Efficacy assessment of ticagrelor versus clopidogrel in Chinese patients with acute coronary syndrome undergoing percutaneous coronary intervention by data mining and machine‐learning decision tree approaches

Abstract

What is known and Objective Although ticagrelor has been well‐known to improve clinical outcomes in patients undergoing percutaneous coronary intervention (PCI), and its effectiveness and safety have not been well evaluated in Chinese patients. This study aimed to evaluate the effectiveness and safety of ticagrelor in Chinese patients. In order to find potential effect modifiers on the drug effects, a decision tree method was performed to detect interactions between treatment and patient characteristics in an automatic and systematic manner. Methods This retrospective study included acute coronary syndrome (ACS) patients who underwent PCI and received either ticagrelor (N = 250) or clopidogrel (N = 291) while hospitalized between August 2014 and August 2015. After propensity score matching, Kaplan‐Meier analysis was used to study the event‐free survival against major adverse cardiovascular events (MACE, primary efficacy outcome, defined as the composite of cardiac death, non‐fatal myocardial infarction [MI], stroke, restenosis and target vessel revascularization [TVR]), re‐hospitalization, the need for urgent re‐PCI (secondary efficacy outcome) and bleeding events (safety outcome) within 12 months of the PCI date. To search for effect modifiers of the two antiplatelet therapies, a machine‐learning decision tree algorithm was conducted to predict re‐hospitalization status. Results After propensity score matching (N = 442), ticagrelor and clopidogrel had no significant difference in MACE, re‐hospitalization and bleeding. The decision tree analysis showed that the number of diseased vessels modulated the effect of ticagrelor and clopidogrel on re‐hospitalization rates. In single‐vessel disease (SVD) patients, ticagrelor was associated with lower hazards than clopidogrel for all efficacy outcomes: MACE (HR = 0.190, 95% CI: 0.042–0.866), re‐hospitalization (HR = 0.296, 95% CI: 0.108–0.808), urgent re‐PCI (HR = 0.249, 95% CI: 0.069–0.895), bleeding (HR = 1.006, 95% CI: 0.063–16.129). However, in multi‐vessel disease (MVD) patients, the two treatments did not show significant difference. What is New and Conclusion In the general patient population, there was no significant difference between ticagrelor and clopidogrel on the hazard of MACE. However, ticagrelor achieved a better effectiveness than clopidogrel in patients with SVD. This pilot study provides scientific basis to call for a large‐scale prospective study in this population.

Comparison of Ticagrelor and Clopidogrel on Platelet Function and Prognosis of Patients with Unstable Angina

“…Differences in individual genes do not affect the e cacy of the ticagrelor. Ticagrelor can quickly inhibit platelet aggregation [8][9][10][11].…”

Artificial intelligence in cardiovascular prevention: new ways will open new doors

“…Finally, artificial intelligence may allow identifying who will benefit more, less or will not benefit from any specific treatment after an ACS. 89,96,97 Heart failure…”

Design of Decision Tree Structure with Improved BPNN Nodes for High-Accuracy Locomotion Mode Recognition Using a Single IMU

“…A DT has a clear structure and low computational complexity; however, DT results are prone to overfitting. Representative examples of DT algorithms [31] include ID3, C4.5, CART, and the stochastic forest algorithm [32] derived from the DT, which are widely used in pattern recognition tasks [33].…”

“…The time window of the locomotion mode recognition system also depends on the requirements of the control system, which is generally less than 200 ms for better system performance. In this study, an initial time window of 200 ms was selected, which is less than the 250-ms time window employed in a previously reported backpropagation neural network [31]. Here, to verify the identification effect of different time windows on the classification model, the length of the time window was reduced to 150 and 100 ms under the condition that the original values were taken as input and the classification model adopted the IBPNN-DTS B with the highest accuracy.…”