Logo

American Heart Association

  2
  0


Final ID: MDP1692

A Machine Learning-Based Novel Risk Score Model for Spontaneous Coronary Artery Dissection

Abstract Body (Do not enter title and authors here): Background
Spontaneous coronary artery dissection (SCAD) remains a poorly understood differential diagnosis of acute coronary syndrome (ACS). We aimed to develop a machine learning-based risk score model to predict in-hospital mortality in patients with SCAD.
Methods
The National Inpatient Sample (NIS) 2016-2020 database was used to identify all adult patients (≥18 years of age) with SCAD, identified using ICD-10 code I25.42. Relevant clinical characteristics and outcomes were extracted. The primary endpoint was in-hospital all-cause mortality. The dataset was randomly split into 3 subsets: training, validation, and testing, with a ratio of 0.7, 0.2, and 0.1, respectively. The risk score was generated using R software’s Autoscore package, which is a machine learning-based automatic clinical score generator, and performance was evaluated using the area under receiver-operative characteristics curve (AUC) with 95% confidence intervals (95%CI).
Results
Among the 8,260 SCAD patients identified [age 60.9±14.4 years, female 4,708 (57%)], there were 480 (5.8%) primary outcome events. Out of the top 20 covariates seen in the Parsimony plot, we used six for our risk score (0–100): age, comorbidity burden, cardiogenic shock, balloon pump, extracorporeal membrane oxygenation, and race (Figure 1A). The AUC for the derivation and validation cohorts was 0.862 (0.817–0.907) and 0.833 (0.788–0.879), respectively (Figures 1B and 1C).
Conclusion
We developed and internally validated a machine learning-based risk score model to predict outcomes in patients with SCAD with a high AUC of 0.833 (0.788–0.879). Risk score models guide decision-making, and future studies are needed for external validation of our findings.
  • Agrawal, Ankit  ( Cleveland Clinic , Cleveland , Ohio , United States )
  • Arockiam, Aro Daniela  ( Cleveland Clinic Foundation , Cleveland , Ohio , United States )
  • Bhagat, Umesh  ( Cleveland Clinic Foundation , Cleveland , Ohio , United States )
  • Haroun, Elio  ( Cleveland Clinic Foundation , Cleveland , Ohio , United States )
  • Majid, Muhammad  ( AdventHealth Florida , Sebri , Florida , United States )
  • Wang, Tom Kai Ming  ( Cleveland Clinic , Cleveland , Ohio , United States )
  • Author Disclosures:
    Ankit Agrawal: DO NOT have relevant financial relationships | Aro Daniela Arockiam: DO NOT have relevant financial relationships | umesh bhagat: No Answer | Elio Haroun: DO NOT have relevant financial relationships | Muhammad Majid: DO NOT have relevant financial relationships | Tom Kai Ming Wang: DO NOT have relevant financial relationships
Meeting Info:

Scientific Sessions 2024

2024

Chicago, Illinois

Session Info:

MINOCA and Endothelial Function in ACS

Monday, 11/18/2024 , 09:30AM - 10:55AM

Moderated Digital Poster Session

More abstracts on this topic:
Aggressive LDL cholesterol lowering post ACS with triple combination therapy: Insights from the multicentric LAI-REACT study

Puri Raman, Mahajan Kunal, Agarwala Rajeev, Gupta Ashu, Batra Aditya, Khan Aziz, Vijan Vinod, Sharma Jai Bharat, Himral Surender

A Rare Case of Sequential Impella Mechanical Failures due to Infective Endocarditis Vegetations

Sawalski Cathryn, Seu Michelle, Darki Amir

More abstracts from these authors:
Relationships between aortic valve area planimetry on four-dimensional cardiac computed tomography and survival following transcatheter aortic valve replacement

Arockiam Aro Daniela, Harb Serge, Popovic Zoran, Rodriguez L, Puri Rishi, Reed Grant, Krishnaswamy Amar, Griffin Brian, Kapadia Samir, Wang Tom Kai Ming, Dong Tiffany, Haroun Elio, El Dahdah Joseph, Agrawal Ankit, Khurana Rishabh, Saraswati Ushasi, Bhalla Jaideep, Paul Aritra

A Machine Learning-Based Novel Risk Score Model for Takotsubo Cardiomyopathy

Agrawal Ankit, Bhagat Umesh, Haroun Elio, Arockiam Aro Daniela, Majid Muhammad, Wang Tom Kai Ming

You have to be authorized to contact abstract author. Please, Login
Not Available