Multi‐modality machine learning approach for risk stratification in heart failure with left ventricular ejection fraction ≤ 45%

Abstract

Aims Heart failure (HF) involves complex remodelling leading to electrical and mechanical dysfunction. We hypothesized that machine learning approaches incorporating data obtained from different investigative modalities including atrial and ventricular measurements from electrocardiography and echocardiography, blood inflammatory marker [neutrophil-to-lymphocyte ratio (NLR)], and prognostic nutritional index (PNI) will improve risk stratification for adverse outcomes in HF compared to logistic regression. Methods and results Consecutive Chinese patients referred to our centre for transthoracic echocardiography and subsequently diagnosed with HF, between 1 January 2010 and 31 December 2016, were included in this study. Two machine learning techniques, multilayer perceptron and multi-task learning, were compared with logistic regression for their ability to predict incident atrial fibrillation (AF), transient ischaemic attack (TIA)/stroke, and all-cause mortality. This study included 312 HF patients [mean age: 64 (55-73) years, 75% male]. There were 76 cases of new-onset AF, 62 cases of incident TIA/stroke, and 117 deaths during follow-up. Univariate analysis revealed that age, left atrial reservoir strain (LARS) and contractile strain (LACS) were significant predictors of new-onset AF. Age and smoking predicted incident stroke. Age, hypertension, type 2 diabetes mellitus, chronic kidney disease, mitral or aortic regurgitation, P-wave terminal force in V1, the presence of partial inter-atrial block, left atrial diameter, ejection fraction, global longitudinal strain, serum creatinine and albumin, high NLR, low PNI, and LARS and LACS predicted all-cause mortality. Machine learning techniques achieved better prediction performance than logistic regression. Conclusions Multi-modality assessment is important for risk stratification in HF. A machine learning approach provides additional value for improving outcome prediction.

Predictive value of H2FPEF score in patients with heart failure with preserved ejection fraction

“…This phenotypic coding helps introduce a better understanding of the risk factors, aetiology, pathophysiology, and clinical course of HFpEF and contributes to guiding targeted treatment, as is the case for HFrEF. 23 In the near future, treatment targeted to aetiology and co-morbidities may be the best choice in treatment of HFpEF patients.…”

“…introduced a clinical phenotypic classification of HFpEF, 22 which included the following: (i) vascular‐related HFpEF; (ii) cardiomyopathy‐related HFpEF; (iii) right heart‐ and pulmonary‐related HFpEF; (iv) valvular‐ and rhythm‐related HFpEF; and (v) extracardiac disease‐related HFpEF. This phenotypic coding helps introduce a better understanding of the risk factors, aetiology, pathophysiology, and clinical course of HFpEF and contributes to guiding targeted treatment, as is the case for HFrEF 23 . In the near future, treatment targeted to aetiology and co‐morbidities may be the best choice in treatment of HFpEF patients.…”

Multi‐parametric system for risk stratification in mitral regurgitation: A multi‐task Gaussian prediction approach

“…The major findings of this study are that a multi-parametric approach incorporating baseline comorbidity data, laboratory indices reflecting inflammatory and nutritional states, electrocardiographic P-wave and echocardiographic assessment can offer a moderate predictive value for mortality risk stratification. A machine learning approach using multi-task Gaussian process model performed significantly better than decision tree and logistic regression analyses 41 . Conduction delay along Bachmann's bundle between left and right atria leads to inter-atrial block.…”

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

“…Tse et al . 102 aimed at improving the risk stratification for adverse outcomes in heart failure, such as incident AF, transient ischaemic attack (TIA)/stroke, and all-cause mortality, while Wu et al . 103 focused on a more specific risk stratification model of young patients with hypertension.…”