It’s Time to Add Electrocardiography and Echocardiography to CVD Risk Prediction Models: Results from a Prospective Cohort Study

Li, Zhao; Yang, Yiqing; Zheng, Liqiang; Sun, Guozhe; Guo, Xiaofan; YingXian, Sun

doi:10.2147/rmhp.s337466

Cited by 4 publications

(4 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These variables are also reportedly among the top predictors in other large-scale studies. ( 31 ) For CT variables, markers from coronary artery calcium (CAC) scans were consistently among the top predictors, adding to the growing evidence in the literature about the importance of CAC. Abdominal aortic calcium variables such as the number and size of lesions of the abdominal aorta and common iliac aorta are also among the top 30–50 predictors.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Utility of multimodal longitudinal imaging data for dynamic prediction of cardiovascular and renal disease: the CARDIA study

Nguyen,

Vasconcellos,

Keck

et al. 2024

Front. Radiol.

View full text Add to dashboard Cite

BackgroundMedical examinations contain repeatedly measured data from multiple visits, including imaging variables collected from different modalities. However, the utility of such data for the prediction of time-to-event is unknown, and only a fraction of the data is typically used for risk prediction. We hypothesized that multimodal longitudinal imaging data could improve dynamic disease prognosis of cardiovascular and renal disease (CVRD).MethodsIn a multi-centered cohort of 5,114 CARDIA participants, we included 166 longitudinal imaging variables from five imaging modalities: Echocardiography (Echo), Cardiac and Abdominal Computed Tomography (CT), Dual-Energy x-ray Absorptiometry (DEXA), Brain Magnetic Resonance Imaging (MRI) collected from young adulthood to mid-life over 30 years (1985–2016) to perform dynamic survival analysis of CVRD events using machine learning dynamic survival analysis (Dynamic-DeepHit, LTRCforest, and Extended Cox for Time-varying Covariates). Risk probabilities were continuously updated as new data were collected. Model performance was assessed using integrated AUC and C-index and compared to traditional risk factors.ResultsLongitudinal imaging data, even when being irregularly collected with high missing rates, improved CVRD dynamic prediction (0.03 in integrated AUC, up to 0.05 in C-index compared to traditional risk factors; best model's C-index = 0.80–0.83 up to 20 years from baseline) from young adulthood followed up to midlife. Among imaging variables, Echo and CT variables contributed significantly to improved risk estimation. Echo measured in early adulthood predicted midlife CVRD risks almost as well as Echo measured 10–15 years later (0.01 C-index difference). The most recent CT exam provided the most accurate prediction for short-term risk estimation. Brain MRI markers provided additional information from cardiac Echo and CT variables that led to a slightly improved prediction.ConclusionsLongitudinal multimodal imaging data readily collected from follow-up exams can improve CVRD dynamic prediction. Echocardiography measured early can provide a good long-term risk estimation, while CT/calcium scoring variables carry atherosclerotic signatures that benefit more immediate risk assessment starting in middle-age.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Variable importance ranking (top 20).These variables are also reportedly among the top predictors in other large-scale studies (31). For CT variables, markers from coronary artery calcium (CAC) scans were consistently among the top predictors, adding to the growing evidence in the literature about the importance of CAC.…”

mentioning

confidence: 91%

Utility of multimodal longitudinal imaging data for dynamic prediction of cardiovascular and renal disease: the CARDIA study

Nguyen,

Vasconcellos,

Keck

et al. 2024

Front. Radiol.

View full text Add to dashboard Cite

show abstract

“…The cohort was from the Northeast China Rural Cardiovascular Health Study (NCRCHS), and that study’s design, as well as inclusion and exclusion criteria, were explained in our previous work [ 5 ]. In brief, a total of 11,956 participants aged ≥ 35 years old were recruited from Dawa, Zhangwu, and Liaoyang counties in Liaoning province between 2012 and 2013.…”

Section: Methodsmentioning

confidence: 99%

Interventricular Septum Thickness for the Prediction of Coronary Heart Disease and Myocardial Infarction in Hypertension Population: A Prospective Study

Yang

Zhao

Guo

et al. 2022

JCM

Self Cite

View full text Add to dashboard Cite

The aim of the present study was to evaluate the prognostic value of interventricular septum thickness (IVSd) on the incidence of cardiovascular diseases. Based on the general population in Northeast China, 10,349 participants were successfully followed up for echocardiography over a median follow-up time of 4.66 years, among which 4801 were hypertensive. Coronary heart disease (CHD) and myocardial infarction (MI) incidence were followed up. Cox proportional hazards models were used to estimate the association of the baseline IVSd with adverse outcomes. IVS hypertrophy increased incident rates of CHD and MI compared with normal IVSd in the overall population and in the female sex-stratification group. In males, IVS hypertrophy had parallel increase rates of CHD (all p < 0.05). Kaplan–Meier analysis showed that IVS hypertrophy could predict CHD and MI incidence and CHD-free and MI-free survival. Multivariable Cox analysis revealed that IVS hypertrophy was correlated with CHD incidence (HR = 1.155, 95% CI = 1.155–2.861, p = 0.01) and MI incidence (HR = 2.410, 95% CI = 1.303–4.458, p = 0.005). In women, IVS hypertrophy was independently associated with CHD and MI incidence (all p < 0.05). Our prospective cohort study illustrated that IVS hypertrophy detected by echocardiography has a prognostic significance for CHD and MI. Therefore, the early detection of IVSd should be conducted to avoid adverse outcomes in further clinical practice.

show abstract

“…These variables are also reportedly among the top predictors in other largescale studies. 31 For CT variables, markers from coronary artery calcium (CAC) scans were consistently among the top predictors, adding to the growing evidence in the literature about the importance of CAC. Abdominal aortic calcium variables such as the number and size of lesions of the abdominal aorta and common iliac aorta are also among the top 30-50 predictors.…”

Section: Importance Of Imaging Subsetsmentioning

confidence: 99%

Utility of Multimodal Longitudinal Imaging Data for Dynamic Prediction of Cardiovascular and Renal Disease: The CARDIA Study

Nguyen

Vasconcellos

Keck

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Medical examinations contain repeatedly measured data from multiple visits, including imaging variables collected from different modalities. However, the utility of such data for the prediction of time-to-event is unknown, and only a fraction of the data is typically used for risk prediction. We hypothesized that multimodal longitudinal imaging data could improve dynamic disease prognosis of cardiovascular and renal disease (CVRD). Methods: In a multi-centered cohort of 5114 CARDIA participants, we included 166 longitudinal imaging variables from five imaging modalities: Echocardiography (Echo), Cardiac and Abdominal Computed Tomography (CT), Dual-Energy X-ray Absorptiometry (DEXA), Brain Magnetic Resonance Imaging (MRI) collected from young adulthood to mid-life over 30 years (1985-2016) to perform dynamic survival analysis of CVRD events using machine learning dynamic survival analysis (Dynamic-DeepHit, LTRCforest, and Extended Cox for Time-varying Covariates). Risk probabilities were continuously updated as new data were collected. Model performance was assessed using integrated AUC and C-index and compared to traditional risk factors. Results: Longitudinal imaging data, even when being irregularly collected with high missing rates, improved CVRD dynamic prediction (+0.03 integrated AUC gain, up to 0.05 C-index gain compared to traditional risk factors) from young adulthood followed up to midlife. Among imaging variables, Echo and CT variables contributed significantly to improved risk estimation. Echo measured in early adulthood predicted midlife CVRD risks almost as well as Echo measured 10-15 years later (0.01 C-index difference). The most recent CT exam provided the most accurate prediction for short-term risk estimation. Brain MRI markers provided additional information from cardiac Echo and CT variables that led to a slightly improved prediction. Conclusions: Longitudinal multimodal imaging data readily collected from follow-up exams can improve CVRD dynamic prediction. Echocardiography measured early can provide a good long-term risk estimation, while CT/calcium scoring variables carry atherosclerotic signatures that benefit more immediate risk assessment starting in middle-age.

show abstract

It’s Time to Add Electrocardiography and Echocardiography to CVD Risk Prediction Models: Results from a Prospective Cohort Study

Cited by 4 publications

References 62 publications

Utility of multimodal longitudinal imaging data for dynamic prediction of cardiovascular and renal disease: the CARDIA study

Utility of multimodal longitudinal imaging data for dynamic prediction of cardiovascular and renal disease: the CARDIA study

Interventricular Septum Thickness for the Prediction of Coronary Heart Disease and Myocardial Infarction in Hypertension Population: A Prospective Study

Utility of Multimodal Longitudinal Imaging Data for Dynamic Prediction of Cardiovascular and Renal Disease: The CARDIA Study

Contact Info

Product

Resources

About