ABSTRACT
BACKGROUND: predicting the 1-year survival of patients undergoing transcatheter aortic valve implantation (TAVI) is indispensable for managing safe early discharge strategies and resource optimization. METHODS: Routinely acquired data (134 variables) were used from 629 patients, who underwent transfemoral TAVI from 2012 up to 2018. Support vector machines, neuronal networks, random forests, nearest neighbour and Bayes models were used with new, previously unseen patients to predict 1-year mortality in TAVI patients. A genetic variable selection algorithm identified a set of predictor variables with high predictive power. RESULTS: Univariate analyses revealed 19 variables (clinical, laboratory, echocardiographic, computed tomographic and ECG) that significantly influence 1-year survival. Before applying the reject option, the model performances in terms of negative predictive value (NPV) and positive predictive value (PPV) were similar between all models. After applying the reject option, the random forest model identified a subcohort showing a negative predictive value of 96% (positive predictive value = 92%, accuracy = 96%). CONCLUSIONS: Our model can predict the 1-year survival with very high negative and sufficiently high positive predictive value, with very high accuracy. The "reject option" allows a high performance and harmonic integration of machine learning in the clinical decision process.
ABSTRACT
Background: The aim of this study was to assess the incidence, outcomes, and risk factors associated with thrombocytopenia following TAVI according to a corrected platelet count (CPC), to avoid the bias of hemodilution/concentration. Methods: We analyzed patients who underwent TAVI in our center between 2009 and 2018. The study population were divided into three groups: none (NT), mild (MT), and severe (ST) postoperative thrombocytopenia. Primary outcomes were bleedings, length of hospital stay, and mortality. A multivariate logistic regression was performed to assess risk factors for ST. Results: A total of 907 patients were included in the analysis. MT was observed in 28.1% and ST in 2.6% of all patients. The following clinical outcomes were recorded: incidence of life-threatening and major bleeding (NT = 14.2%, MT = 20.8%, ST = 58.3%), the median length of hospital stay (NT = 8, MT = 10, ST = 14 days), in-hospital mortality (NT = 3.9%, MT = 6.3%, ST = 16.7%), and the overall significance in comparison with NT (p < 0.05). The logistic regression showed ST was associated with preoperative CPC, transapical access, diabetes mellitus, and the critical preoperative state. Conclusions: Worse clinical outcomes are associated with both MT and ST after TAVI. In particular, ST is associated with higher in-hospital and 30-day mortality. Management of modifiable baseline and procedural variables may improve this outcome.
