1
|
Mechanical dispersion of left ventricle and left atrial reservoir strain are both superior to global longitudinal strain to predict exercise capacity in heart failure with preserved ejection fraction. Eur Heart J Cardiovasc Imaging 2022. [DOI: 10.1093/ehjci/jeab289.077] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Abstract
Funding Acknowledgements
Type of funding sources: Public hospital(s). Main funding source(s): Fundação Adib Jatene
Background/Introduction:
Peak oxygen uptake (peak VO2) measures cardiovascular fitness and is a valuable diagnostic and prognostic marker in patients with heart failure with preserved ejection fraction (HFpEF). Measurement of peak VO2, however, requires specialized equipment and expert supervision, limiting its routine use by practicing clinicians.
Strain curves obtained by speckle tracking echocardiography (STE) can provide different parameters of myocardial mechanics such as the Global Longitudinal Strain (GLS), which is the most robust STE feature for clinical practice.
Notwithstanding, there is conflicting data on whether the GLS is associated with peak VO2 in HFpEF subjects.
Moreover, few studies have addressed the relationship between peak VO2 and other interesting deformation parameters such as the left atrial (LA) reservoir strain or the left ventricular mechanical dispersion (MD).
Purpose
The present study aimed to examine the utility of the myocardial mechanics as assessed by STE in predicting peak VO2 in patients with HFpEF.
Methods
From an ongoing prospective cohort of 189 subjects, we sampled subjects with different HFpEF stages. All patients underwent cardiopulmonary exercise testing (CPX) and a 2D-STE (LV GLS, MD, LA reservoir strain, LA conduit strain, and LA contraction strain) obtained by a blinded examinator. The missing data was handled by complete case analysis approach. We excluded subjects who had atrial fibrillation/flutter, severe COPD, STE with poor tracking quality, CPX with respiratory exchange rate (RER) < 1.
The Spearman"s correlation was calculated, and the 95% CI were estimated.
Finally, an estimative of the STE features importance to predict peak VO2 < 20mL/Kg/min was done using the function "xgb.importance()" from machine learning model XGBoost in R software. XGBoost is a variant of Gradient Boosting Method that uses ensembles of decision trees.
Results
We obtained 74 subjects (23 without evidence of heart disease, 23 with pre-heart failure and 28 with HFpEF). The MD presented the highest correlation with peak VO2 (Rho=-0.48; p-value < 0.001) followed by LA reservoir strain (Rho = 0.40; p-value < 0.001), LA conduit strain (Rho= –0.36; p-value < 0.001) and LA contraction (Rho= –0.30 p-value < 0.004) as shown in Figure 1. However, no correlation was found between GLS and peak VO2 (Rho= –0.07 p-value < 0.5) (Figure 2A).
The feature importance score (Figure 2B) showed the MD as the best relative contribution for VO2 prediction (gain= 0.34) superior to LA reservoir strain (gain = 0.25). GLS presented contribution (gain = 20) superior to LA conduit strain (gain =10) and LA contraction strain (gain = 0.08).
Conclusion
Left ventricular mechanical dispersion and left atrial reservoir strain obtained with STE were better predictors of peak VO2 than GLS in patients with different HFpEF stages and may be helpful in risk stratification and diagnosis. Abstract Figure 1 Abstract Figure 2
Collapse
|
2
|
P3426Machine learning for medical decision support in a first attendance ambulatory of a tertiary care cardiologic hospital. Eur Heart J 2019. [DOI: 10.1093/eurheartj/ehz745.0300] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
Abstract
Introduction
Cardiovascular disease is an expensive public health problem. Establish the right level of healthcare attention for each patient in a high-demand system is a complex task, and in this scenario, the development of computational methods to support medical decisions has shown to be quite promising.
Purpose
Define Machine Learning (ML) algorithms to support medical decisions in a first attendance ambulatory of a tertiary cardiology hospital.
Methods
A prospective observational study was performed in 336 patients (58±13 years and 49.4% male), obtaining clinical and ECG/VCG data. A follow up of 15 months was performed in order to access MACE, PCI, Cardiac Surgery and evidence of Severe Cardiac Disease. From twenty-five initial features, running the ML K-means Clustering algorithm, we identify which ones to use and the optimal number of Clusters. Once defined the Clusters the data were labeled, and then the clusters compared with field data (outcomes) and by Kaplan Meyer curves. The labeled data were also run by a Gradient Boosting algorithm in order to define a Predictor for future use in medical decision support.
Results
The best result, with well-defined Clusters, was obtained with the combination 5 Clusters and 8 specific Features, and the follow-up data has matched the Cluster classification as shown in the Table. Kaplan Meyer curves corroborated these finding with statistically significant differences between the Clusters: Log-rank test (p<0.001). Predictor algorithm, trained by the labeled data, presented an average precision of 95% (CI 95%; 91–100%).
Clustering Outcomes vs Follow-up results Cluster Patients Features Follow-up 15 months results Age BMI Previous Cardiac Previous Previous Diabetes** SM QRS_T QRS_T_loop Severe Heart Outcome (year)* (kg/m2)* Surgery** MI** PCI** angle* index* Disease* (%) 1 96 46±12 28.3±5.4 0 0.03 0.02 0 60±34 0.31±0.61 0.26 4.2% 2 60 61±12 29.6±5.5 0 0.25 0 1 97±45 0.41±1.32 0.57 20.0% 3 34 64±11 27.6±3.8 1 0.59 0.35 0.5 118±43 -0.11±1.22 0.72 35.3% 4 114 64±9 25.4±4.0 0 0.21 0 0 101±41 0.48±0.98 0.38 12.3% 5 32 50±10 28.7±5.1 0 0.88 1 0.47 82±34 0.52±0.69 0.81 50.0% *Mean ± sd; **yes = 1; no = 0.
Conclusion
The defined Predictor, using eight simple, quick and easy to get Features (clinical and ECG/VCG), shows excellent performance to classify patients who require tertiary cardiovascular healthcare attention.
Collapse
|