Identifying novel phenotypes of elevated left ventricular end diastolic pressure using hierarchical clustering of features derived from electromechanical waveform data

Abstract

Introduction: Elevated left ventricular end diastolic pressure (LVEDP) is a consequence of compromised left ventricular compliance and an important measure of myocardial dysfunction. An algorithm was developed to predict elevated LVEDP utilizing electro-mechanical (EM) waveform features. We examined the hierarchical clustering of selected features developed from these EM waveforms in order to identify important patient subgroups and assess their possible prognostic significance.

Materials and methods: Patients presenting with cardiovascular symptoms (N = 396) underwent EM data collection and direct LVEDP measurement by left heart catheterization. LVEDP was classified as non-elevated ( ≤ 12 mmHg) or elevated (≥25 mmHg). The 30 most contributive features to the algorithm output were extracted from EM data and input to an unsupervised hierarchical clustering algorithm. The resultant dendrogram was divided into five clusters, and patient metadata overlaid.

Results: The cluster with highest LVEDP (cluster 1) was most dissimilar from the lowest LVEDP cluster (cluster 5) in both clustering and with respect to clinical characteristics. In contrast to the cluster demonstrating the highest percentage of elevated LVEDP patients, the lowest was predominantly non-elevated LVEDP, younger, lower BMI, and males with a higher rate of significant coronary artery disease (CAD). The next adjacent cluster (cluster 2) to that of the highest LVEDP (cluster 1) had the second lowest LVEDP of all clusters. Cluster 2 differed from Cluster 1 primarily based on features extracted from the electrical data, and those that quantified predictability and variability of the signal. There was a low predictability and high variability in the highest LVEDP cluster 1, and the opposite in adjacent cluster 2.

Conclusion: This analysis identified subgroups of patients with varying degrees of LVEDP elevation based on waveform features. An approach to stratify movement between clusters and possible progression of myocardial dysfunction may include changes in features that differentiate clusters; specifically, reductions in electrical signal predictability and increases in variability. Identification of phenotypes of myocardial dysfunction evidenced by elevated LVEDP and knowledge of factors promoting transition to clusters with higher levels of left ventricular filling pressures could permit early risk stratification and improve patient selection for novel therapeutic interventions.

Keywords: artificial intelligence; digital health; left ventricular filling pressures; machine learning; risk stratification.

Figure 1

Signal acquisition using the CorVista Capture, with the electrodes placed on the torso (electrode on the back not visible), and the PPG clip placed on the finger.

Figure 2

(A) Example OVG data in phase space, with coordinates from each bipolar channel (ORTH1, ORTH2, ORTH3) represented as a three-dimensional coordinate in that space, and (B) example PPG data in the time domain, containing both red and infrared time series.

Figure 3

(A) Dendrogram colored to identify each cluster, associated to a heatmap visualizing the magnitude of the feature values for each subject, and (B) colored dendrogram associated with the pairwise distance matrix across the dataset, with bold boxes defining each cluster, and dotted lines delineating between adjacent clusters.

Figure 4

The variability and lack of predictability feature values for cluster 2 (Green) and cluster 1 (Purple), with the mean of each feature for each cluster marked with dashed lines.