Software supported robotic PCI in coronary arteries – comparison from the ROBO.pci trial

Background

Robotic percutaneous coronary interventions (rPCI) have proven to be efficient and safe. The robotics software has recently been updated and now allows precise and fully controlled navigation of devices and wires to fit the various morphologic conditions of coronary arteries and calcified segments.

Objectives

In the present study we aimed to compare the different robotic wiring modalities supported by the new software.

Study design

rPCI performed using the updated robotics software was compared with rPCI using the manually executed wire positioning. Lesion crossing was performed with each method under identical circumstances, crossing the same lesion and measuring the wire times. Measurements were started at the ostium of the guiding catheter and were stopped at a pre-defined individual coronary anatomical landmark.

Results

Eleven consecutive patients with 11 lesions were enrolled in this trial. The mean age of patients was 63±6 years with typical cardiovascular comorbidities and 54% (6/11) presented with three-vessel disease. All patients underwent PCI in an elective setting with stable chronic coronary syndrome. The majority of lesions were located in the LCX (45%, 5/11) followed by the LAD (27%, 3/11) and the RCA (27%, 3/11). All lesions were de novo ACC/AHA grade B2/C lesions, and the procedure was performed by experienced (high-volume) interventional cardiologists. The lesion crossing times were not significantly different (manual crossing 15.00 [IQR: 40] sec vs. rPCI without software support 18.00 [IQR: 18] sec vs. rPCI with software support 13.00 [IQR: 47] sec; p=n.s.).

Summary

rPCI without software support tends to be slower than rPCI with software support. There was no statistical significance. rPCI was found to be safe and feasible and the new software tends to reduced procedural time, which could reduce operators' health risks and improve patients' outcomes. Further randomized controlled trials are needed to evaluate the long-term benefits.

Funding Acknowledgement

Type of funding sources: None.

Artificial intelligence to improve decision making in transcatheter aortic valve implantation

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.

A double-blind comparison of the effects of carvedilol and captopril on serum lipid concentrations in patients with mild to moderate essential hypertension and dyslipidaemia

We have studied 250 patients with mild to moderate essential hypertension (diastolic blood pressure 95-114 mmHg) and dyslipidaemia (high-density lipoprotein cholesterol (HDL-C) below 1.03 mmol.l-1, total cholesterol 5.17-9.05 mmol.l-1, and triglycerides 2.26-5.64 mmol.l-1) in a controlled double-blind, multicentre, parallel group trial. The patients took a fat-modified diet. After a 4-week placebo period, patients who continued to fulfil the selection criteria were randomly allocated to treatment with either carvedilol (a vasodilating beta-blocker) 25-50 mg o.d. (n = 116) or captopril (an ACE inhibitor) 25-50 mg o.d. (n = 117) for 6 months. In both groups there were favourable effects on the serum lipids. The relative changes (medians) in the carvedilol and captopril group were respectively: increase in HDL-C by 11% and 8%, decrease in total cholesterol by 11% and 10%, in low-density lipoprotein cholesterol by 16% and 12%, and in triglycerides by 13% and 14%. Equivalence of the two treatments was confirmed for the target variable change in HDL-C at a significance level of 5%. Reductions in supine systolic/diastolic blood pressures were comparable in the two groups (carvedilol: 23/19 mmHg, captopril: 20/18 mmHg). The improvement in lipid metabolism in patients treated with carvedilol is probably due to its alpha 1-blocking properties.

Effects of triamterene on serum and skeletal muscle electrolytes in diuretic-treated patients

The effects on plasma and skeletal muscle electrolytes of the combination of triamterene 37.5 mg and hydrochlorothiazide 25 mg daily were studied in 19 patients on prior long-term (greater than 1 year) diuretic therapy for arterial hypertension and/or congestive heart failure. A further 20 patients fulfilling the same admission criteria were used as controls. Blood samples and skeletal muscle biopsies were taken before the study and after 6 months on therapy. The diuretic-treated group had a significant increase in skeletal muscle potassium and magnesium after 6 months on therapy as compared to the controls. Thus, the combination of triamterene and hydrochlorothiazide appeared effective in preserving the cellular content of potassium and magnesium on a long-term basis in the type of patient studied.