BACKGROUND: Identifying patients at higher risk of healthcare-associated infections (HAIs) in intensive care unit (ICU) represents a major challenge for public health. Machine learning could improve patient risk stratification and lead to targeted infection prevention and control interventions.AIM: To evaluate the performance of the Simplified Acute Physiology Score (SAPS) II for HAIs risk prediction in ICUs, using both traditional statistical and machine learning approaches.METHODS: We used data of 7827 patients from the "Italian Nosocomial Infections Surveillance in Intensive Care Units" project. The Support Vector Machines (SVM) algorithm was applied to classify patients according to sex, patient origin, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II at admission, presence of invasive devices, trauma, impaired immunity, antibiotic therapy in 48 hours before ICU admission.FINDINGS: The performance of SAPS II for predicting the risk of HAIs provides a ROC (Receiver Operating Characteristics) curve with an AUC (Area Under the Curve) of 0.612 (p<0.001) and an accuracy of 56%. Considering SAPS II along with other characteristics at ICU admission, we found an accuracy of the SVM classifier of 88% and an AUC of 0.90 (p<0.001) for the test set. In line, the predictive ability was lower when considering the same SVM model but removing the SAPS II variable (accuracy= 78% and AUC= 0.66).CONCLUSIONS: Our study suggested the SVM model as a tool to early predict patients at higher risk of HAI at ICU admission.

A machine learning approach to predict healthcare-associated infections at intensive care unit admission: findings from the SPIN-UTI project / Martina, Barchitta; Andrea, Maugeri; Giuliana, Favara; Paolo Marco, Riela; Giovanni, Gallo; Ida, Mura; Antonella, Agodi; behalf of the SPIN-UTI network Paola Murgia, On; Dolores, Maria; Masia, ; Brusaferro, Silvio; Celotto, Daniele; Arnoldo, Luca; Bissolo, Emanuela; Rigo, Alberto; Tardivo, Stefano; Moretti, Francesca; Carli, Alberto; Pascu, Diana; Tessari, Lorella; Olga Bernasconi, Mara; Brusaferro, Marco; Pappalardo, Federico; Auxilia, Francesco; Fenaroli, Salesia; Pasquarella, Cesira; Sicoli, Ennio; Teresa Montagna, Maria; Egitto, Giovanni; Squeri, Raffaele; Tribastoni, Salvatore; Pulvirenti, Alessandro; Catalano, Sebastiano; Battaglia, Pietro; Bellocch, Patrizia; Castiglione, Igiacomo; Rita Mattaliano, Anna; Astuto, Marinella; Giuseppa LaCamera, Marinella; Maria Longhitano, Anna; Scrofani, Giorgio; Concetta Monea, Maria; Milazzo, Marina; Giarratano, Antonino; Calamusa, Giuseppe; Valeriatorregrossa, Maria; Di Benedetto, Antonino; MariaGisella Rizzo, Giuseppa; Manta, Giuseppe; Tetamo, Romano; Mancuso, Rosa; Maria Mella, Laura; Dei, Ignazio; Pandiani Antonino Cannistrà, Irene; Piotti, Paola; Girardis, Massimo; Righi, Elena; Barbieri, Alberto; Crollari, Patricia; Borracino, Albino; Coniglio, Salvatore; Palermo, Rosaria; Pintaudi, Sergio; Distefano, Daniela; Romeo, Antonina; Sticca, Giovanna; Minerva, Massimo; Fabiani, Leila; Gentile, Alessandra; Stefanini, Paolo; Mario D'Errico, Marcello; Donati, Abele; Deremigis, Santa; Venturoni, Federica; Antoci, Manuela; Pagliarulo, Riccardo; Bianco, Aida; Pavia, Maria; Pasculli, Marcello; Vittori, Cesare; Battista Orsi, Giovanni; Arrigoni, Cristina; Patrizia Olori, Maria; Antonelli, Massimo; Laurenti, Patrizia; Ingala, Franco; Conte, Carmela; Russo, Salvatore; Condorelli, Laura; Farruggia, Patrizia; Maria Luisa, Cristina; Galassi, Italia. - In: THE JOURNAL OF HOSPITAL INFECTION. - ISSN 0195-6701. - 112:(2021), pp. 77-86. [10.1016/j.jhin.2021.02.025]

A machine learning approach to predict healthcare-associated infections at intensive care unit admission: findings from the SPIN-UTI project

Elena Righi;Alberto Barbieri
Membro del Collaboration Group
;
2021

Abstract

BACKGROUND: Identifying patients at higher risk of healthcare-associated infections (HAIs) in intensive care unit (ICU) represents a major challenge for public health. Machine learning could improve patient risk stratification and lead to targeted infection prevention and control interventions.AIM: To evaluate the performance of the Simplified Acute Physiology Score (SAPS) II for HAIs risk prediction in ICUs, using both traditional statistical and machine learning approaches.METHODS: We used data of 7827 patients from the "Italian Nosocomial Infections Surveillance in Intensive Care Units" project. The Support Vector Machines (SVM) algorithm was applied to classify patients according to sex, patient origin, non-surgical treatment for acute coronary disease, surgical intervention, SAPS II at admission, presence of invasive devices, trauma, impaired immunity, antibiotic therapy in 48 hours before ICU admission.FINDINGS: The performance of SAPS II for predicting the risk of HAIs provides a ROC (Receiver Operating Characteristics) curve with an AUC (Area Under the Curve) of 0.612 (p<0.001) and an accuracy of 56%. Considering SAPS II along with other characteristics at ICU admission, we found an accuracy of the SVM classifier of 88% and an AUC of 0.90 (p<0.001) for the test set. In line, the predictive ability was lower when considering the same SVM model but removing the SAPS II variable (accuracy= 78% and AUC= 0.66).CONCLUSIONS: Our study suggested the SVM model as a tool to early predict patients at higher risk of HAI at ICU admission.
2021
112
77
86
A machine learning approach to predict healthcare-associated infections at intensive care unit admission: findings from the SPIN-UTI project / Martina, Barchitta; Andrea, Maugeri; Giuliana, Favara; Paolo Marco, Riela; Giovanni, Gallo; Ida, Mura; Antonella, Agodi; behalf of the SPIN-UTI network Paola Murgia, On; Dolores, Maria; Masia, ; Brusaferro, Silvio; Celotto, Daniele; Arnoldo, Luca; Bissolo, Emanuela; Rigo, Alberto; Tardivo, Stefano; Moretti, Francesca; Carli, Alberto; Pascu, Diana; Tessari, Lorella; Olga Bernasconi, Mara; Brusaferro, Marco; Pappalardo, Federico; Auxilia, Francesco; Fenaroli, Salesia; Pasquarella, Cesira; Sicoli, Ennio; Teresa Montagna, Maria; Egitto, Giovanni; Squeri, Raffaele; Tribastoni, Salvatore; Pulvirenti, Alessandro; Catalano, Sebastiano; Battaglia, Pietro; Bellocch, Patrizia; Castiglione, Igiacomo; Rita Mattaliano, Anna; Astuto, Marinella; Giuseppa LaCamera, Marinella; Maria Longhitano, Anna; Scrofani, Giorgio; Concetta Monea, Maria; Milazzo, Marina; Giarratano, Antonino; Calamusa, Giuseppe; Valeriatorregrossa, Maria; Di Benedetto, Antonino; MariaGisella Rizzo, Giuseppa; Manta, Giuseppe; Tetamo, Romano; Mancuso, Rosa; Maria Mella, Laura; Dei, Ignazio; Pandiani Antonino Cannistrà, Irene; Piotti, Paola; Girardis, Massimo; Righi, Elena; Barbieri, Alberto; Crollari, Patricia; Borracino, Albino; Coniglio, Salvatore; Palermo, Rosaria; Pintaudi, Sergio; Distefano, Daniela; Romeo, Antonina; Sticca, Giovanna; Minerva, Massimo; Fabiani, Leila; Gentile, Alessandra; Stefanini, Paolo; Mario D'Errico, Marcello; Donati, Abele; Deremigis, Santa; Venturoni, Federica; Antoci, Manuela; Pagliarulo, Riccardo; Bianco, Aida; Pavia, Maria; Pasculli, Marcello; Vittori, Cesare; Battista Orsi, Giovanni; Arrigoni, Cristina; Patrizia Olori, Maria; Antonelli, Massimo; Laurenti, Patrizia; Ingala, Franco; Conte, Carmela; Russo, Salvatore; Condorelli, Laura; Farruggia, Patrizia; Maria Luisa, Cristina; Galassi, Italia. - In: THE JOURNAL OF HOSPITAL INFECTION. - ISSN 0195-6701. - 112:(2021), pp. 77-86. [10.1016/j.jhin.2021.02.025]
Martina, Barchitta; Andrea, Maugeri; Giuliana, Favara; Paolo Marco, Riela; Giovanni, Gallo; Ida, Mura; Antonella, Agodi; behalf of the SPIN-UTI network Paola Murgia, On; Dolores, Maria; Masia, ; Brusaferro, Silvio; Celotto, Daniele; Arnoldo, Luca; Bissolo, Emanuela; Rigo, Alberto; Tardivo, Stefano; Moretti, Francesca; Carli, Alberto; Pascu, Diana; Tessari, Lorella; Olga Bernasconi, Mara; Brusaferro, Marco; Pappalardo, Federico; Auxilia, Francesco; Fenaroli, Salesia; Pasquarella, Cesira; Sicoli, Ennio; Teresa Montagna, Maria; Egitto, Giovanni; Squeri, Raffaele; Tribastoni, Salvatore; Pulvirenti, Alessandro; Catalano, Sebastiano; Battaglia, Pietro; Bellocch, Patrizia; Castiglione, Igiacomo; Rita Mattaliano, Anna; Astuto, Marinella; Giuseppa LaCamera, Marinella; Maria Longhitano, Anna; Scrofani, Giorgio; Concetta Monea, Maria; Milazzo, Marina; Giarratano, Antonino; Calamusa, Giuseppe; Valeriatorregrossa, Maria; Di Benedetto, Antonino; MariaGisella Rizzo, Giuseppa; Manta, Giuseppe; Tetamo, Romano; Mancuso, Rosa; Maria Mella, Laura; Dei, Ignazio; Pandiani Antonino Cannistrà, Irene; Piotti, Paola; Girardis, Massimo; Righi, Elena; Barbieri, Alberto; Crollari, Patricia; Borracino, Albino; Coniglio, Salvatore; Palermo, Rosaria; Pintaudi, Sergio; Distefano, Daniela; Romeo, Antonina; Sticca, Giovanna; Minerva, Massimo; Fabiani, Leila; Gentile, Alessandra; Stefanini, Paolo; Mario D'Errico, Marcello; Donati, Abele; Deremigis, Santa; Venturoni, Federica; Antoci, Manuela; Pagliarulo, Riccardo; Bianco, Aida; Pavia, Maria; Pasculli, Marcello; Vittori, Cesare; Battista Orsi, Giovanni; Arrigoni, Cristina; Patrizia Olori, Maria; Antonelli, Massimo; Laurenti, Patrizia; Ingala, Franco; Conte, Carmela; Russo, Salvatore; Condorelli, Laura; Farruggia, Patrizia; Maria Luisa, Cristina; Galassi, Italia
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0195670121000840-main.pdf

Accesso riservato

Tipologia: Versione pubblicata dall'editore
Dimensione 427.82 kB
Formato Adobe PDF
427.82 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1244576
Citazioni
  • ???jsp.display-item.citation.pmc??? 6
  • Scopus 11
  • ???jsp.display-item.citation.isi??? 10
social impact