezzoli M, Busatto S, et al. Analysis of a nanoparticle-enriched fraction of plasma reveals miRNA candidates for Down syndrome pathogenesis. Int J Mol Med 2019; 43:2303–2318.
Codenotti S, Vezzoli M, Poliani PL, et al. Caveolin-1, Caveolin-2 and Cavin-1 are strong predictors of adipogenic differentiation in human tumors and cell lines of liposarcoma. Eur J Cell Biol 2016; 95:252–264.
Vezzoli M, Ravaggi A, Zanotti L, et al. RERT: a novel regression tree approach to predict extrauterine disease in endometrial carcinoma patients. Sci Rep 2017; 7:10528.
Carpita M, Vezzoli M. Statistical evidence of the subjective work quality: the fairness drivers of the job satisfaction. Electron J Appl Stat Anal 2012; 5:89–107.
Abate G, Vezzoli M, Polito L, et al. A conformation variant of p53 combined with machine learning identifies alzheimer disease in preclinical and prodromal stages. J Pers Med 2021; 11:1–16.
Garrafa E, Vezzoli M, Ravanelli M, et al. Early prediction of in-hospital death of COVID-19 patients: a machine-learning model based on age, blood analyses, and chest x-ray score. eLife 2021; 10:e70640.
Breiman L. Random Forests. Mach Learn 2001; 45:5–32.
Vezzoli M. Exploring the facets of overall job satisfaction through a novel ensemble learning. Electron J Appl Stat Anal 2011; 4:23–38.
Savona R, Vezzoli M. Fitting and forecasting sovereign defaults using multiple risk signals. Oxf Bull Econ Stat 2015; 77:66–92.
Azzolina D, Ileana B, Giulia B, et al. Machine learning in clinical and epidemiological research: isn’t it time for biostatisticians to work on it? Epidemiol Biostat Public Health 2019; 16:e13245-1–e13245-3.
Friedman JH. Greedy Function Approximation: a gradient boosting machine. Ann Stat 2001; 29:1189–1232.
Knight SR, Ho A, Pius R, et al. Risk stratification of patients admitted to hospital with covid-19 using the ISARIC WHO Clinical Characterisation Protocol: development and validation of the 4C Mortality Score. BMJ 2020; 370:m3339.
Halasz G, Sperti M, Villani M, et al. A machine learning approach for mortality prediction in COVID-19 pneumonia: development and evaluation of the Piacenza score. J Med Internet Res 2021; 23:e29058.
Yuan Y, Sun C, Tang X, et al. Development and validation of a prognostic risk score system for COVID-19 inpatients: a multi-center retrospective study in China. Eng Beijing China 2020; 8:116–121.
Wiersinga WJ, Rhodes A, Cheng AC, Peacock SJ, Prescott HC. Pathophysiology, transmission, diagnosis, and treatment of coronavirus disease 2019 (COVID-19): a review. JAMA 2020; 324:782–793.
Romero Starke K, Petereit-Haack G, Schubert M, et al. The age-related risk of severe outcomes due to COVID-19 infection: a rapid review, meta-analysis, and meta-regression. Int J Environ Res Public Health 2020; 17:E5974.
Opal SM, Girard TD, Ely EW. The immunopathogenesis of sepsis in elderly patients. Clin Infect Dis 2005; 41: (Suppl 7): S504–512.
Wu Z, McGoogan JM. Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in China: summary of a report of 72314 cases from the Chinese Center for Disease Control and Prevention. JAMA 2020; 323:1239–1242.
Gibson PG, Qin L, Puah SH. COVID-19 acute respiratory distress syndrome (ARDS): clinical features and differences from typical pre-COVID-19 ARDS. Med J Aust 2020; 213:54.e1–56.e1.
Grasselli G, Greco M, Zanella A, et al. Risk factors associated with mortality among patients with COVID-19 in intensive care units in Lombardy, Italy. JAMA Intern Med 2020; 180:1345–1355.
Cheng Y, Luo R, Wang K, et al. Kidney disease is associated with in-hospital death of patients with COVID-19. Kidney Int 2020; 97:829–838.
Wang M, Xiong H, Chen H, Li Q, Ruan XZ. Renal injury by SARS-CoV-2 infection: a systematic review. Kidney Dis 2021; 7:100–110.
Wang D, Hu B, Hu C, et al. Clinical characteristics of 138 hospitalized patients with 2019 novel coronavirus–infected pneumonia in Wuhan, China. JAMA 2020; 323:1061–1069.
Inciardi RM, Solomon SD, Ridker PM, Metra M. Coronavirus 2019 disease (COVID-19), systemic inflammation, and cardiovascular disease. J Am Heart Assoc 2020; 9:e017756.
Nie S-F, Yu M, Xie T, et al. Cardiac troponin I is an independent predictor for mortality in hospitalized patients with COVID-19. Circulation 2020; 142:608–610.

Auteurs

Marika Vezzoli (M)

Department of Molecular and Translational Medicine, University of Brescia, Italy.

Riccardo Maria Inciardi (RM)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Chiara Oriecuia (C)

Department of Molecular and Translational Medicine, University of Brescia, Italy.
Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Sara Paris (S)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Natalia Herrera Murillo (NH)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Piergiuseppe Agostoni (P)

Centro Cardiologico Monzino, IRCCS, Department of Clinical Sciences and Community Health, University of Milano, Milan.
Department of Clinical Sciences and Community Health, University of Milano, Milan.

Pietro Ameri (P)

IRCCS Ospedale Policlinico San Martino and Department of Internal Medicine, University of Genova, Genova.

Antonio Bellasi (A)

Innovation and Brand Reputation Unit, Papa Giovanni XXIII Hospital, Bergamo.

Rita Camporotondo (R)

Fondazione IRCCS Policlinico S. Matteo and University of Pavia, Pavia.

Claudia Canale (C)

IRCCS Ospedale Policlinico San Martino and Department of Internal Medicine, University of Genova, Genova.

Valentina Carubelli (V)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Stefano Carugo (S)

Division of Cardiology, Ospedale San Paolo, ASST Santi Paolo E Carlo, University of Milano, Milan.

Francesco Catagnano (F)

Fondazione IRCCS Policlinico S. Matteo and University of Pavia, Pavia.
Cardiology Department, Policlinico Di Monza, Monza.

Giambattista Danzi (G)

Division of Cardiology, Ospedale Maggiore Di Cremona, Cremona.

Laura Dalla Vecchia (L)

Department of Cardiology, Istituti Clinici Scientifici Maugeri, IRCCS, Istituto Scientifico Di Milano, Milan.

Stefano Giovinazzo (S)

IRCCS Ospedale Policlinico San Martino and Department of Internal Medicine, University of Genova, Genova.

Massimiliano Gnecchi (M)

Fondazione IRCCS Policlinico S. Matteo and University of Pavia, Pavia.

Marco Guazzi (M)

Heart Failure Unit, Cardiology Department, IRCCS San Donato Hospital, University of Milan, Milan.

Anita Iorio (A)

Cardiovascular Department and Cardiology Unit, Papa Giovanni XXIII Hospital-Bergamo, Bergamo.

Maria Teresa La Rovere (MT)

Department of Cardiology, Istituti Clinici Scientifici Maugeri, IRCCS, Istituto Scientifico Di Pavia, Pavia.

Sergio Leonardi (S)

Fondazione IRCCS Policlinico S. Matteo and University of Pavia, Pavia.

Gloria Maccagni (G)

Heart Failure Unit, Cardiology Department, IRCCS San Donato Hospital, University of Milan, Milan.

Massimo Mapelli (M)

Centro Cardiologico Monzino, IRCCS, Department of Clinical Sciences and Community Health, University of Milano, Milan.
Department of Clinical Sciences and Community Health, University of Milano, Milan.

Davide Margonato (D)

Fondazione IRCCS Policlinico S. Matteo and University of Pavia, Pavia.
Cardiology Department, Policlinico Di Monza, Monza.

Marco Merlo (M)

Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, Trieste.

Luca Monzo (L)

Istituto Clinico Casal Palocco, Rome.
Policlinico Casilino, Rome.

Andrea Mortara (A)

Cardiology Department, Policlinico Di Monza, Monza.

Vincenzo Nuzzi (V)

Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, Trieste.

Matteo Pagnesi (M)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Massimo Piepoli (M)

Heart Failure Unit, G da Saliceto Hospital, AUSL Piacenza, Piacenza.
Institute of Life Sciences, Sant'Anna School of Advanced Studies, Pisa.

Italo Porto (I)

IRCCS Ospedale Policlinico San Martino and Department of Internal Medicine, University of Genova, Genova.

Andrea Pozzi (A)

Cardiovascular Department and Cardiology Unit, Papa Giovanni XXIII Hospital-Bergamo, Bergamo.

Giovanni Provenzale (G)

Division of Cardiology, Ospedale San Paolo, ASST Santi Paolo E Carlo, University of Milano, Milan.

Filippo Sarullo (F)

Cardiovascular Rehabilitation Unit, Buccheri La Ferla Fatebenefratelli Hospital, Palermo.

Michele Senni (M)

Cardiovascular Department and Cardiology Unit, Papa Giovanni XXIII Hospital-Bergamo, Bergamo.

Gianfranco Sinagra (G)

Cardiovascular Department, Azienda Sanitaria Universitaria Integrata, Trieste.

Daniela Tomasoni (D)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Marianna Adamo (M)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Maurizio Volterrani (M)

Department of Medical Sciences, Istituto Di Ricovero E Cura a Carattere Scientifico (IRCCS) San Raffaele Pisana.

Roberto Maroldi (R)

Radiology ASST Spedali Civili di Brescia and Department of Medical and Surgical, Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia, Italy.

Marco Metra (M)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Carlo Mario Lombardi (CM)

Cardiology, ASST Spedali Civili di Brescia and Department of Medical and Surgical Specialties, Radiological Sciences and Public Health, University of Brescia, Brescia.

Claudia Specchia (C)

Department of Molecular and Translational Medicine, University of Brescia, Italy.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH