A streamlined, machine learning-derived approach to risk-stratification in heart failure patients with secondary tricuspid regurgitation. (3rd October 2022)

• Record Type: Journal Article
• Authors: Heitzinger, G; Spinka, G; Koschatko, S; Dannenberg, V; Halavina, K; Mascherbauer, K; Winter, M P; Strunk, G; Pavo, N; Kastl, S; Huelsmann, M; Rosenhek, R; Hengstenberg, C; Bartko, P E; Goliasch, G
• Is Part Of: European heart journal. Volume 43(2022)Supplement 2
• Publication Date: 2022-10-03
• Subjects: Cardiology -- Periodicals; Heart -- Diseases -- Periodicals; 616.12005
• DOI: 10.1093/eurheartj/ehac544.1654
• Languages: English
• ISSNs: 0195-668X

Abstract

Abstract: Background: Secondary tricuspid regurgitation (sTR) is the most frequent valvular heart disease and has significant impact on mortality. A high burden of comorbidities often worsens the already dismal prognosis of sTR, while tricuspid interventions remain underused and initiated too late. Objectives: To examine the most powerful predictors of all-cause mortality in moderate and severe sTR using machine learning techniques and to provide a streamlined approach to risk-stratification using readily available clinical, echocardiographic and laboratory parameters. Methods: This large-scale, long-term observational study included 3359 moderate and 1509 severe sTR patients encompassing the entire heart failure spectrum (preserved, mid-range and reduced ejection fraction). A random survival forest was applied to investigate the most important predictors and group patients according to their number of adverse features (Figure 1). Results: The identified predictors and thresholds, that were associated with significantly worse mortality were higher age (≥75 in moderate and ≥70 years in moderate and severe sTR respectively), higher NT-proBNP (≥4000 pg/ml), increased high sensitivity C-reactive protein (≥1.0 mg/dl), serum albumin <40 g/L and hemoglobin <13 g/dL. Additionally, grouping patients according to the number of adverse features yielded important prognostic information, as patients with 4 or 5 adverse features had a sevenfold risk increase in moderate sTR (7.11 [2.27–4.30] HR 95% CI, P<0.001) and fivefold risk increase in severe sTR (5.08 [3.13–8.24] HR 95% CI, P<0.001) (Figure 2: A moderate sTR derivation, B moderate sTR validation, C severe sTR derivation, D severe sTR validation). Conclusion: This study presents a streamlined, machine learning-derived and internally validated approach to risk-stratification in patients with moderate and severe sTR, that adds important prognostic information to aid clinical decision-making. Funding Acknowledgement: Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Austrian Science Fund