Machine Learning Adds to Clinical and CAC Assessments in Predicting 10-Year CHD and CVD Deaths

Nakanishi, Rine; Slomka, Piotr J.; Ríos, Richard; Betancur, Julián; Blaha, Michael J.; Nasir, Khurram; Miedema, Michael D.; Rumberger, John A.; Gransar, Heidi; Shaw, Leslee J.; Rozanski, Alan; Budoff, Matthew J.; Berman, Daniel S.

doi:10.1016/j.jcmg.2020.08.024

Cited by 71 publications

(65 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ML method is a form of artificial intelligence, and does not make a priori assumptions about causality, which distinguishes it from regression-based methods. ML had been widely used in the diagnosis and prognosis of CAD [ 12 , 16 , 17 ]. However, no studies developed a ML prediction model that can be used to predict all-cause mortality in CAD patients with AF.…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning (ML) is usually used to develop a predictive model to predict various results, and the computer algorithms were applied into ML to identify patterns in large databases with multiple variables [ 9 – 12 ]. Motwani et al developed a ML model for the prediction of 5-year all-cause mortality in patients with only CAD [ 9 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Liu

Jiang

Wei

et al. 2021

BMC Cardiovasc Disord

View full text Add to dashboard Cite

Background Machine learning (ML) can include more diverse and more complex variables to construct models. This study aimed to develop models based on ML methods to predict the all-cause mortality in coronary artery disease (CAD) patients with atrial fibrillation (AF). Methods A total of 2037 CAD patients with AF were included in this study. Three ML methods were used, including the regularization logistic regression, random forest, and support vector machines. The fivefold cross-validation was used to evaluate model performance. The performance was quantified by calculating the area under the curve (AUC) with 95% confidence intervals (CI), sensitivity, specificity, and accuracy. Results After univariate analysis, 24 variables with statistical differences were included into the models. The AUC of regularization logistic regression model, random forest model, and support vector machines model was 0.732 (95% CI 0.649–0.816), 0.728 (95% CI 0.642–0.813), and 0.712 (95% CI 0.630–0.794), respectively. The regularization logistic regression model presented the highest AUC value (0.732 vs 0.728 vs 0.712), specificity (0.699 vs 0.663 vs 0.668), and accuracy (0.936 vs 0.935 vs 0.935) among the three models. However, no statistical differences were observed in the receiver operating characteristic (ROC) curve of the three models (all P > 0.05). Conclusion Combining the performance of all aspects of the models, the regularization logistic regression model was recommended to be used in clinical practice.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Liu

Jiang

Wei

et al. 2021

BMC Cardiovasc Disord

View full text Add to dashboard Cite

show abstract

“…Although to date 18 F-NaF coronary PET research was predominantly focused on subjects with established disease, this imaging modality was also shown to identify active atherosclerotic disease across the entire spectrum of patients with subclinical, suspected, and established coronary artery disease. While in patients with advanced atherosclerosis 18 F-NaF PET clearly outperforms clinical characteristics and scores in risk stratification, it remains to be studied whether it can add to the alreadyrobust risk prediction in patients with the suspected disease [73]. Similar to coronary PET imaging, active calcification processes in valvular, great, and peripheral vessel disease would likely also benefit from advanced motion correction techniques and novel uptake measures.…”

Section: Discussionmentioning

confidence: 99%

Advances in Quantitative Analysis of ¹⁸F-Sodium Fluoride Coronary Imaging

2021

Self Cite

View full text Add to dashboard Cite

18F-sodium fluoride (18F-NaF) positron emission tomography (PET) has emerged as a promising noninvasive imaging tool for the assessment of active calcification processes in coronary artery disease. 18F-NaF uptake colocalizes to high-risk and ruptured atherosclerotic plaques. Most recently, 18F-NaF coronary uptake was shown to be a robust and independent predictor of myocardial infarction in patients with advanced coronary artery disease. In this review, we provide an overview of the advances in coronary 18F-NaF imaging. In particular, we discuss the recently developed and validated motion correction techniques which address heart contractions, tidal breathing, and patient repositioning during the prolonged PET acquisitions. Additionally, we discuss a novel quantification approach—the coronary microcalcification activity (which has been inspired by the widely employed method in oncology total active tumor volume measurement). This new method provides a single number encompassing 18F-NaF activity within the entire coronary vasculature rather than just information regarding a single area of most intense tracer uptake.

show abstract

“…It uses information that can be easily provided, such as age, sex, and pre-hospitalize diagnosis. Previous scoring systems [4,11,15] , including a recently reported deep learning model [29] , require laboratory or radiographic ndings as the main variables. Although such models can be helpful in fully equipped medical facilities, they initially consume a certain amount of medical resources and time.…”

Section: Discussionmentioning

confidence: 99%

Development and Validation of a Risk Score for Predicting 1-Year Mortality Risk of STEMI Based on a Nationwide Cohort in China

Chen

Che

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundA risk assessment for identifying long-term risk of post-discharge mortality in Chinese STEMI patients remains a concern. The aim of this study is to establish a bedside available risk scoring system for predicting 1-year mortality risk among Chinese STEMI patients. Methods STEMI patients(n=12611) were enrolled from the China STEMI Care Project Phase 2(CSCAP-2) collected between 2015 and 2016. Confounding bias was controlled using propensity score matching. Epidemiological, clinical, laboratory, and imaging variables, treatment strategy and medicine records were screened using extreme gradient boosting and nomogram according to the hazard ratio of Cox regression analysis to construct a predictive score. A validation cohort included 7342 patients collected in 2017 from CSCAP-2 was analyzed using receiver ROC and expectation (E)/observation (O) ratio to validate the risk scoring system. Results From 39 potential predictors, 8 variables were independent predictive factor and were included in the risk score: Killip class, early reperfusion strategy, Non-PCI intraoperative anticoagulants, heart rate, gender, age, anterior-wall myocardial infarction (AWMI) and inferior-wall myocardial infarction (IWMI). The new model demonstrated an excellent discrimination and calibration. The c-statistic and E/O ratio were 0.87(95%CI, 0.80-0.93) and 1.14(95%CI, 0.93-1.39) in the train set, 0.88 (95%CI, 0.78-0.96) and 1.15(95%CI, 0.85-1.56) in the test set, meanwhile, 0.89(95%CI, 0.82-0.95) and 1.00(95%CI, 0.81-1.23) in the validation cohort. The score has better sensitivity than the GRACE score and can recognize risk stratification among STEMI patients (P<0.001).Conclusions We developed a risk scoring system for predicting 1-year mortality risk of STEMI in a large Chinese population. The new score is easy-to-use and demonstrating a good discriminatory accuracy in predicting both short-term and long-term mortality risk in Chinese patients with STEMI.

show abstract

Machine Learning Adds to Clinical and CAC Assessments in Predicting 10-Year CHD and CVD Deaths

Cited by 71 publications

References 28 publications

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Advances in Quantitative Analysis of ¹⁸F-Sodium Fluoride Coronary Imaging

Development and Validation of a Risk Score for Predicting 1-Year Mortality Risk of STEMI Based on a Nationwide Cohort in China

Contact Info

Product

Resources

About

Machine Learning Adds to Clinical and CAC Assessments in Predicting 10-Year CHD and CVD Deaths

Cited by 71 publications

References 28 publications

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Prediction of all-cause mortality in coronary artery disease patients with atrial fibrillation based on machine learning models

Advances in Quantitative Analysis of 18F-Sodium Fluoride Coronary Imaging

Development and Validation of a Risk Score for Predicting 1-Year Mortality Risk of STEMI Based on a Nationwide Cohort in China

Contact Info

Product

Resources

About

Advances in Quantitative Analysis of ¹⁸F-Sodium Fluoride Coronary Imaging