Background: Mechanisms of myocardial ischemia in obstructive and non-obstructive coronary artery disease (CAD), and the interplay between clinical, functional, biological and psycho-social features, are still far to be fully elucidated. Objectives: To develop a machine-learning (ML) model for the supervised prediction of obstructive versus non-obstructive CAD. Methods: From the EVA study, we analysed adults hospitalized for IHD undergoing conventional coronary angiography (CCA). Non-obstructive CAD was defined by a stenosis < 50% in one or more vessels. Baseline clinical and psycho-socio-cultural characteristics were used for computing a Rockwood and Mitnitski frailty index, and a gender score according to GENESIS-PRAXY methodology. Serum concentration of inflammatory cytokines was measured with a multiplex flow cytometry assay. Through an XGBoost classifier combined with an explainable artificial intelligence tool (SHAP), we identified the most influential features in discriminating obstructive versus non-obstructive CAD. Results: Among the overall EVA cohort (n = 509), 311 individuals (mean age 67 ± 11 years, 38% females; 67% obstructive CAD) with complete data were analysed. The ML-based model (83% accuracy and 87% precision) showed that while obstructive CAD was associated with higher frailty index, older age and a cytokine signature characterized by IL-1β, IL-12p70 and IL-33, non-obstructive CAD was associated with a higher gender score (i.e., social characteristics traditionally ascribed to women) and with a cytokine signature characterized by IL-18, IL-8, IL-23. Conclusions: Integrating clinical, biological, and psycho-social features, we have optimized a sex- and gender-unbiased model that discriminates obstructive and non-obstructive CAD. Further mechanistic studies will shed light on the biological plausibility of these associations. Clinical trial registration: NCT02737982.

A machine-learning based bio-psycho-social model for the prediction of non-obstructive and obstructive coronary artery disease

Raparelli, Valeria
Primo
;
Tiziana Bellini
Membro del Collaboration Group
;
Giovanni Zuliani
Membro del Collaboration Group
;
Angelina Passaro
Membro del Collaboration Group
;
Brombo Gloria
Membro del Collaboration Group
;
Andrea Cutini
Membro del Collaboration Group
;
Eleonora Capatti
Membro del Collaboration Group
;
Edoardo Dalla Nora
Membro del Collaboration Group
;
Francesca Di Vece
Membro del Collaboration Group
;
Andrea D’Amuri
Membro del Collaboration Group
;
Tommaso Romagnoli
Membro del Collaboration Group
;
Michele Polastri
Membro del Collaboration Group
;
Alessandra Violi
Membro del Collaboration Group
;
Valeria Fortunato
Membro del Collaboration Group
;
Alessandro Bella
Membro del Collaboration Group
;
Salvatore Greco
Membro del Collaboration Group
;
Riccardo Spaggiari
Membro del Collaboration Group
;
Gerarda Scaglione
Membro del Collaboration Group
;
Alessandra Di Vincenzo
Membro del Collaboration Group
;
Roberto Manfredini
Membro del Collaboration Group
;
Alfredo De Giorgi
Membro del Collaboration Group
;
2023

Abstract

Background: Mechanisms of myocardial ischemia in obstructive and non-obstructive coronary artery disease (CAD), and the interplay between clinical, functional, biological and psycho-social features, are still far to be fully elucidated. Objectives: To develop a machine-learning (ML) model for the supervised prediction of obstructive versus non-obstructive CAD. Methods: From the EVA study, we analysed adults hospitalized for IHD undergoing conventional coronary angiography (CCA). Non-obstructive CAD was defined by a stenosis < 50% in one or more vessels. Baseline clinical and psycho-socio-cultural characteristics were used for computing a Rockwood and Mitnitski frailty index, and a gender score according to GENESIS-PRAXY methodology. Serum concentration of inflammatory cytokines was measured with a multiplex flow cytometry assay. Through an XGBoost classifier combined with an explainable artificial intelligence tool (SHAP), we identified the most influential features in discriminating obstructive versus non-obstructive CAD. Results: Among the overall EVA cohort (n = 509), 311 individuals (mean age 67 ± 11 years, 38% females; 67% obstructive CAD) with complete data were analysed. The ML-based model (83% accuracy and 87% precision) showed that while obstructive CAD was associated with higher frailty index, older age and a cytokine signature characterized by IL-1β, IL-12p70 and IL-33, non-obstructive CAD was associated with a higher gender score (i.e., social characteristics traditionally ascribed to women) and with a cytokine signature characterized by IL-18, IL-8, IL-23. Conclusions: Integrating clinical, biological, and psycho-social features, we have optimized a sex- and gender-unbiased model that discriminates obstructive and non-obstructive CAD. Further mechanistic studies will shed light on the biological plausibility of these associations. Clinical trial registration: NCT02737982.
2023
Raparelli, Valeria; Romiti, Giulio Francesco; Di Teodoro, Giulia; Seccia, Ruggiero; Tanzilli, Gaetano; Viceconte, Nicola; Marrapodi, Ramona; Flego, Davide; Corica, Bernadette; Cangemi, Roberto; Pilote, Louise; Basili, Stefania; Proietti, Marco; Palagi, Laura; Lucia, Stefanini; Tiberti, Claudio; Panimolle, Federica; Isidori, Andrea; Giannetta, Elisa; Mary Anna Venneri, ; Napoleone, Laura; Novo, Marta; Quattrino, Silvia; Ceccarelli, Simona; Anastasiadou, Eleni; Megiorni, Francesca; Marchese, Cinzia; Mangieri, Enrico; Tanzilli, Gaetano; Viceconte, Nicola; Barillà, Francesco; Gaudio, Carlo; Paravati, Vincenzo; Tellan, Guglielmo; Ettorre, Evaristo; Servello, Adriana; Miraldi, Fabio; Moretti, Andrea; Tanzilli, Alessandra; Mazzonna, Piergiovanni; Suleyman Al Kindy, ; Iorio, Riccardo; Martina Di Iorio, ; Petriello, Gennaro; Gioffrè, Laura; Indolfi, Eleonora; Pero, Gaetano; Cocco, Nino; Iannetta, Loredana; Giannuzzi, Sara; Centaro, Emilio; Sonia Cristina Sergi, ; Pignatelli, Pasquale; Amoroso, Daria; Bartimoccia, Simona; Minisola, Salvatore; Morelli, Sergio; Fraioli, Antonio; Nocchi, Silvia; Fontana, Mario; Toriello, Filippo; Ruscio, Eleonora; Todisco, Tommaso; Sperduti, Nicolò; Santangelo, Giuseppe; Visioli, Giacomo; Vano, Marco; Borgi, Marco; Ludovica Maria Antonini, ; Robuffo, Silvia; Tucci, Claudia; Rossoni, Agostino; Spugnardi, Valeria; Vernile, Annarita; Santoliquido, Mariateresa; Santori, Verdiana; Tosti, Giulia; Recchia, Fabrizio; Morricone, Francesco; Scacciavillani, Roberto; Lipari, Alice; Zito, Andrea; Testa, Floriana; Ricci, Giulia; Vellucci, Ilaria; Vincenti, Marianna; Pietropaolo, Silvia; Scala, Camilla; Rubini, Nicolò; Tomassi, Marta; Rozzi, Gloria; Santomenna, Floriana; Cantelmi, Claudio; Costanzo, Giacomo; Rumbolà, Lucas; Giarrizzo, Salvatore; Sapia, Carlotta; Scotti, Biagio; Talerico, Giovanni; Toni, Danilo; Falcou, Anne; Kaur, Amanpreet; Behlouli, Hassan; Anna Rita Vestri, ; Ferroni, Patrizia; Crescioli, Clara; Antinozzi, Cristina; Francesca Serena Pignataro, ; Bellini, Tiziana; Zuliani, Giovanni; Passaro, Angelina; Brombo, Gloria; Cutini, Andrea; Capatti, Eleonora; DALLA NORA, Edoardo; DI VECE, Francesca; D’Amuri, Andrea; Romagnoli, Tommaso; Polastri, Michele; Violi, Alessandra; Fortunato, Valeria; Bella, Alessandro; Greco, Salvatore; Spaggiari, Riccardo; Scaglione, Gerarda; Di Vincenzo, Alessandra; Manfredini, Roberto; DE GIORGI, Alfredo; Carnevale, Roberto; Carlo Catalano, Cristina Nocella.; Carbone, Iacopo; Galea, Nicola; Suppa, Marianna; Rosa, Antonello; Galardo, Gioacchino; Alessandroni, Maria; Coppola, Alessandro; Palladino, Mariangela; Illuminati, Giulio; Consorti, Fabrizio; Mariani, Paola; Neri, Fabrizio; Salis, Paolo; Segatori, Antonio; Tellini, Laurent; Costabile, Gianluca
File in questo prodotto:
File Dimensione Formato  
s00392-023-02193-5.pdf

accesso aperto

Descrizione: versione editoriale
Tipologia: Full text (versione editoriale)
Licenza: Creative commons
Dimensione 2.89 MB
Formato Adobe PDF
2.89 MB Adobe PDF Visualizza/Apri

I documenti in SFERA sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11392/2507671
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 2
social impact