Personalised preinterventional risk stratification of mortality, length of stay and hospitalisation costs in transcatheter aortic valve implantation using a machine learning algorithm: a pilot trial.

INTRODUCTION: Risk stratification based on Euroscore II (ESII) is used in some centres to assist decisions to perform transcatheter aortic valve implant (TAVI) procedures. ESII is a generic, non-TAVI-specific metric, and its performance fades for mortality at follow-up longer than 30 days. We investigated if a TAVI-specific predictive model could achieve improved predictive preinterventional accuracy of 1-year mortality compared with ESII. PATIENTS AND METHODS: In this prospective pilot study, 284 participants with severe symptomatic aortic valve stenosis who underwent TAVI were enrolled. Standard clinical metrics (American Society of Anesthesiology (ASA), New York Heart Association and ESII) and patient-reported outcome measures (EuroQol-5 Dimension-Visual Analogue Scale, Kansas City Cardiomyopathy Questionnaire and Clinical Frailty Scale (CFS)) were assessed 1 day before TAVI. Using these data, we tested predictive models (logistic regression and decision tree algorithm (DTA)) with 1-year mortality as the dependent variable. RESULTS: Logistic regression yielded the best prediction, with ASA and CFS as the strongest predictors of 1-year mortality. Our logistic regression model score showed significantly better prediction accuracy than ESII (area under the curve=0.659 vs 0.800; p=0.002). By translating our results to a DTA, cut-off score values regarding 1-year mortality risk emerged for low, intermediate and high risk. Treatment costs and length of stay (LoS) significantly increased in high-risk patients. CONCLUSIONS AND SIGNIFICANCE: A novel TAVI-specific model predicts 1-year mortality, LoS and costs after TAVI using simple, established, transparent and inexpensive metrics before implantation. Based on this preliminary evidence, TAVI team members and patients can make informed decisions based on a few key metrics. Validation of this score in larger patient cohorts is needed.

Heart Rate Variability as a Surrogate Marker of Severe Chronic Coronary Syndrome in Patients with Obstructive Sleep Apnea.

BACKGROUND AND OBJECTIVES: Obstructive sleep apnea (OSA) is a known risk factor for chronic coronary syndrome (CCS). CCS and OSA are separately associated with significant changes in heart rate variability (HRV). In this proof-of-concept study, we tested whether HRV values are significantly different between OSA patients with concomitant severe CCS, and OSA patients without known CCS. MATERIAL AND METHODS: The study comprised a retrospective assessment of the historical and raw polysomnography (PSG) data of 32 patients who presented to a tertiary university hospital with clinical complaints of OSA. A total of 16 patients (four females, mean age 62.94 ± 2.74 years, mean body mass index (BMI) 31.93 ± 1.65 kg/m2) with OSA (median apnea-hypopnea index (AHI) 39.1 (30.5-70.6)/h) and severe CCS were compared to 16 patients (four females, mean age 62.35 ± 2.06 years, mean BMI 32.19 ± 1.07 kg/m2) with OSA (median AHI 40 (30.6-44.5)/h) but without severe CCS. The short-long-term HRV (in msec) was calculated based on the data of a single-lead electrocardiogram (ECG) provided by one full-night PSG, using the standard deviation of the NN, normal-to-normal intervals (SDNN) and the heart rate variability triangular index (HRVI) methods, and compared between the two groups. RESULTS: A significant reduction (p < 0.05) in both SDNN and HRVI was found in the OSA group with CCS compared to the OSA group without CCS. CONCLUSIONS: Severe CCS has a significant impact on short-long-term HRV in OSA patients. Further studies in OSA patients with less-severe CCS may shed more light onto the involved mechanistic processes. If confirmed in future larger studies, this physiologic metric has the potential to provide a robust surrogate marker of severe CCS in OSA patients.

Personalized Preoperative Prediction of the Length of Hospital Stay after TAVI Using a Dedicated Decision Tree Algorithm.

Background: The aim of this study was to identify pre-operative parameters able to predict length of stay (LoS) based on clinical data and patient-reported outcome measures (PROMs) from a scorecard database in patients with significant aortic stenosis who underwent TAVI (transfemoral aortic valve implantation). Methods: 302 participants (51.7% males, age range 78.2−84.2 years.) were prospectively recruited. After computing the median LoS value (=6 days, range = 5−8 days), we implemented a decision tree algorithm by setting dichotomized values at median LoS as the dependent variable and assessed baseline clinical variables and PROMs (Clinical Frailty Scale (CFS), EuroQol-5 Dimension-5 Levels (EQ-5D) and Kansas City Cardiomyopathy Questionnaire (KCCQ)) as potential predictors. Results: Among clinical parameters, only peripheral arterial disease (p = 0.029, HR = 1.826) and glomerular filtration rate (GFR, cut-off < 33 mL/min/1.73 m2, p = 0.003, HR = 2.252) were predictive of LoS. Additionally, two PROMs (CFS; cut-off = 3, p < 0.001, HR = 1.324 and KCCQ; cut-off = 30, p = 0.003, HR = 2.274) were strong predictors. Further, a risk score for LoS (RS_LoS) was calculated based on these predictors. Patients with RS_LoS = 0 had a median LoS of 5 days; patients RS_LoS ≥ 3 had a median LoS of 8 days. Conclusions: based on the pre-operative values of the above four predictors, a personalized prediction of LoS after TAVI can be achieved.

A Novel Method to Predict Mortality and Length of Stay after Transfemoral Transcatheter Aortic Valve Implantation.

Background and Objectives: We tested if a novel combination of predictors could improve the accuracy of outcome prediction after transfemoral transcatheter aortic valve implantation (TAVI). Materials and Methods: This prospective study recruited 169 participants (49% female; median age 81 years). The primary endpoint was midterm mortality; secondary endpoints were acute Valve Academic Research Consortium (VARC)-3 complication rate and post-TAVI in-hospital length of stay (LoS). EuroSCORE II (ESII), comorbidities (e.g., coronary artery disease), eGFR (estimated glomerular filtration rate; based on cystatin C), hemoglobin, creatinine, N-Terminal pro-Brain Natriuretic Peptide (NTproBNP) levels and patient-reported outcome measures (PROMs, namely EuroQol-5-Dimension-5-Levels, EQ5D5L; Kansas City Cardiomyopathy Questionnaire, KCCQ; clinical frailty scale, CFS) at baseline were tested as predictors. Regression (uni- and multi-variate Cox; linear; binary logistic) and receiver operating characteristic (ROC)-curve analysis were applied. Results: Within a median follow-up of 439 (318-585) days, 12 participants died (7.1%). Independent predictors of mortality using multivariate Cox regression were baseline eGFR (p = 0.001) and KCCQ (p = 0.037). Based on these predictors, a Linear Prediction Score (LPS1) was calculated. The LPS1-area under the curve (AUC)-value (0.761) was significantly higher than the ESII-AUC value (0.597; p = 0.035). Independent predictors for LoS > 6 days (the median LoS) were eGFR (p = 0.028), NTproBNP (p = 0.034), and EQ5D5L values (p = 0.002); a respective calculated LPS2 provided an AUC value of 0.677 (p < 0.001). Eighty participants (47.3%) experienced complications. Male sex predicted complications only in the univariate analysis. Conclusions: The combination of KCCQ and eGFR can better predict midterm mortality than ES II alone. Combining eGFR, NTproBNP, and EQ5D5L can reliably predict LoS after TAVI. This novel method improves personalized TAVI risk stratification and hence may help reduce post-TAVI risk.