Background
There is a paucity of outcome data on patients who are morbidly obese (MO) undergoing transcatheter aortic valve replacement. We aimed to determine their periprocedural and midterm outcomes and investigate the impact of obesity phenotype.
Methods and Results
Consecutive patients who are MO (body mass index, ≥40 kg/m
2
, or ≥35 kg/m
2
with obesity‐related comorbidities; n=910) with severe aortic stenosis who underwent transcatheter aortic valve replacement in 18 tertiary hospitals were compared with a nonobese cohort (body mass index, 18.5–29.9 kg/m
2
, n=2264). Propensity‐score matching resulted in 770 pairs. Pre–transcatheter aortic valve replacement computed tomography scans were centrally analyzed to assess adipose tissue distribution; epicardial, abdominal visceral and subcutaneous fat. Major vascular complications were more common (6.6% versus 4.3%;
P
=0.043) and device success was less frequent (84.4% versus 88.1%;
P
=0.038) in the MO group. Freedom from all‐cause and cardiovascular mortality were similar at 2 years (79.4 versus 80.6%,
P
=0.731; and 88.7 versus 87.4%,
P
=0.699; MO and nonobese, respectively). Multivariable analysis identified baseline glomerular filtration rate and nontransfemoral access as independent predictors of 2‐year mortality in the MO group. An adverse MO phenotype with an abdominal visceral adipose tissue:subcutaneous adipose tissue ratio ≥1 (VAT:SAT) was associated with increased 2‐year all‐cause (hazard ratio [HR], 3.06; 95% CI, 1.20–7.77;
P
=0.019) and cardiovascular (hazard ratio, 4.11; 95% CI, 1.06–15.90;
P
=0.041) mortality, and readmissions (HR, 1.81; 95% CI, 1.07–3.07;
P
=0.027). After multivariable analysis, a (VAT:SAT) ratio ≥1 remained a strong predictor of 2‐year mortality (hazard ratio, 2.78;
P
=0.035).
Conclusions
Transcatheter aortic valve replacement in patients who are MO has similar short‐ and midterm outcomes to nonobese patients, despite higher major vascular complications and lower device success. An abdominal VAT:SAT ratio ≥1 identifies an obesity phenotype at higher risk of adverse clinical outcomes.
INTROduCTIONThe prevalence of aortic valve stenosis (AS), the most common acquired valvular heart disease, increases with age. As life expectancy is increasing, the number of patients requiring treatment for AS is expected to grow steadily. 1,2 Advanced age is a known risk factor in surgical aortic valve replacement (SAVR). Introduction of transcatheter aortic valve implantation (TAVI) provided an effective and less -invasive alternative
Aims
Prediction of adverse events in mid-term follow-up after transcatheter aortic valve implantation (TAVI) is challenging. We sought to develop and validate a machine learning model for prediction of 1-year all-cause mortality in patients who underwent TAVI and were discharged following the index procedure.
Methods and Results
The model was developed on data of patients who underwent TAVI at a high-volume center between January 2013 and March 2019. Machine learning by extreme gradient boosting was trained and tested with repeated 10-fold hold-out testing using 34 pre- and 25 periprocedural clinical variables. External validation was performed on unseen data from two other independent high volume TAVI centers.
Six hundred and four patients (43% men, 81 ± 5 years old, EuroSCORE II 4.8 [3.0–6.3]%) in the derivation and 823 patients (46% men, 82 ± 5 years old, EuroSCORE II 4.7 [2.9–6.0]%) in the validation cohort underwent TAVI and were discharged home following the index procedure. Over the 12 months of follow-up, 68 (11%) and 95 (12%) subjects died in the derivation and validation cohort respectively. In external validation the machine learning model had an area under the receiver-operator-curve of 0.82 (0.78–0.87) for prediction of 1-year all-cause mortality following hospital discharge after TAVI which was superior to pre- and periprocedural clinical variables including age 0.52 (0.46–0.59) and the EuroSCORE II 0.57 (0.51–0.64), p < 0.001 for a difference.
Conclusion
Machine learning based on readily available clinical data allows accurate prediction of 1-year all-cause mortality following a successful TAVI.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.