Abstract 13915: Unsupervised Machine Learning Algorithm Identifies People From the General Population at Risk of Heart Failure Based on Speckle Tracking Patterns: The Copenhagen City Heart Study

• Published in: Circulation (New York, N.Y.) Vol. 144; no. Suppl_1; p. A13915
• Main Authors: Simonsen, Jakob Oeystein, Skaarup, Kristoffer G, Modin, Daniel, Djernæs, Kasper, Lassen, Mats, Johansen, Niklas D, Martinez, Sergio S, Claggett, Brian L, Marott, Jacob, Jorgensen, Peter G, Jensen, Gorm, Schnohr, Peter, Mogelvang, Rasmus, Biering-Sørensen, Tor
• Format: Journal Article
• Language: English
• Published: Lippincott Williams & Wilkins 16.11.2021
• ISSN: 0009-7322; 1524-4539
• DOI: 10.1161/circ.144.suppl_1.13915

BackgroundPeak global longitudinal strain (Peak-GLS) is recognized as a powerful predictor of heart failure (HF). However, the entire strain curve remain undiscovered and therefore important prognostic information regarding HF might be lost. HypothesisWe hypothesized that analysis of the strain curve using unsupervised machine learning (uML) would reveal novel ventricular deformation patterns capable of predicting incident HF independently of Peak-GLS. MethodsLongitudinal strain curves from 3,767 subjects from the general population without prevalent HF were analyzed using uML. ResultsMean age was 56 years and 43% were male. During a median follow-up of 5.3 years, 94 subjects (2.5%) developed HF. The uML algorithm generated a hierarchical clustering tree (HCT)(Figure 1a) resulting in 9 different clusters with mean strain curves (figure 1b and 1c). Figure 1a summarizes the mean age, IRHF and number of subjects in each cluster. In multivariable Cox regression cluster 3 was significantly associated with reduced incidence of HF when compared to cluster 2 [HR 0.13, 95%CI0.04;0.41, P<0.001]. Cluster 4 was also significantly associated with reduced incidence of HF compared to cluster 2 [HR 0.21, 95%CI0.08;0.57, P=0.002]. Cluster 2 was associated with increased incidence of HF compared to cluster 3 and 4 even though cluster 2 displayed healthier clinical baseline characteristics as well as higher EF and Peak-GLS. The mean strain curve of cluster 2 had an increased absolute peak value, more rapid decline during systole, faster increase during diastole and a larger diastolic curvature compared to the mean strain curves of cluster 3 and cluster 4. ConclusionuML was capable of identifying a cluster (cluster 2) exhibiting a deformation pattern associated with increased risk of HF despite having higher EF and peak-GLS. The deformation patterns of cluster 2 was characterized by a faster contraction, faster relaxation and a higher deacceleration after early filling.