A Profile of Candidate Causal Genes of Spontaneous Coronary Artery Dissection Identified Through Machine Learning

2020 ◽  
Author(s):  
Yang Sun ◽  
Lei Xiao ◽  
Yanghui Chen ◽  
Shiyang Li ◽  
Dong Hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Coronary Artery ◽  
Artery Dissection ◽  
Spontaneous Coronary Artery Dissection ◽  
Coronary Artery Dissection ◽  
Causal Genes

scholarly journals MACHINE LEARNING AND DEEP LEARNING TO PREDICT MORTALITY IN PATIENTS WITH SPONTANEOUS CORONARY ARTERY DISSECTION

2021 ◽  
Vol 77 (18) ◽  
pp. 3412
Author(s):  
Chayakrit Krittanawong ◽  
Anirudh Kumar ◽  
Mehmet Aydar ◽  
Zhen Wang ◽  
Matthew P. Stewart ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Coronary Artery ◽  
Artery Dissection ◽  
Spontaneous Coronary Artery Dissection ◽  
Coronary Artery Dissection

scholarly journals Machine learning and deep learning to predict mortality in patients with spontaneous coronary artery dissection

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Chayakrit Krittanawong ◽  
Hafeez Ul Hassan Virk ◽  
Anirudh Kumar ◽  
Mehmet Aydar ◽  
Zhen Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Logistic Regression ◽  
Deep Learning ◽  
Coronary Artery ◽  
Hospital Mortality ◽  
Deep Neural Network ◽  
Artery Dissection ◽  
Spontaneous Coronary Artery Dissection ◽  
Coronary Artery Dissection

AbstractMachine learning (ML) and deep learning (DL) can successfully predict high prevalence events in very large databases (big data), but the value of this methodology for risk prediction in smaller cohorts with uncommon diseases and infrequent events is uncertain. The clinical course of spontaneous coronary artery dissection (SCAD) is variable, and no reliable methods are available to predict mortality. Based on the hypothesis that machine learning (ML) and deep learning (DL) techniques could enhance the identification of patients at risk, we applied a deep neural network to information available in electronic health records (EHR) to predict in-hospital mortality in patients with SCAD. We extracted patient data from the EHR of an extensive urban health system and applied several ML and DL models using candidate clinical variables potentially associated with mortality. We partitioned the data into training and evaluation sets with cross-validation. We estimated model performance based on the area under the receiver-operator characteristics curve (AUC) and balanced accuracy. As sensitivity analyses, we examined results limited to cases with complete clinical information available. We identified 375 SCAD patients of which mortality during the index hospitalization was 11.5%. The best-performing DL algorithm identified in-hospital mortality with AUC 0.98 (95% CI 0.97–0.99), compared to other ML models (P < 0.0001). For prediction of mortality using ML models in patients with SCAD, the AUC ranged from 0.50 with the random forest method (95% CI 0.41–0.58) to 0.95 with the AdaBoost model (95% CI 0.93–0.96), with intermediate performance using logistic regression, decision tree, support vector machine, K-nearest neighbors, and extreme gradient boosting methods. A deep neural network model was associated with higher predictive accuracy and discriminative power than logistic regression or ML models for identification of patients with ACS due to SCAD prone to early mortality.

Percutaneous coronary intervention in spontaneous coronary artery dissection: a case-control study

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
D Kotecha ◽  
A.D.P.E Premawardhana ◽  
M Garcia-Guimaraes ◽  
D Pellegrini ◽  
A.D Wood ◽  
...  
Keyword(s):  
Coronary Artery ◽  
Case Control Study ◽  
Case Control ◽  
Artery Dissection ◽  
Funding Source ◽  
Complication Rates ◽  
Spontaneous Coronary Artery Dissection ◽  
Coronary Artery Dissection ◽  
Control Study ◽  
Reduced Flow

Abstract Background Spontaneous Coronary Artery Dissection (SCAD) is an important cause of acute coronary syndrome particularly in young-middle aged women. Revascularisation is challenging due to an underlying disrupted and friable coronary vessel wall leading to widely reported worse outcomes than for atherosclerotic coronary disease. Therefore, a conservative approach where possible is favoured however in some cases haemodynamic instability, ongoing ischaemia and reduced distal flow mandates consideration of revascularisation. Purpose To compare SCAD survivors managed with PCI or conservatively in terms of presentation characteristics, complications and long-term outcomes. Methodology and results 226 angiographically confirmed SCAD survivors (95% female,47±9.7yrs) who underwent PCI were compared in a case control study with two hundred and twenty-five angiographically confirmed SCAD survivors (92% female, 49±9.9yrs) who were conservatively managed. Patients were recruited from UK, Spanish and Dutch SCAD registries and both groups were well matched in terms of baseline demographics. Those treated with PCI were more likely to present with proximal SCAD (30.8% vs 7.6% P&lt;0.01) and ST elevation myocardial infarction (STEMI) or cardiac arrest with reduced flow (32.3% vs 6.3% P&lt;0.01). Intervention was performed with stents in 72.4%, plain old balloon angioplasty in 21.1% and wiring in 6.4% of cases and more often for multi-segment disease (40.8% vs 26.3% P&lt;0.01). In cases with initial reduced flow undergoing PCI an improvement in flow was seen in 83%. Analysis of UK PCI cases (n=144) reveal complications in 56 (38.8%). However, when assessed for significance defined by a reduction in flow in a proximal/mid vessel, stent extension into left main stem, iatrogenic dissection requiring PCI and CABG as a consequence of PCI only 13 cases (9%) met criteria. Iatrogenic dissection accounts for the majority (76.9%). SCAD lesion length was associated with presence of complications (P=0.025). There was a non-significant trend towards major adverse cardiovascular events (MACE) occurring more frequently in those undergoing PCI (18% vs 11% P=0.067) driven by revascularisation (5% vs 1% P=0.036). Median follow up was 2.7 years. Conclusions PCI in SCAD is often performed in higher risk patients; in those presenting with reduced flow, the majority demonstrate improvement. Importantly whilst overall complication rates were similar to those widely reported, clinically significant complications were low. Multivariate modelling will reveal factors associated with complications to aid future decision making in this challenging patient group. Funding Acknowledgement Type of funding source: Public grant(s) – National budget only. Main funding source(s): British Heart Foundation

Sign in / Sign up

Export Citation Format

Share Document