Lower Confidence Bound Research Articles

Enhancing solar energy conversion efficiency: Thermophysical property predicting of MXene/Graphene hybrid nanofluids via bayesian-optimized artificial neural networks

Accurately predicting thermo-physical properties (TPPs) of MXene/graphene-based nanofluids is crucial for photovoltaic/thermal solar systems, driving focused research on developing precise TPP predictive models. This study presents optimized multi-layer perceptron neural network (MLPNN) models, leveraging Bayesian optimization to refine architectural and training hyperparameters, including hidden layers, neurons, activation functions, standardization, and regularization terms. A comparative analysis of Bayesian acquisition functions—the probability of improvement (POI), lower confidence bound (LCB), expected improvement (EI), expected improvement plus (EIP), expected improvement per second plus (EIPSP), and expected improvement per second (EIPS)—demonstrated that the POI-MLPNN achieves the most accurate results, as evidenced by the lowest MAPE of 1.0923 % and exceptional consistency with an R-value of 0.99811. The EI-MLPNN and EIP-MLPNN models recorded the same outputs. The EI/EIP-MLPNN (R = 0.99668) model excels in consistency over LCB-MLPNN (R = 0.99529) and EIPSP-MLPNN (R = 0.99667). The optimized models offer a reliable, cost-efficient alternate for experimental and computational TPP analyses. Leveraging insights from these models enables better control over nanofluid TPPs in solar systems, enhancing energy conversion efficiency.

Diverse randomized value functions: A provably pessimistic approach for offline reinforcement learning

Offline Reinforcement Learning (RL) faces challenges such as distributional shift and unreliable value estimation, especially for out-of-distribution (OOD) actions. To address these issues, existing uncertainty-based methods penalize the value function with uncertainty quantification and require numerous ensemble networks, leading to computational challenges and suboptimal outcomes. In this paper, we introduce a novel strategy that employs diverse randomized value functions to estimate the posterior distribution of Q-values. This approach provides robust uncertainty quantification and estimates the lower confidence bounds (LCB) of Q-values. By applying moderate value penalties for OOD actions, our method fosters a provably pessimistic approach. We also emphasize diversity within randomized value functions and enhance efficiency by introducing a diversity regularization method, thereby reducing the requisite number of networks. These modules result in reliable value estimation and efficient policy learning from offline data. Theoretical analysis shows that our method recovers the provably efficient LCB-penalty under linear MDP assumptions. Extensive empirical results demonstrate that our proposed method significantly outperforms baseline methods in terms of performance and parametric efficiency.

Bayes_Opt-SWMM: A Gaussian process-based Bayesian optimization tool for real-time flood modeling with SWMM

Real-time flood model plays a pivotal role in averting urban flood damage, particularly when there is minimal lead time for preparatory measures. However, urban flood modeling in real-time often contends with inherent uncertainties arising from input data uncertainty and parameter ambiguities. This study introduces a real-time calibration (RTC) tool called Bayes_Opt-SWMM , specifically tailored for real-time urban flood modeling and uncertainty optimization. This tool leverages the Gaussian process-based Bayesian optimization algorithm and interfaces seamlessly with the Stormwater Management Model (SWMM). It integrates real-time model forcing data and flood monitoring collected through sensors and gauges which are strategically placed within critical locations of urban drainage systems. Our approach hinges on the Surrogate Model based Uncertainty Optimization (SMUO) concept, providing an avenue for enhancing real-time flood modeling. Bayes_Opt-SWMM runs the optimization process using a surrogate model called Gaussian Process emulator with two inference methods: (1) the Gaussian Process (GP) model and (2) Markov Chain Monte Carlo (MCMC) algorithm in GP model (GP_MCMC). Furthermore, three acquisition functions, namely Expected Improvement (EI), Maximum Probability of Improvement (MPI), and Lower Confidence Bound (LCB), facilitate optimal parameter fitting within the surrogate models. The efficiency of GP-based surrogate models in learning SWMM model parameters, leads to an improved uncertainty quantification and accelerated real-time flood modeling in urban areas. Overall, Bayes_Opt-SWMM emerges as a cost-effective and valuable tool for real-time flood modeling and monitoring, with significant potential for managing intelligent storm water systems in urban environments.

Constrained Bayesian Optimization with Lower Confidence Bound

In this article, we present a hybrid Bayesian optimization (BO) framework to solve constrained optimization problems by adopting a state-of-the-art acquisition function from the unconstrained BO literature, the well-known lower confidence bound acquisition function and propose a novel variant that analyzes the feasible and infeasible regions which ensure the theoretical convergence guarantee. The proposed variant is compared with the existing state-of-the-art approaches in the constrained BO literature via implementing these approaches on six different problems, including black-box, classical engineering, and hyperparameter tuning problems. Further, we demonstrate the effectiveness of our approach through graphical and statistical testing.

1-Year Outcomes From the CLASP IID Randomized Trial for Degenerative Mitral Regurgitation

BackgroundThe CLASP IID (Edwards PASCAL TrAnScatheter Valve RePair System Pivotal Clinical) trial is the first randomized controlled trial comparing the PASCAL system and the MitraClip system in prohibitive risk patients with significant symptomatic degenerative mitral regurgitation (DMR). ObjectivesThis study sought to report primary and secondary endpoints and 1-year outcomes for the full cohort of the CLASP IID trial. MethodsProhibitive-risk patients with 3+/4+ DMR were randomized 2:1 (PASCAL:MitraClip). The 1-year assessments included secondary effectiveness endpoints (mitral regurgitation [MR] ≤2+ and MR ≤1+), and clinical, echocardiographic, functional, and quality-of-life outcomes. Primary safety (30-day composite major adverse events [MAEs]) and effectiveness (6-month MR ≤2+) endpoints were assessed for the full cohort. ResultsA total of 300 patients were randomized (PASCAL: n = 204; MitraClip: n = 96). At 1 year, differences in survival, freedom from heart failure hospitalization, and MAE were nonsignificant (P > 0.05 for all). Noninferiority of the PASCAL system compared with the MitraClip system persisted for the primary endpoints in the full cohort (for PASCAL vs MitraClip, the 30-day MAE rates were 4.6% vs 5.4% with a rate difference of −0.8% and 95% upper confidence bound of 4.6%. The 6-month MR ≤2+ rates were 97.9% vs 95.7% with a rate difference of 2.2% and 95% lower confidence bound (LCB) of −2.5%, respectively). Noninferiority was met for the secondary effectiveness endpoints at 1 year (MR ≤2+ rates for PASCAL vs MitraClip were 95.8% vs 93.8% with a rate difference of 2.1% and 95% LCB of −4.1%. The MR ≤1+ rates were 77.1% vs 71.3% with a rate difference of 5.8% and 95% LCB of −5.3%, respectively). Significant improvements in functional classification and quality of life were sustained in both groups (P < 0.05 for all vs baseline). ConclusionsThe CLASP IID trial full cohort met primary and secondary noninferiority endpoints, and at 1 year, the PASCAL system demonstrated high survival, significant MR reduction, and sustained improvements in functional and quality-of-life outcomes. Results affirm the PASCAL system as a beneficial therapy for prohibitive-surgical-risk patients with significant symptomatic DMR.

Kriging-assisted indicator-based evolutionary algorithm for expensive multi-objective optimization

Selection mechanisms based on performance indicators are popular for solving multi-objective optimization problems (MOPs), which can provide a comprehensive evaluation of the convergence and diversity of candidate solutions. However, these mechanisms recently encounter difficulties when tackling computationally expensive MOPs attributed to the restricted quantity of real function evaluations. To tackle this problem, this paper proposes a Kriging-assisted indicator-based evolutionary algorithm. The primary concept is to utilize the Kriging model to approximate computationally expensive objective functions, thereby reducing the computational cost, and to employ the R2 indicator to assess the quality of candidate solutions. In addition, a dual selection mechanism based on the lower confidence bound is proposed as the model management strategy to balance exploration and exploitation. The experimental results demonstrate that the proposed algorithm is competitive when compared to five representative algorithms.

QMLMaterial─A Quantum Machine Learning Software for Material Design and Discovery.

Structural elucidation of chemical compounds is challenging experimentally, and theoretical chemistry methods have added important insight into molecules, nanoparticles, alloys, and materials geometries and properties. However, finding the optimum structures is a bottleneck due to the huge search space, and global search algorithms have been used successfully for this purpose. In this work, we present the quantum machine learning software/agent for materials design and discovery (QMLMaterial), intended for automatic structural determination in silico for several chemical systems: atomic clusters, atomic clusters and the spin multiplicity together, doping in clusters or solids, vacancies in clusters or solids, adsorption of molecules or adsorbents on surfaces, and finally atomic clusters on solid surfaces/materials or encapsulated in porous materials. QMLMaterial is an artificial intelligence (AI) software based on the active learning method, which uses machine learning regression algorithms and their uncertainties for decision making on the next unexplored structures to be computed, increasing the probability of finding the global minimum with few calculations as more data is obtained. The software has different acquisition functions for decision making (e.g., expected improvement and lower confidence bound). Also, the Gaussian process is available in the AI framework for regression, where the uncertainty is obtained analytically from Bayesian statistics. For the artificial neural network and support vector regressor algorithms, the uncertainty can be obtained by K-fold cross-validation or nonparametric bootstrap resampling methods. The software is interfaced with several quantum chemistry codes and atomic descriptors, such as the many-body tensor representation. QMLMaterial's capabilities are highlighted in the current work by its applications in the following systems: Na20, Mo6C3 (where the spin multiplicity was considered), H2O@CeNi3O5, Mg8@graphene, Na3Mg3@CNT (carbon nanotube).

Analysis of the Effectiveness of Metaheuristic Methods on Bayesian Optimization in the Classification of Visual Field Defects.

Bayesian optimization (BO) is commonly used to optimize the hyperparameters of transfer learning models to improve the model's performance significantly. In BO, the acquisition functions direct the hyperparameter space exploration during the optimization. However, the computational cost of evaluating the acquisition function and updating the surrogate model can become prohibitively expensive due to increasing dimensionality, making it more challenging to achieve the global optimum, particularly in image classification tasks. Therefore, this study investigates and analyses the effect of incorporating metaheuristic methods into BO to improve the performance of acquisition functions in transfer learning. By incorporating four different metaheuristic methods, namely Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) Optimization, Harris Hawks Optimization, and Sailfish Optimization (SFO), the performance of acquisition function, Expected Improvement (EI), was observed in the VGGNet models for visual field defect multi-class classification. Other than EI, comparative observations were also conducted using different acquisition functions, such as Probability Improvement (PI), Upper Confidence Bound (UCB), and Lower Confidence Bound (LCB). The analysis demonstrates that SFO significantly enhanced BO optimization by increasing mean accuracy by 9.6% for VGG-16 and 27.54% for VGG-19. As a result, the best validation accuracy obtained for VGG-16 and VGG-19 is 98.6% and 98.34%, respectively.

Robust Bayesian target value optimization

We consider the problem of finding an input to a stochastic black box function such that the scalar output of the black box function is as close as possible to a target value in the sense of the expected squared error. While the optimization of stochastic black boxes is classic in (robust) Bayesian optimization, the current approaches based on Gaussian processes predominantly focus either on (i) maximization/minimization rather than target value optimization or (ii) on the expectation, but not the variance of the output, ignoring output variations due to stochasticity in uncontrollable environmental variables. In this work, we fill this gap and derive acquisition functions for common criteria such as the expected improvement, the probability of improvement, and the lower confidence bound, assuming that aleatoric effects are Gaussian with known variance. Our experiments illustrate that this setting is compatible with certain extensions of Gaussian processes, and show that the thus derived acquisition functions can outperform classical Bayesian optimization even if the latter assumptions are violated. An industrial use case in billet forging is presented.

Study of a hull form optimization system based on a Gaussian process regression algorithm and an adaptive sampling strategy, Part I: Single-objective optimization

Simulation-based design (SBD) is recognized as a hull form optimization method with great advantages, but its development process has exposed two obvious shortcomings: difficulty in uncertainty quantification (UQ) of the surrogate model and inefficiencies when solving large-scale optimization problems. To mitigate these deficiencies, this paper first proposes a UQ method for the surrogate model based on a Gaussian process regression (GPR) algorithm. Mathematical optimization results show that when the number of samples is insufficient, coupling this UQ method into the deterministic optimization process can, to some extent, reduce the uncertainty of the optimization results. The drawback of the SBD over-reliance on the surrogate model for global prediction accuracy is addressed by designing a hull form optimization system that performs the sequential sampling specifically for the region of interest. This method is referred to as sequential sampling-based optimization (SBO). It was combined with the basic properties of a GPR surrogate model, and a variety of adaptive sampling strategies suitable for the SBO optimization system were designed. Mathematical optimization results show that a hybrid optimization system, SBO-MSE + LCB, which uses the adaptive sampling strategy with the maximum squared error (MSE) and the minimum lower confidence bound (LCB) of the GPR surrogate model has the best efficiency when solving single-objective optimization problems. This method was also used for optimization design of the total resistance coefficient of a 130,000-ton deep-sea aquaculture vessel. The results show that the optimization efficiency of the SBO-MSE + LCB optimization system was improved by 46.67% with respect to that of a conventional SBD optimization system when the optimization solutions were similar, hence demonstrating the efficiency advantage of this system in practical applications.

Association of cardiopulmonary bypass with acute kidney injury in patients undergoing coronary artery bypass grafting: a retrospective cohort study.

Association of cardiopulmonary bypass with acute kidney injury in patients undergoing coronary artery bypass grafting: a retrospective cohort study.

Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism

Offline reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main methods are used: imitation learning which is suitable for expert datasets, and vanilla offline RL which often requires uniform coverage datasets. From a practical standpoint, datasets often deviate from these two extremes and the exact data composition is usually unknown. To bridge this gap, we present a new offline RL framework, called single-policy concentrability, that smoothly interpolates between the two extremes of data composition, hence unifying imitation learning and vanilla offline RL. Under this new framework, we ask: can one develop an algorithm that achieves a minimax optimal rate adaptive to unknown data composition? To address this question, we consider a lower confidence bound (LCB) algorithm developed based on pessimism in the face of uncertainty in offline RL. We study finite-sample properties of LCB as well as information-theoretic limits in multi-armed bandits, contextual bandits, and Markov decision processes (MDPs). Our analysis reveals surprising facts about optimality rates. In particular, in both contextual bandits and RL, LCB achieves a fast convergence rate for nearly-expert datasets, analogous to the one achieved by imitation learning, contrary to the slow rate achieved in offline RL. In contextual bandits, we prove that LCB is adaptively optimal for the entire data composition range, achieving a smooth transition from imitation learning to offline RL. We further show that LCB is almost adaptively optimal in MDPs.

An Efficient Method for Antenna Design Based on a Self-Adaptive Bayesian Neural Network-Assisted Global Optimization Technique

Gaussian process (GP) is a very popular machine learning method for online surrogate-model-assisted antenna design optimization. Despite many successes, two improvements are important for the GP-based antenna global optimization methods, including: 1) the convergence speed (i.e., the number of necessary electromagnetic (EM) simulations to obtain a high-performance design) and 2) the GP model training cost when there are several tens of design variables and/or specifications. In both aspects, the state-of-the-art GP-based methods show practical but not desirable performance. Therefore, a new method, called the self-adaptive Bayesian neural network surrogate-model-assisted differential evolution (DE) for antenna optimization (SB-SADEA), is presented in this article. The key innovations include: 1) the introduction of the Bayesian neural network (BNN)-based antenna surrogate modeling method into this research area, replacing GP modeling, and 2) a bespoke self-adaptive lower confidence bound (LCB) method for antenna design landscape making use of the BNN-based antenna surrogate model. The performance of SB-SADEA is demonstrated by two challenging design cases, showing considerable improvement in terms of both convergence speed and machine learning cost compared with the state-of-the-art GP-based antenna global optimization methods.

Lines optimisation of an underwater vehicle using SMOTE and adaptive minimise LCB based dynamic surrogate models

ABSTRACT The lines optimisation of an underwater vehicle based on a dynamic surrogate model is studied. Four performances including rapidity, manoeuverability, energy consumption and structure of the underwater vehicle are considered in the optimisation framework constructed by a generalised collaborative optimisation method. Expert knowledge based analytic hierarchy process is conducted to obtain the optimisation object that involves the four performances. Numerical simulation is performed to accurately analyze the rapidity, manoeuverability and structure performances of the underwater vehicle. To reduce the calculation burden, dynamic surrogate models are proposed to replace numerical simulation in the optimisation framework. To guarantee the optimisation efficiency and accuracy, a synthetic minority oversampling technique (SMOTE) and adaptive minimise lower confidence bound (LCB) are combined in constructing the dynamic surrogate models. The proposed optimisation strategy is applied to the SUBOFF model and compared with other dynamic surrogate models. Comparison results prove the advantages of the proposed dynamic surrogate model.

GOSH: Task Scheduling Using Deep Surrogate Models in Fog Computing Environments

Recently, intelligent scheduling approaches using surrogate models have been proposed to efficiently allocate volatile tasks in heterogeneous fog environments. Advances like deterministic surrogate models, deep neural networks (DNN) and gradient-based optimization allow low energy consumption and response times to be reached. However, deterministic surrogate models, which estimate objective values for optimization, do not consider the uncertainties in the distribution of the Quality of Service (QoS) objective function that can lead to high Service Level Agreement (SLA) violation rates. Moreover, the brittle nature of DNN training and the limited exploration with low agility in gradient-based optimization prevent such models from reaching minimal energy or response times. To overcome these difficulties, we present a novel scheduler that we call GOSH for Gradient Based Optimization using Second Order derivatives and Heteroscedastic Deep Surrogate Models. GOSH uses a second-order gradient based optimization approach to obtain better QoS and reduce the number of iterations to converge to a scheduling decision, subsequently lowering the scheduling time. Instead of a vanilla DNN, GOSH uses a Natural Parameter Network (NPN) to approximate objective scores. Further, a Lower Confidence Bound (LCB) optimization approach allows GOSH to find an optimal trade-off between greedy minimization of the mean latency and uncertainty reduction by employing error-based exploration. Thus, GOSH and its co-simulation based extension GOSH*, can adapt quickly and reach better objective scores than baseline methods. We show that GOSH* reaches better objective scores than GOSH, but it is suitable only for high resource availability settings, whereas GOSH is apt for limited resource settings. Real system experiments for both GOSH and GOSH* show significant improvements against the state-of-the-art in terms of energy consumption, response time and SLA violations by up to 18, 27 and 82 percent, respectively.

Estimation of predictive performance in high-dimensional data settings using learning curves

In high-dimensional prediction settings, it remains challenging to reliably estimate the test performance. To address this challenge, a novel performance estimation framework is presented. This framework, called Learn2Evaluate, is based on learning curves by fitting a smooth monotone curve depicting test performance as a function of the sample size. Learn2Evaluate has several advantages compared to commonly applied performance estimation methodologies. Firstly, a learning curve offers a graphical overview of a learner. This overview assists in assessing the potential benefit of adding training samples and it provides a more complete comparison between learners than performance estimates at a fixed subsample size. Secondly, a learning curve facilitates in estimating the performance at the total sample size rather than a subsample size. Thirdly, Learn2Evaluate allows the computation of a theoretically justified and useful lower confidence bound. Furthermore, this bound may be tightened by performing a bias correction. The benefits of Learn2Evaluate are illustrated by a simulation study and applications to omics data.

The effects of measurement errors on estimating and assessing the multivariate process capability with imprecise characteristic

In industrial environments, process capability indices are daily employed as numerical metrics to summarize the performance of a process according to a predefined set of specification limits. Neglecting gauge measurement errors is a common phenomenon in process capability evaluations by researchers in laboratory investigations and by practitioners in daily operations. However, this common negligence is far from reality regardless of the employment of highly modern measuring tools, and may notably influence the efficiency of the measuring method for assessing the performance of a manufacturing process. In this paper, a linear covariate error model is applied to investigate the effects of gauge measurement errors on the classical and fuzzy estimation approaches of the multivariate process capability index SpkT for univariate and multivariate normally distributed quality characteristics with precise specification limits. Moreover, lower confidence bounds are also derived for the yield index SpkT in the presence of measurement errors and based on a fuzzy approach. In addition to the theoretical results, extensive simulations have been conducted to analyze how the behavior of the test statistic and lower confidence bound (LCB) for assessing the performance of the process is affected by different sources of the measurement errors. The obtained results indicate that a serious underestimation of the process capability occurs when the data is contaminated with measurement errors. It is also shown that the underestimation problem is somewhat solved by taking multiple measurements from the identical item. Moreover, comparative analyses show that the proposed method is superior to Scagliarini’s method and Wang’s way such that the negative effects of errors on underestimating the LCB are reduced in the proposed plan. This paper also extends the application of the introduced method to correlated variables. Finally, three practical examples are discussed to demonstrate the use of the proposed method in industrial applications.

Multibranch Machine Learning-Assisted Optimization and Its Application to Antenna Design

To satisfy certain requirements for an antenna design, many full-wave electromagnetic (EM) simulations are required, and they involve a considerable computational burden. A multibranch machine learning-assisted optimization (MB-MLAO) method is proposed to dramatically reduce the computational complexity in this task. Then, this method is applied to antenna design and worst case performance (WCP) searching under a practical manufacturing tolerance. In the conventional Gaussian process regression (GPR)-based MLAO method, a lower confidence bound (LCB) prescreening strategy with an empirical LCB constant is used to weigh the predicted value and predicted uncertainty. Using a variable-fidelity machine learning method, an adaptive LCB variable, and a retraining and repredicting method, the proposed MB-MLAO method can strike a delicate balance between exploitation and exploration in searching. Moreover, variable-fidelity data from full-wave EM simulations are used in the multifidelity GPR machine learning method to further reduce the computational burden. Finally, two test functions and three types of antennas are selected as examples to illustrate the superiority of the proposed MB-MLAO method.

A new active learning approach for adsorbate-substrate structural elucidation in silico.

Adsorbate interactions with substrates (e.g. surfaces and nanoparticles) are fundamental for several technologies, such as functional materials, supramolecular chemistry, and solvent interactions. However, modeling these kinds of systems in silico, such as finding the optimum adsorption geometry and energy, is challenging, due to the huge number of possibilities of assembling the adsorbate on the surface. In the current work, we have developed an artificial intelligence (AI) approach based on an active learning (AL) method for adsorption optimization on the surface of materials. AL uses machine learning (ML) regression algorithms and their uncertainties to make a decision (based on a policy) for the next unexplored structures to be computed, increasing, though, the probability of finding the global minimum with a small number of calculations. The methodology allows an accurate and automated structural elucidation of the adsorbate on the surface, based on the minimization of the total electronic energy. The new AL method for adsorption optimization was developed and implemented in the quantum machine learning software/agent for material design and discovery (QMLMaterial) program and was applied for C60@TiO2 anatase (101). It marks another software extension with a new feature in addition to the automatic structural elucidation of defects in materials and of nanoparticles as well. SCC-DFTB calculations were used to build the complex search surfaces with a reasonably low computational cost. An artificial neural network (NN) was employed in the AL framework evaluated together with two uncertainty quantification methods: K-fold cross-validation and non-parametric bootstrap (BS) resampling. Also, two different acquisition functions for decision-making were used: expected improvement (EI) and the lower confidence bound (LCB).

A Randomized Comparison of the Healing Response Between the Firehawk Stent and the Xience Stent in Patients With ST-Segment Elevation Myocardial Infarction at 6 Months of Follow-Up (TARGET STEMI OCT China Trial): An Optical Coherence Tomography Study.

BackgroundThe healing response of the Firehawk stent in patients with ST-segment elevation myocardial infarction (STEMI) remains unclear.AimWe compared the vascular healing of a biodegradable polymer sirolimus-eluting stent (Firehawk) vs. a durable polymer everolimus-eluting stent (Xience) at 6 months after percutaneous coronary intervention (PCI) in patients with STEMI.MethodsIn this prospective, multicenter, randomized, non-inferiority study, patients within 12 h of STEMI onset were randomized in a ratio of 1:1 to receive Firehawk or Xience stents. Optical coherence tomography (OCT) follow-up was performed 6 months after the index procedure and assessed frame by frame. The primary endpoint was the neointimal thickness (NIT) at 6 months evaluated by OCT. The safety endpoint was target lesion failure (TLF) at 12 months.ResultsThe Firehawk stent was non-inferior to the Xience stent in terms of the neointimal thickness (73.03 ± 33.30 μm vs. 78.96 ± 33.29 μm; absolute difference: −5.94 [one-sided 95% lower confidence bound: −23.09]; Pnon−inferiority < 0.001). No significant difference was observed between the Firehawk and Xience groups regarding the percentage of uncovered struts (0.55 [0.08, 1.32]% vs. 0.40 [0.21, 1.19]%, P = 0.804), the percentage of malapposed struts (0.17 [0.00, 1.52]% vs. 0.17 [0.00, 0.69]%, P = 0.662), and the healing score (1.56 [0.23, 5.74] vs. 2.12 [0.91, 3.81], P = 0.647). At 12 months, one patient in the Firehawk group experienced a clinically indicated target lesion revascularization. No other TLF events occurred in both groups. Independent risk factors of the NIT included body mass index, hyperlipidemia, B2/C lesions, thrombus G3–G5, thrombus aspiration, and postdilation pressure.ConclusionIn patients with STEMI, Firehawk was non-inferior to Xience in vascular healing at 6 months. Both stents exhibited nearly complete strut coverage, moderate neointimal formation, and minimal strut malapposition.Clinical Trial NumberNCT04150016.