A machine-learning based bio-psycho-social model for the prediction of non-obstructive and obstructive coronary artery disease
Valeria Raparelli, Giulio Francesco Romiti, Giulia Di Teodoro, Ruggiero Seccia, Gaetano Tanzilli, Nicola Viceconte, Ramona Marrapodi, Davide Flego, Bernadette Corica, Roberto Cangemi, Louise Pilote, Stefania Basili, Marco Proietti, Laura Palagi, Lucia Stefanini, EVA Investigators, Claudio Tiberti, Federica Panimolle, Andrea Isidori, Elisa Giannetta, Mary Anna Venneri, Laura Napoleone, Marta Novo, Silvia Quattrino, Simona Ceccarelli, Eleni Anastasiadou, Francesca Megiorni, Cinzia Marchese, Enrico Mangieri, Gaetano Tanzilli, Nicola Viceconte, Francesco Barillà, Carlo Gaudio, Vincenzo Paravati, Guglielmo Tellan, Evaristo Ettorre, Adriana Servello, Fabio Miraldi, Andréa Moretti, Alessandra Tanzilli, Piergiovanni Mazzonna, Suleyman Al Kindy, Riccardo Iorio, Martina Di Iorio, Gennaro Petriello, L Gioffrè, Eleonora Indolfi, Gaetano Pero, Nino Cocco, Loredana Iannetta, Sara Giannuzzi, Emilio Centaro, Sonia Cristina Sergi, Pasquale Pignatelli, Daria Amoroso, Simona Bartimoccia, Salvatore Minisola, Sergio Morelli, Antonio Fraioli, Silvia Nocchi, Mario Fontana, Filippo Toriello, Eleonora Ruscio, Tommaso Todisco, Nicolò Sperduti, Giuseppe Santangelo, Giacomo Visioli, Marco Vano, Marco Borgi, Ludovica Maria Antonini, Silvia Robuffo, Claudia Tucci, Agostino Rossoni, Valeria Spugnardi, A Vernile, Mariateresa Santoliquido, Verdiana Santori, Giulia Tosti, Fabrizio Recchia, Francesco Morricone, Roberto Scacciavillani, Alice Lipari, Andrea Zito, Floriana Testa, Giulia Ricci, Ilaria Vellucci, Marianna Vincenti, Silvia Pietropaolo, Camilla Scala, Nicolò Rubini, Marta Tomassi, Gloria Rozzi, Floriana Santomenna, Claudio Cantelmi, Giacomo Costanzo, Lucas Rumbolà, Salvatore Giarrizzo, Carlotta Sapia, Biagio Scotti, Giovanni Talerico
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.