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

Jingyi Zheng; Yuexin Li; Nedret Billor; Mustafa I Ahmed; Yu-Hua Dean Fang; Betty Pat; Thomas S Denney; Louis J Dell'Italia

doi:10.3389/fcvm.2023.1112797

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

Front Cardiovasc Med. 2023 Apr 21:10:1112797. doi: 10.3389/fcvm.2023.1112797. eCollection 2023.

Authors

Jingyi Zheng¹, Yuexin Li¹, Nedret Billor¹, Mustafa I Ahmed², Yu-Hua Dean Fang³, Betty Pat^{2

4}, Thomas S Denney⁵, Louis J Dell'Italia^{2

4}

Affiliations

¹ Department of Mathematics and Statistics, Auburn University, Auburn, AL, United States.
² Division of Cardiovascular Disease, University of Alabama at Birmingham, Birmingham, AL, United States.
³ Department of Radiology, University of Alabama at Birmingham, Birmingham, AL, United States.
⁴ Birmingham Veterans Affairs Health Care System, Birmingham, AL, United States.
⁵ Department of Electrical and Computer Engineering, Samuel Ginn College of Engineering, Auburn University, Auburn, AL, United States.

Abstract

Background: Class 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).

Objective: Use regression and machine learning models to identify a combination of CMR LV remodeling and function parameters that predict LVEF < 50% after mitral valve surgery.

Methods: CMR 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.

Results: Thirteen 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.

Conclusions: These 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.

Keywords: LV circumferential strain rate; machine learning; mitral regurgitation (MR); post-surgical LVEF; predictive models.

Grants and funding

This work was supported by the National Heart, Lung, and Blood Institute and Specialized Centers of Clinically Oriented Research grant [P50HL077100 to L.J.D] in cardiac dysfunction; Department of Veteran Affairs for Merit Review grant [1CX000993-01 to L.J.D]; and National Institutes of Health Grant [P01 HL051952 to L.J.D]. No relationships to industry.