Geza Halasz1, Michela Sperti2, Matteo Villani3, Umberto Michelucci4, Piergiuseppe Agostoni5, Andrea Biagi1, Luca Rossi6, Andrea Botti7, Chiara Mari7, Marco Maccarini8, Filippo Pura8, Loris Roveda8, Alessia Nardecchia9, Emanuele Mottola10, Massimo Nolli3, Elisabetta Salvioni5, Massimo Mapelli5, Marco Agostino Deriu2, Dario Piga8, Massimo Piepoli1. 1. Cardiology department, Guglielmo Da Saliceto Hospital, Piacenza, Italy;, Via Taverna, Piacenza, IT. 2. PolitoBIOMed Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Torino, Italy.;, Torino, IT. 3. Anesthesiology and ICU department Guglielmo da Saliceto Hospital; Piacenza, Italy.;, Piacenza, IT. 4. TOELT LLC, Birchlenstr. 25, 8600 Dubendorf, Switzerland.;, Dubendorf, CH. 5. Department of Clinical Sciences and Community Health, Centro Cardiologico Monzino, IRCCS Milan, Italy.;, Milano, IT. 6. Cardiology Department Guglielmo Da Saliceto Hospital; Piacenza, Italy.;, Piacenza, IT. 7. Department of Clinical and Experimental Medicine, University of Parma, Parma, Italy.;, Parma, IT. 8. Istituto Dalle Molle di studi sulI'Intelligenza Artificiale IDSIA - USI/SUPSI, Via la Santa 1, CH-6962 Lugano-Viganello, Switzerland.;, Lugano, CH. 9. IIS A.Cesaris, viale Cadorna, Casalpusterlengo, Italy.;, Casalpusterlengo, IT. 10. 7HC srl, Rome Italy.;, Rome, IT.
Abstract
BACKGROUND: Several models have been developed to predict mortality in patients with COVID-19 pneumonia, but only few have demonstrated enough discriminatory capacity. Machine-learning algorithms represent a novel approach for data-driven prediction of clinical outcomes with advantages over statistical modelling. OBJECTIVE: To develop the Piacenza score, a Machine-learning based score, for 30-day mortality prediction in patients with COVID-19 pneumonia. METHODS: The study comprised 852 patients with COVID-19 pneumonia, admitted to the Guglielmo da Saliceto Hospital (Italy) from February to November 2020. The patients' medical history, demographic and clinical data were collected in an electronic health record. The overall patient dataset was randomly splitted into derivation and test cohort. The score was obtained through the Naïve Bayes classifier and externally validated on 86 patients admitted to Centro Cardiologico Monzino (Italy) in February 2020. Using a forward-search algorithm six features were identified: age; mean corpuscular haemoglobin concentration; PaO2/FiO2 ratio; temperature; previous stroke; gender. The Brier index was used to evaluate the ability of the ML model to stratify and predict observed outcomes. A user-friendly web site available at https://covid.7hc.tech was designed and developed to enable a fast and easy use of the tool by the final user (i.e., the physician). Regarding the customization properties to the Piacenza score, we added a personalized version of the algorithm inside the website, which enables an optimized computation of the mortality risk score for a single patient, when some variables used by the Piacenza score are not available. In this case, the Naïve Bayes classifier is re-trained over the same derivation cohort but using a different set of patient's characteristics. We also compared the Piacenza score with the 4C score and with a Naïve Bayes algorithm with 14 features chosen a-priori. RESULTS: The Piacenza score showed an AUC of 0.78 (95% CI 0.74-0.84 Brier-score 0.19) in the internal validation cohort and 0.79 (95% CI 0.68-0.89, Brier-score 0.16) in the external validation cohort showing a comparable accuracy respect to the 4C score and to the Naïve Bayes model with a-priori chosen features, which achieved an AUC of 0.78 (95% CI 0.73-0.83, Brier-score 0.26) and 0.80 (95% CI 0.75-0.86, Brier-score 0.17) respectively. CONCLUSIONS: A personalized Machine-learning based score with a purely data driven features selection is feasible and effective to predict mortality in patients with COVID-19 pneumonia.
BACKGROUND: Several models have been developed to predict mortality in patients with COVID-19 pneumonia, but only few have demonstrated enough discriminatory capacity. Machine-learning algorithms represent a novel approach for data-driven prediction of clinical outcomes with advantages over statistical modelling. OBJECTIVE: To develop the Piacenza score, a Machine-learning based score, for 30-day mortality prediction in patients with COVID-19 pneumonia. METHODS: The study comprised 852 patients with COVID-19 pneumonia, admitted to the Guglielmo da Saliceto Hospital (Italy) from February to November 2020. The patients' medical history, demographic and clinical data were collected in an electronic health record. The overall patient dataset was randomly splitted into derivation and test cohort. The score was obtained through the Naïve Bayes classifier and externally validated on 86 patients admitted to Centro Cardiologico Monzino (Italy) in February 2020. Using a forward-search algorithm six features were identified: age; mean corpuscular haemoglobin concentration; PaO2/FiO2 ratio; temperature; previous stroke; gender. The Brier index was used to evaluate the ability of the ML model to stratify and predict observed outcomes. A user-friendly web site available at https://covid.7hc.tech was designed and developed to enable a fast and easy use of the tool by the final user (i.e., the physician). Regarding the customization properties to the Piacenza score, we added a personalized version of the algorithm inside the website, which enables an optimized computation of the mortality risk score for a single patient, when some variables used by the Piacenza score are not available. In this case, the Naïve Bayes classifier is re-trained over the same derivation cohort but using a different set of patient's characteristics. We also compared the Piacenza score with the 4C score and with a Naïve Bayes algorithm with 14 features chosen a-priori. RESULTS: The Piacenza score showed an AUC of 0.78 (95% CI 0.74-0.84 Brier-score 0.19) in the internal validation cohort and 0.79 (95% CI 0.68-0.89, Brier-score 0.16) in the external validation cohort showing a comparable accuracy respect to the 4C score and to the Naïve Bayes model with a-priori chosen features, which achieved an AUC of 0.78 (95% CI 0.73-0.83, Brier-score 0.26) and 0.80 (95% CI 0.75-0.86, Brier-score 0.17) respectively. CONCLUSIONS: A personalized Machine-learning based score with a purely data driven features selection is feasible and effective to predict mortality in patients with COVID-19 pneumonia.
Authors: Maria Elena Laino; Elena Generali; Tobia Tommasini; Giovanni Angelotti; Alessio Aghemo; Antonio Desai; Pierandrea Morandini; Giulio G Stefanini; Ana Lleo; Antonio Voza; Victor Savevski Journal: Arch Med Sci Date: 2022-01-14 Impact factor: 3.707
Authors: Alexandra June Gordon; Prasanthi Govindarajan; Christopher L Bennett; Loretta Matheson; Michael A Kohn; Carlos Camargo; Jeffrey Kline Journal: BMJ Open Date: 2022-04-21 Impact factor: 3.006
Authors: Robert A Raschke; Pooja Rangan; Sumit Agarwal; Suresh Uppalapu; Nehan Sher; Steven C Curry; C William Heise Journal: PLoS One Date: 2022-07-06 Impact factor: 3.752
Authors: Alba González-Cebrián; Joan Borràs-Ferrís; Juan Pablo Ordovás-Baines; Marta Hermenegildo-Caudevilla; Mónica Climente-Marti; Sonia Tarazona; Raffaele Vitale; Daniel Palací-López; Jesús Francisco Sierra-Sánchez; Javier Saez de la Fuente; Alberto Ferrer Journal: PLoS One Date: 2022-09-22 Impact factor: 3.752
Authors: J M Smit; M E van Genderen; M J T Reinders; D A M P J Gommers; J H Krijthe; J Van Bommel Journal: Crit Care Date: 2021-12-23 Impact factor: 9.097