Background: Currently available risk scores fail to accurately predict morbidity and mortality in patients with severe symptomatic aortic stenosis who undergo transcatheter aortic valve implantation (TAVI). In this context, biomarkers like matrix metalloproteinase-2 (MMP-2) and Galectin-3 (Gal-3) may provide additional prognostic information. Methods: Patients with severe aortic stenosis undergoing consecutive, elective, transfemoral TAVI were included. Baseline demographic data, functional status, echocardiographic findings, clinical outcomes and biomarker levels were collected and analysed. Results: The study cohort consisted of 89 patients (age 80.4 +/- 5.1 years, EuroScore II 7.1 +/- 5.8%). During a median follow-up period of 526 d, 28 patients (31.4%) died. Among those who died, median baseline MMP-2 (alive: 221.6 [170.4; 263] pg/mL vs. deceased: 272.1 [225; 308.8] pg/mL, p < 0.001) and Gal-3 levels (alive: 19.1 [13.5; 24.6] pg/mL vs. deceased: 25 [17.6; 29.5] pg/mL, p = 0.006) were higher than in survivors. In ROC analysis, MMP-2 reached an acceptable level of discrimination to predict mortality (AUC 0.733, 95% CI [0.62; 0.83], p < 0.001), but the predictive value of Gal-3 was poor (AUC 0.677, 95% CI [0.56; 0.79], p = 0.002). Kaplan-Meier and Cox regression analyses showed that patients with MMP-2 and Gal-3 concentrations above the median at baseline had significantly impaired long-term survival (p = 0.004 and p = 0.02, respectively). Conclusions: In patients with severe aortic stenosis undergoing transfemoral TAVI, MMP-2 and to a lesser extent Gal-3, seem to have additive value in optimizing risk prediction and streamlining decision-making.

Abstract Background In patients < 60 years (yrs) with crytogenic embolism associated with a patent foramen ovale (PFO) guidelines recommend interventional closure based on several randomized studies. There is no recommendation for elderly patients, although they seem to carry a similar risk for recurrent events. There are only scarce data on early and particularly late outcome. Methods We therefore retrospectively analyzed the up to 10 years outcome (median 4,2 yrs) in 444 consecutive patients (female, male) according to age at PFO closure. Results From 444 patients in our study population, 155 were >60 years of age (mean age 66,7 (IQR 63,1-71,74), 45% females. Older patients had higher prevalence of cardiovascular risk factors like hypertension, hyperlipidemia and diabetes (p< 0,01 for all vs. younger patients) while smoking was more prevalent in younger patients (p<0,01). No difference in procedural success and periinterventional complications was observed between the two age groups. During follow up of median 4,2 years (5 patients lost to FU) event rate of recurrent stroke, atrial fibrillation and acute myocardial infarction did not differ between older and younger patients. Conclusions Long term outcome was independent of age despite higher CV risk factors burden and supports PFO closure in elderly patients.

BACKGROUND:Early graft failure (EGF) after coronary artery bypass grafting (CABG) occurs in up to 12% of grafts, but is often clinically unapparent. EGF may result in perioperative myocardial infarction with consequently increased mortality. The aim of the present study was to analyze the incidence of clinically apparent EGF in patients undergoing CABG and the influence on mortality. METHODS:We analyzed outcomes of consecutive patients undergoing CABG from January 2015 to December 2018 with respect to postoperative emergency coronary angiography (CAG) due to suspected EGF and 30-day mortality. Patients with CAG-documented EGF were matched to patients without EGF to examine predictors of mortality. RESULTS:The analysis included 5638 patients undergoing CABG. Eighty-six patients (1.5%) underwent emergency CAG due to suspected EGF. Clinically apparent EGF was observed in 61 of these patients (70.9%), whereas 14 (16.3%) had a culprit lesion in a native coronary artery. The majority of patients (n = 45; 52.3%) were treated with percutaneous coronary intervention and 31 (36%) underwent re-do CABG. The remaining patients were treated conservatively. The 30-day mortality rate of suspected EGF patients undergoing CAG was 22.4% (n = 19), which was higher than the mortality rate of 2.8% overall (P<.001); this remained higher after matching the EGF patients with the control group (11 [20.4%] vs 2 [4.0%]; P=.02). CONCLUSION:Emergency CAG after CABG is rare and is primarily carried out in patients with EGF. The 30-day mortality rate of these patients is high, and EGF is an independent predictor of mortality. Perioperative CAG with subsequent treatment is mandatory in these patients.

Background Robotically assisted remote-controlled PCI (rPCI) was introduced in the past decade as one of the latest enhancements in this rapidly evolving field. The use of a second-generation rPCI system in ST-elevation myocardial infarction (STEMI) is an effort to couple immediate revascularization with the accuracy of newer robotic assistance and software support. Case summary Here we report on the safety and efficacy of rPCI applied to a 74-year-old female STEMI patient with persistent acute chest pain as well as regional wall motion abnormalities in the echocardiogram. The first medical contact-to-device time was 76 min, and door-to-balloon time was 33 min. The impatient course was uneventful, so the patient was discharged from hospital after 5 days. To the best of our knowledge, this is the first report of the successful application of second-generation rPCI in STEMI. Discussion In the case presented, rPCI was feasible and safe even in acute coronary syndrome based on a single-centre experience. rPCI is a revolutionary new technique that may be applied to various types of clinical presentations.

Since the publication of the ESC/ESH guidelines on arterial hypertension in 2018, several sham-controlled, high-quality trials on renal denervation have been published, which demonstrated the safety and efficacy of renal denervation. Therefore, renal denervation is an additional therapeutic option for patients with uncontrolled resistant hypertension, whereby the latter should be confirmed by ambulatory blood pressure monitoring. Renal denervation may also be applied in selected patients with drug intolerances. Decision making should take patient preferences after comprehensive information and the individual cardiovascular risk into account. A multidisciplinary hypertension team should establish the indications for renal denervation and perform the treatment. Interventionalists must be experienced in performing renal interventions and receive a special training for renal denervation. In Germany, renal denervation should be performed by specialized centers, which fulfill personal, spatial and technical criteria as defined by the national societies [23].

BACKGROUND:No comparative data exist with the latest generation self-expanding ACURATE neo2 (Neo2) and the balloon-expandable SAPIEN 3 Ultra (Ultra) transcatheter heart valves (THV).AIMS:We aimed to compare the outcomes after transcatheter aortic valve implantation (TAVI) using the Neo2 and the Ultra THV.METHODS:A total of 1,356 patients at 4 centres were treated either with the Neo2 (n=608) or the Ultra (n=748). The primary endpoint was device success according to the latest Valve Academic Research Consortium definitions. The association of the THV used and the primary endpoint was assessed using inverse probability treatment weighting (IPTW) and 1:1 propensity score matching (PSM), which identified 472 matched pairs.  Results: After PSM, there were no relevant differences between the groups. While rates of moderate to severe paravalvular leakage (PVL) were overall low (0.6% vs 1.1%; p=0.725), elevated transvalvular gradients (≥20 mmHg) were less frequent with the Neo2 (2.4% vs 7.7%; p<0.001), which translated into a significantly higher rate of device success with the Neo2 compared with the Ultra (91.9% vs 85.0%; p<0.001). Consistently, the Neo2 was associated with higher rates of device success in the IPTW analysis (odds ratio [OR] 1.961, 95% confidence interval [CI]: 1.269-3.031; p=0.002). Rates of mild PVL were significantly lower with the Ultra compared with the Neo2 (20.0% vs 32.8%; p<0.001). Clinical events at 30 days were comparable between the 2 groups.CONCLUSIONS:Short-term outcomes after TAVI using the Neo2 or Ultra THV were excellent and, overall, comparable. However, transvalvular gradients were lower with the Neo2, which translated into higher rates of device success. Rates of mild PVL were significantly lower with the Ultra THV.

Lysyl oxidase (LOX) is a secretory protein that catalyzes elastin and collagen cross-linking. Lowering LOX expression and activity in endothelial cells is associated with a high risk of aneurysms and vascular malformation. Interleukin-6 (IL-6), elevated in hypertension, is known to suppress LOX expression. The influence of anti-hypertensive medication on the plasma LOX concentration is currently unknown. In a cohort of 34 patients diagnosed with resistant hypertension and treated with up to nine different drugs, blood concentration of LOX was analyzed to identify drugs that have an impact on plasma LOX concentration. Key findings were confirmed in a second independent patient cohort of 37 patients diagnosed with dilated cardiomyopathy. Blood concentrations of aldosterone and IL-6 were analyzed. In vitro, the effect of IL-6 on LOX expression was analyzed in endothelial cells. Patients receiving aldosterone antagonists had the highest plasma LOX concentration in both cohorts. This effect was independent of sex, age, blood pressure, body mass index, and co-medication. Blood aldosterone concentration correlates with plasma IL-6 concentration. In vitro, IL-6 decreased the expression of LOX in endothelial cells but not fibroblasts. Aldosterone was identified as a factor that affects blood concentration of LOX in an IL-6-dependent manner.

Abstract Funding Acknowledgements Type of funding sources: None. Background Although three dimensional (3D) electroanatomic mapping systems allow detailed assessment of anatomy and substrates, ablation still carries substantial risk when close proximity to coronary arteries is suspected. 3D integration of coronary anatomy in mapping systems is still cumbersome, highlighting the need for an option of ad hoc acquirement of coronary artery anatomy. The goal of this case series was to evaluate the feasibility of a wire-based approach to the live visualization of coronary arteries and to assess its diagnostic information regarding procedure guiding. Methods For this single center case series, we included procedures in which close proximity of an ablation site to an epicardial vessel had to be suspected. An uninsulated-tip wire was then introduced into the relevant coronaries via diagnostic catheters after exclusion of critical stenosis by coronary angiography. The wire was connected to an impedance based 3D mapping system using a clamp and standard pin connection. Integrating this setup in the mapping system allows for live visualization of the wire tip, as well as the assessment of local electrograms within the respective vessel. Results We included a total of 9 procedures (4 ventricular tachycardia (VT) ablation procedures and 5 procedures for the ablation of premature ventricular contractions (PVCs)). The left coronary arteries were mapped in 8 cases, the right coronary artery was mapped in one case. In the majority of cases, the arrhythmogenic substrate was found in the left ventricle (5/9) or left ventricular summit area and the distal coronary sinus respectively (3/9). In two cases, epicardial mapping was performed combined with visualization of the right or left coronary arteries, respectively. There were no complications attributed to coronary wiring and mapping in this case series. In two cases, the diagnostic information from mapping of the coronary arteries could be used to rule out an epicardial origin of arrhythmia. In the majority of cases, coronary visualization was used to ascertain a proper distance between the ablation site and the vessel. Discussion In this case series, we could demonstrate the feasibility and safety of coronary artery visualization and its integration in a 3D mapping system. The data obtained was used for diagnostic, as well as safety aspects. The electrograms from the wire were used to quickly assess relative timing of arrhythmias, thus allowing for an estimation of possible epicardial origin. Conclusion Applying the same caveats as for any other wiring of coronary arteries, their electroanatomic visualization is achieved in a safe and straightforward manner, with minimal technical requirements. Mapping of the coronary arteries adds critical diagnostic information and their real-time visualization is feasible without exceeding costs or risks

BACKGROUND:Left ventricular outflow tract (LVOT) calcification has been associated with worse outcomes in patients undergoing transcatheter aortic valve implantation (TAVI) and may influence the selection of prosthetic valve type.AIMS:We aimed to evaluate the impact of LVOT calcification on outcomes after TAVI with a self-expanding valve (SEV) versus a balloon-expandable valve (BEV).METHODS:Patients of the SOLVE-TAVI trial, randomised to Edwards SAPIEN 3 or Medtronic Evolut R, were divided according to LVOT calcification into no/mild (≤1 calcium nodule extending <5 mm and covering <10% of the LVOT perimeter) and moderate/severe LVOT calcification groups. The primary endpoint was a composite of death, stroke, moderate/severe paravalvular regurgitation, permanent pacemaker implantation and annulus rupture at 30 days. Additional endpoints included all-cause and cardiovascular mortality at 1 year.RESULTS:Out of 416 eligible patients, moderate/severe LVOT calcification was present in 143 (34.4%). Moderate/severe LVOT calcification was associated with significantly longer fluoroscopy time and higher rates of pre- and post-dilation. Regardless of the LVOT calcification group, there was no significant difference in the primary endpoint associated with the valve type (no/mild LVOT calcification group: SEV 25.0% vs BEV 27.0%; hazard ratio [HR] 1.10, 95% confidence interval [95% CI]: 0.68-1.73; p=0.73 and moderate/severe LVOT calcification group: SEV 25.0% vs BEV 19.4%; HR 0.76, 95% CI: 0.38-1.61; p=0.49), no significant interaction between LVOT calcification and valve type (pint=0.29) and no differences between SEV vs BEV within LVOT calcification groups regarding 1-year all-cause and cardiovascular mortality.CONCLUSIONS:Moderate/severe LVOT calcification was associated with longer fluoroscopy time and an increased need for pre- and post-dilation, but not with a higher incidence of early and mid-term adverse clinical outcomes, regardless of valve type. (ClinicalTrials.gov: NCT02737150).

Background Percutaneous coronary intervention (PCI) is the standard-of-care treatment for left main stenosis as an alternative to bypass surgery. In addition, severe coronary lesion calcification can be modified by intravascular lithotripsy (IVL). However, with PCI and debulking treatment options, there are inherent limitations. PCI poses an increased health burden for the treating physician that is associated with wearing a heavy, lead-lined apron and being exposed to radiation. To overcome these issues, a robotically assisted angioplasty system (rPCI) was established that enables the operator to perform PCI remotely in routine clinical procedures. Furthermore, IVL have not been used remotely. Case summary Here, we report the use of this technique for treating a heavily calcified left main stenosis in an 82-year-old male with previously diagnosed two-vessel coronary artery disease, progressive symptoms of dyspnoea at high cardio-vascular risk profile. The decision of the local heart team declined surgery. To the best of our knowledge, this is the first report of successful rPCI combined with IVL. Discussion In the case presented, rPCI was feasible and safe even in a complex lesion of the left main coronary artery requiring IVL. rPCI is a revolutionary new technique that may be applied to various types of coronary artery lesions.

The main aim of this study was to assess the prognostic utility of TAPSE/PASP as an echocardiographic parameter of maladaptive RV remodeling in cardiomyopathy patients using cardiac magnetic resonance (CMR) imaging. Furthermore, we sought to compare TAPSE/PASP to TAPSE. The association of the echocardiographic parameters TAPSE/PASP and TAPSE with CMR parameters of RV and LV remodeling was evaluated in 111 patients with ischemic and non-ischemic cardiomyopathy and cut-off values for maladaptive RV remodeling were defined. In a second step, the prognostic value of TAPSE/PASP and its cut-off value were analyzed regarding mortality in a validation cohort consisting of 221 patients with ischemic and non-ischemic cardiomyopathy. A low TAPSE/PASP (<0.38 mm/mmHg) and TAPSE (<16 mm) were associated with a lower RVEF and a long-axis RV global longitudinal strain (GLS) as well as higher RVESVI, RVEDVI and NT-proBNP. A low TAPSE/PASP, but not TAPSE, was associated with a lower LVEF and long-axis LV GLS, and a higher LVESVI, LVEDVI and T1 relaxation time at the interventricular septum and the RV insertion points. Furthermore, in the validation cohort, low TAPSE/PASP was associated with a higher mortality and TAPSE/PASP was an independent predictor of mortality. TAPSE/PASP is a predictor of maladaptive RV and LV remodeling associated with poor outcomes in cardiomyopathy patients.

Background: The most common method of percutaneous closure in transfemoral transcatheter aortic valve implantation (TAVI) employs two obtusely oriented ProGlide devices. The aim of this study was to assess the feasibility and safety of using a single ProGlide system for primary access site closure in comparison with the double ProGlide approach in an all-corners TAVI population. Methods: Between March 2016 and December 2018, a total of 1105 patients underwent transfemoral TAVI for severe aortic stenosis at our center. Application of two ProGlide systems was standard until April 2017 (n = 432), whereas thereafter a single ProGlide system was used (n = 663). A 1:1 propensity score matching was performed to adjust for baseline differences between the two groups, resulting in 327 matched cases. Primary outcomes of interest were main access site-related vascular complications. Results: The mean number of ProGlide devices used per patient was 1.03 (SD 0.2) in the single-ProGlide group versus 2.01 (SD 0.14) in the double-ProGlide group. An additional vascular closure device was required to obtain full hemostasis in 23.2% versus 9.5% of patients (p < 0.001) in the two groups, respectively. Technical success of ProGlide usage was similar (94.3% versus 92.1%, p = 0.163). In the matched cohorts, the rates of main access site-related major vascular complications were similar (4.0% vs. 6.4%, p = 0.217). Conclusion: The single-ProGlide technique is feasible, with rates of technical success similar to those of the double-ProGlide technique. Use of this method did not lead to more frequent access site-related complications but was more cost effective than the double-ProGlide approach. (C) 2021 Elsevier B.V. All rights reserved.

This manual addressing the interventional treatment (part 2) is a recommendation for interventional cardiologists. It displays the latest evidence in interventional cardiology. Each chapter was designed to focus on the everyday practicability and to provide decision support for cardiologists in the daily clinical routine of a catheter laboratory. Despite the practical advice by many experts, this manual cannot replace the medical evaluation of each individual patient and thus an adaptation of the diagnostics or treatment is necessary.

Interventional cardiovascular medicine has seen constant progress over the last few decades. Since the first angiograms and percutaneous transluminal coronary angioplasty were carried out, this progress has been tremendous and has led to a substantial decline in cardiovascular morbidity and mortality. The purpose of this article is to report and review the latest developments and evidence in robotics-assisted percutaneous coronary intervention (rPCI) and its potential future applications, opportunities, and limitations. Contemporary evidence shows that rPCI can lead to a significant reduction in radiation exposure as well as medical hazards for cardiologists. Rates of device and procedural success remain high and there is no evidence of a disadvantage for the patient. The accuracy of implantation with a reduced geographic mismatch is a further advantage that can result in a higher quality of treatment. Even in complex coronary lesions and procedures, rPCI seems to be safe and efficient. The latest developments include telestenting over hundreds of kilometers from a remote platform. Currently, the main limitations are the absence of large-scale randomized trials for the valid assessment of the benefits and disadvantages of rPCI as well as the technical limitations of the currently available rPCI systems. rPCI is a forward-looking innovation in cardiology that is applicable to a wide range of coronary interventions. Despite the present lack of knowledge and the limited data concerning the outcome for the patient, the available literature reveals promising results that should lead to improvements for physicians and patients.

Abstract Background Cardiac myosin binding protein-C is a protein expressed in the myosin thick filament backbone that was recently described as a novel cardiac biomarker. Its N-terminal region, C0-C1f, is released within the first minutes of ischemia and plays a crucial role in the initiation of inflammation in bone marrow-derived macrophages. Long-term C0-C1f exposure induces cardiac fibrosis in transgenic mice; however, the mechanism by which C0-C1f causes fibrosis is unclear. The aim of the study was to investigate the effects of C0-C1f on fibroblasts, which are the main contributor to cardiac fibrosis, in vitro. We determined whether C0-C1f directly activates fibroblasts and causes a transdifferentiation to myofibroblasts or induces inflammatory responses. Moreover, we clarify whether other cell types could be involved in inducing fibrosis, i.e. by the release of pro-inflammatory cytokines upon C0-C1f interaction. Methods A novel human fibroblast cell line (huFib) was treated with C0-C1f, C0-Linker, TGF-β, or LPS for different time periods. Inflammatory and fibrotic responses were evaluated at the RNA and protein level using different techniques including microarray, qRT-PCR, and immunofluorescence imaging. For signalling pathway analysis, TLR4 and NFκB were inhibited using chemical compounds TAK-242 or Bay11–0785 respectively. Results C0-C1f treatment induced an increase in mRNA corresponding to pro-inflammatory genes in huFib cells (i.a. CXL1 upon 24 hours treatment: 29 fold, p<0.001 and CCL2 4-fold, p<0.001). The mRNA expression levels of pro-fibrotic genes such as ACTA2 or COL1A1, which were upregulated by TGF-β, were not reduced by C0-C1f (ACTA2 induced by TGF-β: 3,8 fold, p<0.001, co-stimulation with C0-C1f: 1,8 fold, p=0.11 compared to control; COL1A1 induced by TGF-β: 2,94 fold, p<0.001, co-stimulation with C0-C1f: 2.09 fold (p<0.01) compared to control. Interestingly, co-stimulation of fibroblasts with C0-C1f and TGF-β led also to markedly lower inflammatory response compared to C0-C1f treatment alone (CXCL1 induction upon co-stimulation: 2,0 fold, p<0.001, CCL2: 1,9 fold, p=0.001, which is a reduction by 27 fold, p<0.001 or 2 fold, p=0.002, respectively). Inhibition of TLR4 or NFκB signaling diminished C0-C1f-mediated inflammatory responses. Conclusion C0-C1f induces inflammation in fibroblasts via TLR4/NFκB signalling pathway. Downregulation of C0-C1f mediated inflammatory responses upon co-stimulation with TGF-β suggests crosstalk between the two signaling pathways. Contrary, C0-C1f reduced TGF-β mediated pro-fibrotic responses reflected by conversion of fibroblasts into myofibroblasts was not observed. Taken together, these data are consistent with the idea that C0-C1f might play a key role in the early initiation of inflammation upon myocardial infarction, also in fibroblasts, and that TGF-β acts as a counterpart at later stages of cardiac remodeling. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): William G. Kerckhoff Stiftung für wissenschaftliche Forschung und Fortbildung

OBJECTIVES The aim of this study was to characterize the feasibility of coronary angiography (CA) and percutaneous coronary intervention (PCI) in acute settings among patients who have undergone transcatheter aortic valve replacement (TAVR). BACKGROUND Impaired coronary access after TAVR may be challenging and particularly in acute settings could have deleterious consequences. METHODS In this international registry, data from patients with prior TAVR requiring urgent or emergent CA were retrospectively collected. A total of 449 patients from 25 sites with acute coronary syndromes (89.1%) and other acute cardiovascular situations (10.9%) were included. RESULTS Success rates were high for CA of the right coronary artery (98.3%) and left coronary artery (99.3%) and were higher among patients with short stent-frame prostheses (SFPs) than in those with long SFPs for CA of the right coronary artery (99.6% vs 95.9%; P = 0.005) but not for CA of the left coronary artery (99.7% vs 98.7%; P = 0.24). PCI of native coronary arteries was successful in 91.4% of cases and independent of valve type (short SFP 90.4% vs long SFP 93.4%; P = 0.44). Guide engagement failed in 6 patients, of whom 3 underwent emergent coronary artery bypass grafting and another 3 died in the hospital. Among patients requiring revascularization of native vessels, independent predictors of 30-day all-cause mortality were prior diabetes, cardiogenic shock, and failed PCI but not valve type or success of coronary engagement. CONCLUSIONS CA or PCI after TAVR in acute settings is usually successful, but selective coronary engagement may be more challenging in the presence of long SFPs. Among patients requiring PCI, prior diabetes, cardiogenic shock, and failed PCI were predictors of early mortality. (J Am Coll Cardiol Intv 2021;14:1578-90) (c) 2021 by the American College of Cardiology Foundation.

This manual on diagnostic cardiac catheterization (part 1) is a recommendation for application by interventional cardiologists, which reflects the latest evidence in interventional cardiology. Each chapter was designed to focus on the everyday practicability and to provide decision support in the daily clinical routine of the catheter laboratory. Despite the practical advice by many experts, this manual cannot replace the medical evaluation of each individual patient and thus an adaptation of the diagnostics or treatment is necessary.

Abstract Background The current state of the art in the diagnosis and treatment of cardiovascular diseases has been based on evidence resulting from traditional trials as well as years of clinical experience. Due to interindividual differences and a huge number of possible cofounders, in interventional cardiology a linear algorithm is usually not able to precisely estimate individual risk, therapy, or outcome. With the technological evolution in deep machine learning (ML) and artificial intelligence (AI), clinicians may now address aspects that might not have been investigated previously, as supercomputers may handle the plethora of data that are generated as part of treatment. Ultimately, treatment recommendations and decisions may be made on a personalized level. Purpose The aim of this study was to apply AI to routine clinical practice to improve decision making in transcatheter aortic valve implantation (TAVI) to determine the best type and size of prosthesis personalized for each patient with pre-procedural risk stratification. Methods All patients included in the study were undergoing TAVI. To predict the clinical outcomes we applied a random forest classification, a ML method with high interpretability. For baseline data 58 features were chosen, including valve type and size used. After removing highly collinear features with a certain variance inflation factor, feature selection was based on impurity-based feature importance as well as permutation importance. The performance of the estimators was evaluated by a five-fold nested stratified cross-validation. To evaluate the model ROC and mean AUC scores were chosen. Results A total of 3882 patient datasets were included in this trial. The baseline characteristics were consistent with a high cardiovascular risk typical of this collective. Device success was achieved in 83.3%, pacemaker implantation was necessary in 12.2%, and aortic valvular insufficiency was observed in 2.5%. The 30-day mortality was 3.4% and one-year mortality was 12.7%. The mean AUC for the outcome parameters device success, aortic valvular insufficiency, any pacemaker operation, and 30-day and one-year mortality after five-fold cross validation were 0.61±0.03, 0.71±0.04, 0.66±0.04, 0.67±0.03, and 0.69±0.01, respectively. Conclusions We report preliminary data concerning a promising method to improve decision making in the context of TAVI evaluation and planning using ML algorithm. We showed the feasibility with acceptable AUC values for all outcome parameters. Thus, the integration of AI in TAVI strategy planning process offers a valuable tool providing patient focused personalized therapy. Funding Acknowledgement Type of funding sources: None.