2022
DOI: 10.1016/j.atherosclerosis.2022.03.028
|View full text |Cite
|
Sign up to set email alerts
|

Prediction of 3-year all-cause and cardiovascular cause mortality in a prospective percutaneous coronary intervention registry: Machine learning model outperforms conventional clinical risk scores

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
5
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
7
1
1

Relationship

3
6

Authors

Journals

citations
Cited by 14 publications
(5 citation statements)
references
References 30 publications
0
5
0
Order By: Relevance
“…Paul Adrian Cȃlburean et al [19] utilized 140 clinical variables corresponding to 2,242 patients and trained a CatBoost model for all-cause mortality and CVD mortality prediction, 3 years after PCI. The CatBoost model achieved an AUROC score of 0.854 for all-cause mortality prediction and 0.886 for CVD mortality prediction [19]. Compared to the other prior studies, we have utilized a significantly larger patient cohort.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…Paul Adrian Cȃlburean et al [19] utilized 140 clinical variables corresponding to 2,242 patients and trained a CatBoost model for all-cause mortality and CVD mortality prediction, 3 years after PCI. The CatBoost model achieved an AUROC score of 0.854 for all-cause mortality prediction and 0.886 for CVD mortality prediction [19]. Compared to the other prior studies, we have utilized a significantly larger patient cohort.…”
Section: Discussionmentioning
confidence: 99%
“…The DNN model trained by Luan Tran et al reported an AUROC score of 0.88 [18]. Paul Adrian Cȃlburean et al [19] utilized 140 clinical variables corresponding to 2,242 patients and trained a CatBoost model for all-cause mortality and CVD mortality prediction, 3 years after PCI. The CatBoost model achieved an AUROC score of 0.854 for all-cause mortality prediction and 0.886 for CVD mortality prediction [19].…”
Section: Discussionmentioning
confidence: 99%
“…The study flowchart is illustrated in Figure 1 . The registry is accessible online at the website http://pci.cardio.ro/ , has been previously described ( Călburean et al, 2022 ), and is based on the criteria of Cardiology Audit and Registration Data Standards (CARDS) developed by the Department of Health and Children, European Society of Cardiology, Irish Cardiac Society, and the European Commission ( Flynn et al, 2005 ). The CARDS recommendations address data regarding demographics, relevant medical history and comorbid conditions, clinical status at hospital admission, PCI indication, affected and treated coronary artery segments, use of invasive diagnostic or therapeutic devices, procedural complications, and medical treatment during hospitalization and at discharge and in-hospital evolution.…”
Section: Methodsmentioning
confidence: 99%
“…However, due to its underlying mathematical complexity, ML models are difficult to interpret, being considered a black box [ 14 ]. In cardiovascular medicine, ML models can identify complex interactions among clinical variables and make an accurate event prediction [ 15 ]. The aim of our study was to identify potential inflammatory biomarkers with predictive capacity for post-TAVR event prediction from a wide panel of routine biomarkers by employing ML techniques.…”
Section: Introductionmentioning
confidence: 99%