Early Prediction of Left Ventricular Reverse Remodeling in First-Diagnosed Idiopathic Dilated Cardiomyopathy: A Comparison of Linear Model, Random Forest, and Extreme Gradient Boosting

Xie, Xinhua; Yang, Mingwei; Xie, Shan; Wu, Xiaoying; Jiang, Yuan; Liu, Zhaoyu; Zhao, Huiying; Chen, Yangxin; Zhang, Yuling; Wang, Jingfeng

doi:10.3389/fcvm.2021.684004

Cited by 8 publications

(11 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In previous studies, the combination of multiple parameters from clinical findings, imaging and circulating biomarkers has shown promising performance. Xie et al built an XGBoost model to predict LVRR in first‐diagnosed dilated cardiomyopathy, in which cystatin C, right ventricular end‐diastolic dimension measured by echocardiography, electrocardiogram, and HDL‐C were the most important features 27 . Other studies found HF duration, baseline LVEF, and QRS duration were associated with LVRR 5,8,9 …”

Section: Discussionmentioning

confidence: 99%

“…In our study, DCM patients with LVRR had a lower LV volume index and LVSV index at baseline, although LVEF was similar between the two groups. One possible reason was that a minor degree of LV dilation could reduce LV wall stress and neurohormonal activation, which can better trigger or amplify LVRR in DCM 27 . Recently, LVRI, a novel index, has been proposed to quantify LV remodelling and has proven helpful in differentiating cardiomyopathy phenotypes 33,34 .…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

The potential predictive value of cardiac mechanics for left ventricular reverse remodelling in dilated cardiomyopathy

Kan,

Fang,

et al. 2023

ESC Heart Failure

View full text Add to dashboard Cite

AimsLeft ventricular reverse remodelling (LVRR) is an important objective of optimal medical management for dilated cardiomyopathy (DCM) patients, as it is associated with favourable long‐term outcomes. Cardiac magnetic resonance (CMR) can comprehensively assess cardiac structure and function. We aimed to assess the CMR parameters at baseline and investigate independent variables to predict LVRR in DCM patients.Methods and resultsNighty‐eight initially diagnosed DCM patients who underwent CMR and echocardiography examinations at baseline were included. CMR parameters and feature tracking (FT) based left ventricular (LV) global strain (nStrain) and nStrain indexed to LV cardiac mass index (rStrain) were measured. The predictors of LVRR were determined by multivariate logistic regression analyses. Receiver operating characteristic (ROC) curves were used to evaluate the diagnostic performance of CMR parameters and were compared by the DeLong test. At a median follow‐up time of 9 [interquartile range, 7–12] months, 35 DCM patients (36%) achieved LVRR. The patients with LVRR had lower LV volume, mass, LGE extent and stroke volume index (LVSVi) and higher left ventricular remodelling index (LVRI), nStrains, rStrains, and peak systolic strain rate (PSSR) in the longitudinal direction and rStrains in the circumferential direction at baseline (all P < 0.05). In the multivariate logistic regression analyses, LVRI [per SD, odds ratio (OR) 1.79; 95% confidence interval (CI) 1.08–2.98; P = 0.024] and the ratio of global longitudinal peak strain (rGLPS) (per SD, OR 1.88; 95% CI 1.18–3.01; P = 0.008) were independent predictors of LVRR. The combination of LVSVi, LVRI, and rGLPS had a greater area under the curve (AUC) than the combination of LVSVi and LVRI (0.75 vs. 0.68), but not significantly (P = 0.09).ConclusionsPatients with LVRR had a lower LV volume index, lower LVSV index, lower LGE extent, higher LVRI, and preserved myocardial deformation in the longitudinal direction at baseline. LVRI and rGLPS at baseline were independent determinants of LVRR.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

The potential predictive value of cardiac mechanics for left ventricular reverse remodelling in dilated cardiomyopathy

Kan,

Fang,

et al. 2023

ESC Heart Failure

View full text Add to dashboard Cite

show abstract

“…Moreover, left ventricular reverse remodeling (LVRR) has the potential to play a role in the beneficial effects of S/V [14][15][16] . Specially, some previous studies have demonstrated a strong favorable effect conferred by S/V on LVRR 15,17,18 , meanwhile some have reported a positive association between LVRR and clinical outcomes of HF patients 19,20 .…”

Section: Introductionmentioning

confidence: 99%

Predicting hospital readmissions in patients receiving novel-dose Sacubitril/Valsartan therapy: A competing-risk, causal mediation analysis

Hou¹,

Hao²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: The effects of novel-dose Sacubitril/Valsartan (S/V) in patients with heart failure (HF) in the real world have not been adequately studied. We examined the risk for all-cause re-admission in the patients with HF taking novel-dose S/V and the possible mediator role of left ventricular reverse remodeling (LVRR). Methods and Results: There were 464 patients recruited from December 2017 to September 2021 in our hospital with a median follow-up of 660 days (range, 17-1494). Model 1 and 2 were developed based on the results of univariable competing risk analysis, least absolute shrinkage and selection operator approach, backward stepwise regression and multivariable competing risk analysis. The internal verification (data-splitting method) indicated that Model 1 had better discrimination, calibration, and clinical utility. The corresponding nomogram showed that patients aged 75 years and above or taking the lowest-dose S/V (≤50mg twice a day), or diagnosed with ventricular tachycardia, or valvular heart disease, or chronic obstructive pulmonary disease, or diabetes mellitus were at the highest risk of all-cause readmission. In the causal mediation analysis, LVRR was considered as a critical mediator that negatively affected the difference of novel-dose S/V in readmission. Conclusions: A significant association was detected between novel-dose S/V and all-cause readmission in HF patients, in part negatively mediated by LVRR. The web-based nomogram could provide individual prediction of all-cause readmission in HF patients receiving novel-dose S/V. The effects of different novel-dose S/V are still needed to be explored further in the future.

show abstract

“…Thus, machine learning models can identify unexpected predictors not accounted for by linear models and interactions that have prognostic value. With recursive feature elimination and repetitive testing, machine learning models are now being used in pilot analyses even in smaller data sets (9,10).…”

Section: Introductionmentioning

confidence: 99%

Understanding post-surgical decline in left ventricular function in primary mitral regurgitation using regression and machine learning models

Zheng

Billor

et al. 2023

Front. Cardiovasc. Med.

View full text Add to dashboard Cite

BackgroundClass I echocardiographic guidelines in primary mitral regurgitation (PMR) risks left ventricular ejection fraction (LVEF) < 50% after mitral valve surgery even with pre-surgical LVEF > 60%. There are no models predicting LVEF < 50% after surgery in the complex interplay of increased preload and facilitated ejection in PMR using cardiac magnetic resonance (CMR).ObjectiveUse regression and machine learning models to identify a combination of CMR LV remodeling and function parameters that predict LVEF < 50% after mitral valve surgery.MethodsCMR with tissue tagging was performed in 51 pre-surgery PMR patients (median CMR LVEF 64%), 49 asymptomatic (median CMR LVEF 63%), and age-matched controls (median CMR LVEF 64%). To predict post-surgery LVEF < 50%, least absolute shrinkage and selection operator (LASSO), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) were developed and validated in pre-surgery PMR patients. Recursive feature elimination and LASSO reduced the number of features and model complexity. Data was split and tested 100 times and models were evaluated via stratified cross validation to avoid overfitting. The final RF model was tested in asymptomatic PMR patients to predict post-surgical LVEF < 50% if they had gone to mitral valve surgery.ResultsThirteen pre-surgery PMR had LVEF < 50% after mitral valve surgery. In addition to LVEF (P = 0.005) and LVESD (P = 0.13), LV sphericity index (P = 0.047) and LV mid systolic circumferential strain rate (P = 0.024) were predictors of post-surgery LVEF < 50%. Using these four parameters, logistic regression achieved 77.92% classification accuracy while RF improved the accuracy to 86.17%. This final RF model was applied to asymptomatic PMR and predicted 14 (28.57%) out of 49 would have post-surgery LVEF < 50% if they had mitral valve surgery.ConclusionsThese preliminary findings call for a longitudinal study to determine whether LV sphericity index and circumferential strain rate, or other combination of parameters, accurately predict post-surgical LVEF in PMR.

show abstract

Early Prediction of Left Ventricular Reverse Remodeling in First-Diagnosed Idiopathic Dilated Cardiomyopathy: A Comparison of Linear Model, Random Forest, and Extreme Gradient Boosting

Cited by 8 publications

References 49 publications

The potential predictive value of cardiac mechanics for left ventricular reverse remodelling in dilated cardiomyopathy

The potential predictive value of cardiac mechanics for left ventricular reverse remodelling in dilated cardiomyopathy

Predicting hospital readmissions in patients receiving novel-dose Sacubitril/Valsartan therapy: A competing-risk, causal mediation analysis

Understanding post-surgical decline in left ventricular function in primary mitral regurgitation using regression and machine learning models

Contact Info

Product

Resources

About