Causal Models for the Result of Percutaneous Coronary Intervention in Coronary Chronic Total Occlusions

Background: Patients undergoing coronary angiography very frequently exhibit coronary chronic total occlusions (CTOs). Over the last decade, there has been an increasing acceptance of the percutaneous coronary interventions (PCI) in CTOs due to, among else, rising operator experience and advances in...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Applied sciences 2021-10, Vol.11 (19), p.9258
Hauptverfasser: Ganopoulou, Maria, Kangelidis, Ioannis, Sianos, Georgios, Angelis, Lefteris
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Background: Patients undergoing coronary angiography very frequently exhibit coronary chronic total occlusions (CTOs). Over the last decade, there has been an increasing acceptance of the percutaneous coronary interventions (PCI) in CTOs due to, among else, rising operator experience and advances in technology. This study is an effort to address the problem of identifying important factors related to the success or failure of the PCI. Methods: The analysis is based on the EuroCTO Registry, which is the largest database available worldwide, consisting of 164 variables and 29,995 cases for the period 2008–2018. The aim is to assess the dynamics of causal models and causal discovery, using observational data, in predicting the result of the PCI. Causal models use graph structure to assess the cause–effect relationships between variables. In this study, the constrained-based algorithm PC was employed. The focus was to find the local causal structure around the PCI result and use it as a feature selection tool for building a predictive model. Results: The model developed was compared with other modeling approaches from the literature, and it was found to perform equally well or better. Conclusions: The analysis showcased the potential of employing local causal structure in predictive model development.
ISSN:2076-3417
2076-3417
DOI:10.3390/app11199258