ISTH Congress Abstracts

Official abstracts site for the ISTH Congress

MENU 

A Machine-learning-Based Bio-psycho-Social Model for the Prediction of Non-obstructive and Obstructive Coronary Artery Disease

1Dept. Translational Medicine, University of Ferrara, Ferrara, Italy, 2IRCCS Istituti Clinici Scientifici Maugeri, Milan, Italy, 3Dept. Translational and Precision Medicine, Sapienza University of Rome, Rome, Italy, 4Dept. Computer Control and Management Engineering, Sapienza University of Rome, Rome, Italy, 5Dept. Clinical, Internal, Anesthesiology and Cardiovascular Sciences, Sapienza University of Rome, Rome, Italy

Abstract Number: PB0002

Meeting: ISTH 2021 Congress

Theme: Arterial Thromboembolism » Acute Coronary Syndromes

Background: Although cardiovascular disease is the leading cause of mortality in both females and males, women are more likely to have non-obstructive ischemic heart disease (IHD) than men. However, the underlying sex- and gender-specific mechanisms and differences in IHD manifestations are still not fully understood.

Aims: To develop an interpretable machine learning (ML) model to gain insight on the clinical, functional, biological and psychosocial features playing a major role in the supervised prediction of non-obstructive versus obstructive coronary artery disease (CAD).

Methods: From the EVA study, we analysed a consecutive unselected cohort of adults hospitalised for IHD undergoing coronary angiography. Non-obstructive CAD was defined by a coronary stenosis at the angiogram <50%. Baseline clinical and psycho-socio-cultural characteristics were used for computing a frailty index based on Rockwood and Mitnitsky model, and gender score according to GENESIS-PRAXY methodology. The serum concentration of inflammatory cytokines was measured with a multiplex flow cytometry assay. An XGBoost classifier combined to an explainable artificial intelligence tool (SHAP) was employed to identify 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) revealed that while obstructive CAD associated with a lower frailty index (i.e., lower physiological reserve), older age and a cytokine signature characterised by IL-1β, IL-12p70 and IL-33, non-obstructive CAD is more likely associated with higher gender score (i.e., social characteristics traditionally ascribed to women, regardless of biological sex) and with a cytokine signature characterised by IL-18, IL-8, IL-23.

Conclusions: Integrating clinical, biological and psychosocial features, we have optimised a sex- and gender-unbiased model that discriminates obstructive and non-obstructive CAD. Further mechanistic studies will shed light on the biological plausibility of the observed associations.

To cite this abstract in AMA style:

Raparelli V, Proietti M, Romiti GF, Seccia R, Di Teodoro G, Tanzilli G, Marrapodi R, Corica B, Flego D, Cangemi R, Palagi L, Basili S, Stefanini L. A Machine-learning-Based Bio-psycho-Social Model for the Prediction of Non-obstructive and Obstructive Coronary Artery Disease [abstract]. Res Pract Thromb Haemost. 2021; 5 (Suppl 1). https://abstracts.isth.org/abstract/a-machine-learning-based-bio-psycho-social-model-for-the-prediction-of-non-obstructive-and-obstructive-coronary-artery-disease/. Accessed September 24, 2021.

« Back to ISTH 2021 Congress

ISTH Congress Abstracts - https://abstracts.isth.org/abstract/a-machine-learning-based-bio-psycho-social-model-for-the-prediction-of-non-obstructive-and-obstructive-coronary-artery-disease/