{Reference Type}: Journal Article
{Title}: Tailored Risk Stratification in Severe Mitral Regurgitation and Heart Failure Using Supervised Learning Techniques.
{Author}: Heitzinger G;Spinka G;Prausmüller S;Pavo N;Dannenberg V;Donà C;Koschutnik M;Kammerlander A;Nitsche C;Arfsten H;Kastl S;Strunk G;Hülsmann M;Rosenhek R;Hengstenberg C;Bartko PE;Goliasch G;
{Journal}: JACC Adv
{Volume}: 1
{Issue}: 3
{Year}: 2022 Aug
暂无{DOI}: 10.1016/j.jacadv.2022.100063
{Abstract}: <B>UNASSIGNED: </B>Secondary mitral regurgitation (sMR) in the setting of heart failure (HF) has considerable impact on quality of life, HF rehospitalizations, and mortality. Identification of high-risk cohorts is essential to understand disease trajectories and for risk stratification.<BR><B>UNASSIGNED: </B>This study aimed to provide a structured decision tree-like approach to risk stratification in patients with severe sMR and HF.<BR><B>UNASSIGNED: </B>This observational study included 1,317 patients with severe sMR from the entire HF spectrum. Clinical, echocardiographic, and laboratory data were extracted for all patients. The primary end point was all-cause mortality. Survival tree analysis, a supervised learning technique, was applied to identify patient subgroups at risk of mortality and further stratified by HF subtype (preserved, mildly reduced, and reduced ejection fraction).<BR><B>UNASSIGNED: </B>Using supervised learning (survival tree method), 8 distinct subgroups were identified that differed significantly in long-term survival. Subgroup 7, characterized by younger age (≤66 years), higher hemoglobin (>12.7 g/dL), and higher albumin levels (>40.6 g/L) had the best survival. In contrast, subgroup 5 displayed a 20-fold risk of mortality (hazard ratio: 20.38 [95% CI: 10.78-38.52]); P < 0.001 and had older age (>68 years), low serum albumin (≤40.6 g/L), and higher NT-proBNP levels (≥9,750 pg/mL). Unique subgroups were further identified for each type of HF subtypes.<BR><B>UNASSIGNED: </B>Supervised machine learning reveals heterogeneity in the sMR risk spectrum, highlighting the clinical variability in the population. A decision tree-like model can help identify differences in outcomes among subgroups and can help provide tailored risk stratification.