Extrapolation Scenarios Research Articles

Data-driven analysis of bonding strength in laser-structured metal-GFRP hybrid joints via groove morphology

Abstract This study aims to enhance predictions of the mechanical properties of mechanically interlocked hybrid joints by employing machine learning techniques coupled with feature engineering of cross-sectional groove morphology. Unlike mechanical fastening, which promotes localized stress, and adhesive bonding, which requires prolonged contaminant removal, mechanically interlocked joints offer a distinct advantage by eliminating the need for either. The mechanically interlocked joints in this study combine glass fiber reinforced composite fabricated via injection molding, with cold rolled steel structured by a nanosecond laser. Through optical microscopy, crucial groove dimensions such as depth and width are identified for feature extraction. Domain-specific feature engineering is employed to improve predictive accuracy, integrated with existing regression models. The concept of “structure density,” initially defined as groove width over hatch distance, is expanded during feature engineering to include additional relevant features over hatch distance. Experimental investigations identified optimal laser parameters for shear strength, yielding a maximum single lap shear strength of 33.3 MPa under specific conditions. The third polynomial regression model incorporating structure density features emerged as the most effective in predicting shear strength, demonstrating high accuracy in both interpolation and extrapolation scenarios. The study suggests potential cost savings by utilizing surface topography for shear strength prediction, with implications for industries amidst the increasing prevalence of composite materials.

Physics-informed ensemble learning with residual modeling for enhanced building energy prediction

Accurate modeling of building energy use is important to support a diverse spectrum of its downstream applications, such as building energy efficiency assessment, resilience analysis, smart control, etc. As mainstream approaches of building energy modeling, physics-based modeling builds on different fidelities of physics rules yet are usually compromised in modeling accuracy due to insufficiency of physics rules to capture real-world dynamics and incomplete input information. Data-driven approaches are computationally efficient, but black box (uninterpretable) in nature. For improved modeling of building energy use, this work proposes a physics-informed ensemble learning approach in building energy prediction through residual modeling. Specifically, we first analyze the components of building energy use data. Evidence suggests that the building energy use data can be decomposed into physics-driven part, occupant-driven part, and white noise. Second, high-fidelity physics-based building models (EnergyPlus) and low-fidelity ones (RC models) are developed to capture the physics-driven part while time series methods are explored as the residual modeling approach to capture the occupant-driven discrepancies between physics-based simulation and measured building energy use (i.e., residuals). Finally, the physics-informed ensemble learning is proposed to integrate physics-based and data-driven models for enhanced accuracy and robustness of building energy modeling. Results demonstrate 40–90% increase of accuracy between modeling and field observations compared to traditional physics-based modeling methods. Moreover, when the training dataset size is small, the proposed ensemble model overperforms the pure data-driven models, demonstrating its higher robustness in extrapolation scenarios. This work makes fundamental contributions to the development of convergent modeling approaches in the building modeling field.

A comparative study of predicting high entropy alloy phase fractions with traditional machine learning and deep neural networks

Predicting phase stability in high entropy alloys (HEAs), such as phase fractions as functions of composition and temperature, is essential for understanding alloy properties and screening desirable materials. Traditional methods like CALPHAD are computationally intensive for exploring high-dimensional compositional spaces. To address such a challenge, this study explored and compared the effectiveness of random forests (RF) and deep neural networks (DNN) for accelerating materials discovery by building surrogate models of phase stability prediction. For interpolation scenarios (testing on the same order of system as trained), RF models generally produce smaller errors than DNN models. However, for extrapolation scenarios (training on lower-order systems and testing on higher order systems), DNNs generalize more effectively than traditional ML models. DNN demonstrate the potential to predict topologically relevant phase composition when data were missing, making it a powerful predictive tool in materials discovery frameworks. The study uses a CALPHAD dataset of 480 million data points generated from a custom database, available for further model development and benchmarking. Experiments show that DNN models are data-efficient, achieving similar performance with a fraction of the dataset. This work highlights the potential of DNNs in materials discovery, providing a powerful tool for predicting phase stability in HEAs, particularly within the Cr-Hf-Mo-Nb-Ta-Ti-V-W-Zr composition space.

Revisiting Tensor Basis Neural Network for Reynolds stress modeling: Application to plane channel and square duct flows

Recent advances in computing power devoted to Computational Fluid Dynamics (CFD) have opened up a new avenue for addressing the turbulence closure problem through Machine Learning (ML). Several Tensor Basis Neural Network (TBNN) frameworks aimed at enhancing turbulence Reynolds-Averaged Navier–Stokes (RANS) modeling have recently been proposed in the literature as data-driven constitutive models for systems with known invariance properties. However, persistent ambiguities remain regarding the physical adequacy of applying the General Eddy Viscosity Model (GEVM) within these frameworks. This work aims at investigating this aspect in an a priori stage for better predictions of the Reynolds stress anisotropy tensor, while preserving the Galilean and rotational invariances. In particular, we propose a general framework providing optimal tensor basis models for two types of canonical flows with increasing complexity: Plane Channel Flow (PCF) and Square Duct Flow (SDF). Subsequently, deep neural networks based on these optimal models are trained using state-of-the-art strategies to achieve a balanced and physically sound prediction of the full anisotropy tensor. A priori results obtained by the proposed framework are in very good agreement with the reference Direct Numerical Simulations (DNS) data. Notably, our shallow network with three layers excels in providing accurate predictions of the anisotropy tensor for PCF at unobserved friction Reynolds numbers, both in interpolation and extrapolation scenarios. The learning of the SDF case is more challenging because of its physical nature but also due to a lack of training data at various regimes. We propose a numerical strategy to alleviate this problem based on Transfer Learning (TL). In order to more efficiently generalize to an unseen intermediate Reτ regime, we take advantage of our prior knowledge acquired from a training with a larger and wider dataset. Our results indicate the potential of the developed network model, and demonstrate the feasibility and efficiency of the TL process in terms of training data size and training time. Based on these results, we believe there is a promising future by integrating these neural networks into an adapted in-house RANS solver.

Physics-constrained cooperative learning-based reference models for smart management of chillers considering extrapolation scenarios

Smart management of building energy devices, including their optimal control and fault detection technology, is of great significance to building energy conservation. The core of smart management is the development of reference models for target energy device. However, existing reference models show poor extrapolation ability when the operation conditions of online data are outside the scope of training data. To tackle this problem, here we propose a novel physics-constrained cooperative learning framework to train multiple reference models in a cooperative manner in order to improve their extrapolation ability. The general idea of cooperative learning is to constrain the output of different reference models on unknown operation conditions such that the physical inconsistent loss is minimized. In this study, two novel physical inconsistent losses, including energy conservation inconsistent loss and mass conservation inconsistent loss, are designed for seven output reference variables of chiller, forming the physics-constrained cooperative neural networks (PCNNs). Comprehensive data experiments are conducted to compare the model performance of PCNNs with other machine learning models, including Support Vector Machine (SVM), Random Forest (RF), and Artificial Neural Network (ANN). The experimental results showed that the PCNNs outperformed the other models under extrapolation scenarios, showing a lager performance improvement of mean absolute error (MAE) and root mean squared error (RMSE) metrics with 26.94% and 23.49%, respectively. The proposed physics-constrained cooperative learning framework might provide a new perspective for the development of reference models in building energy system.

Pervasive impacts of climate change on the woodiness and ecological generalism of dry forest plant assemblages

Abstract Climate emergency is a significant threat to biodiversity in the 21st century, but species will not be equally affected. In summing up the responses of different species at the local scale, we can assess changes in the species quantity and composition of biotic assemblages. We used more than 420K curated occurrence records of 3060 plant species to model current and future patterns of plant species distribution in one of the world's largest tropical dry forests—the Caatinga. While allowing different model extrapolation scenarios, we estimated potential changes in the species richness and composition of dryland plant assemblages in response to projected climate change, and assessed how the ecological generalism and woodiness of plant assemblages can be impacted by the climate crisis. More than 99% of plant assemblages were projected to lose species by 2060, with biotic homogenisation—the decrease in spatial beta diversity—forecasted in 40% of the Caatinga. The replacement of narrow‐range woody species by wide‐range non‐woody ones should impact at least 90% of Caatinga plant assemblages. The exacerbated species loss in the dryland plant assemblages was connected to the heterogenisation and homogenisation of biotic assemblages. Still, the magnitude of climate change impacts on ecological generalism and woodiness patterns of dryland plant assemblages differ according to the direction of the biotic change process. Synthesis. The future increase in aridity will change the patterns of woodiness and ecological generalism of tropical dry forest plant assemblages by decreasing vegetation diversity and complexity. The projected biotic changes in dryland plant assemblages indicate the erosion of ecosystem services linked to biomass productivity and carbon storage. We highlight the importance of long‐term conservation planning for maintaining tropical dry forests.

Inferring electrochemical performance and parameters of Li-ion batteries based on deep operator networks

Li-ion battery is a complex physicochemical system that generally takes observable current and terminal voltage as input and output, while leaving some unobservable quantities, e.g., Li-ion concentration, for serving as internal variables (states) of the system. On-line estimation for the unobservable states plays a key role in battery management system since they reflect battery safety and degradation conditions. Several kinds of models that map from current to voltage have been established for state estimation, such as accurate but inefficient physics-based models, and efficient but sometimes inaccurate equivalent circuit and black-box models. To realize accuracy and efficiency simultaneously in battery modeling, we propose to build a data-driven surrogate for a battery system while incorporating the underlying physics as constraints. In this work, we innovatively treat the functional mapping from current curve to terminal voltage as a composite of operators, which is approximated by the powerful deep operator network (DeepONet). Its learning capability is firstly verified through a predictive test for Li-ion concentration at two electrodes. In this experiment, the physics-informed DeepONet is found to be more robust than the purely data-driven DeepONet, especially in temporal extrapolation scenarios. A composite surrogate is then constructed for mapping current curve and solid diffusivity to terminal voltage with three operator networks, in which two parallel physics-informed DeepONets are firstly used to predict Li-ion concentration at two electrodes, and then based on their surface values, a DeepONet is built to give terminal voltage predictions. Since the surrogate is differentiable anywhere, it is endowed with the ability to learn from data directly, which was validated by using terminal voltage measurements to estimate input parameters. The proposed surrogate built upon operator networks possesses great potential to be applied in on-board scenarios, since it integrates efficiency and accuracy by incorporating underlying physics, and also leaves an interface for model refinement through a totally differentiable model structure.

Evaluation and quantification of compressor model predictive capabilities under modulation and extrapolation scenarios

Testing and evaluation of select semi-empirical and black-box compressor models is carried out to quantify performance in modulation (variable speed), extrapolation, and additionally, variable superheat scenarios. Three representative literature models and an artificial neural network (ANN) model are benchmarked against the industry standard AHRI model. A methodology quantifying model performance, compared against experimental data, in said scenarios is presented. High-fidelity test data taken from either a hot-gas bypass load stand or compressor calorimeter. Scroll, screw, reciprocating, and spool compressor technologies were collected with R410A, R1234ze(E), R134a, and R32 refrigerants totaling 434 experimental points. Data is divided into training, extrapolation, variable speed, and variable superheat data splits to examine model performance. Mean Absolute Percentage Error (MAPE) is computed for mass flow rate and power after training models with training data and evaluating them against the other data splits. Two literature models are true semi-empirical formulations while the other, the ANN, and AHRI model are more empirical in nature. Neither semi-empirical model predicted all compressors. When the compressor type is predicted, the semi-empirical models yield MAPE’s less than 8%, 5%, and 4% for mass flow rate and power prediction in extrapolation, modulation, and variable superheat scenarios, respectively. The exception is the Popovic and Shapiro model performing at 21% MAPE in variable superheat power prediction for the spool compressor with R1234ze(E). The ANN showed highest errors of 9.3%, 12%, and 17% in extrapolation, modulation, and variable superheat scenarios, respectively. All models outperformed the AHRI model by several orders of magnitude in these scenarios.

How Does Knowledge Graph Embedding Extrapolate to Unseen Data: A Semantic Evidence View

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r, ?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://github.com/renli1024/SE-GNN.

Cost-effectiveness of a transdiagnostic psychotherapy program for youth with common mental health problems

ObjectivesOur objective was to evaluate the cost-effectiveness of the transdiagnostic psychotherapy program Mind My Mind (MMM) for youth with common mental health problems using a cost-utility analysis (CUA) framework and data from a randomized controlled trial. Furthermore, we analyzed the impact of the choice of informant for both quality-of-life reporting and preference weights on the Incremental Cost-Effectiveness Ratio (ICER).MethodsA total of 396 school-aged (6–16 years) youth took part in the 6-month trial carried out in Denmark. CUAs were carried out for the trial period and four one-year extrapolation scenarios. Costs were based on a combination of budget and self-reported costs. Youths and parents were asked to report on the youth’s quality-of-life three times during the trial using the Child Health Utility 9D (CHU9D). Parental-reported CHU9D was used in the base case together with preference weights of a youth population. Analyses using self-reported CHU9D and preference weights of an adult population were also carried out.ResultsThe analysis of the trial period resulted in an ICER of €170,465. The analyses of the one-year scenarios resulted in ICERs between €23,653 and €50,480. The ICER increased by 24% and 71% compared to the base case when using self-reported CHU9D and adult preference weights, respectively.ConclusionThe MMM intervention has the potential to be cost-effective, but the ICER is dependent on the duration of the treatment effects. Results varied significantly with the choice of informant and the choice of preference weights indicating that both factors should be considered when assessing CUA involving youth.

Extrapolation and dosing recommendations for raxibacumab in children from birth to age

The US Food and Drug Administration's Animal Rule allows for the approval of drugs when human efficacy studies are not ethical. While the therapeutic doses of raxibacumab, a monoclonal antibody for the prophylaxis and treatment of inhalational anthrax, have been based on pharmacokinetic data from adult subjects, its disposition in children has not been investigated in clinical trials. Here we evaluate the effect of demographic covariates and maturation processes on the pharmacokinetics of raxibacumab and explore opportunities for the optimisation of paediatric doses. A population pharmacokinetic model was used as basis for the extrapolation of raxibacumab disposition from adults to children. Different extrapolation scenarios, including weight-banded dosing regimens, were considered to assess the effect of growth and maturation on the pharmacokinetic parameters of interest. Area under the concentration-time curve, maximum plasma concentration and the time of serum raxibacumab concentrations greater than or equimolar to the highest serum protective antigen concentrations observed for at least 28 days in any monkey challenged with Bacillus anthracis that died were derived and compared with the currently approved US doses. Based on practical considerations, a weight-banded dosing regimen consisting of 4 dose levels (75 mg/kg for individuals ≤1.5kg, 55 mg/kg for individuals <10kg, 45 mg/kg for individuals <50 kg, 40 mg/kg for all individuals >50 kg) was required to optimise target exposure across the paediatric population. Age-related maturation processes may affect raxibacumab clearance in very young patients. The proposed dosing regimens take into account effects of body weight and maturation processes on the elimination of raxibacumab.

Water Demand Prediction Using Machine Learning Methods: A Case Study of the Beijing–Tianjin–Hebei Region in China

Predicting water demand helps decision-makers allocate regional water resources efficiently, thereby preventing water waste and shortage. The aim of this study is to predict water demand in the Beijing–Tianjin–Hebei region of North China. The explanatory variables associated with economy, community, water use, and resource availability were identified. Eleven statistical and machine learning models were built, which used data covering the 2004–2019 period. Interpolation and extrapolation scenarios were conducted to find the most suitable predictive model. The results suggest that the gradient boosting decision tree (GBDT) model demonstrates the best prediction performance in the two scenarios. The model was further tested for three other regions in China, and its robustness was validated. The water demand in 2020–2021 was provided. The results show that the identified explanatory variables were effective in water demand prediction. The machine learning models outperformed the statistical models, with the ensemble models being superior to the single predictor models. The best predictive model can also be applied to other regions to help forecast water demand to ensure sustainable water resource management.

Cost-Effectiveness of Initial Versus Delayed Lanreotide for Treatment of Metastatic Enteropancreatic Neuroendocrine Tumors.

The Controlled Study of Lanreotide Antiproliferative Response in Neuroendocrine Tumors (CLARINET) trial showed prolonged progression-free survival in patients initially treated with lanreotide versus placebo. We evaluated the cost-effectiveness of upfront lanreotide versus active surveillance with lanreotide administered after progression in patients with metastatic enteropancreatic neuroendocrine tumors (NETs), both of which are treatment options recommended in NCCN Clinical Practice Guidelines in Oncology for Neuroendocrine and Adrenal Tumors. We developed a Markov model calibrated to the CLARINET trial and its extension. We based the active surveillance strategy on the CLARINET placebo arm. We calculated incremental cost-effectiveness ratios (ICERs) in dollars per quality-adjusted life-year (QALY). We modeled lanreotide's cost at $7,638 per 120 mg (average sales price plus 6%), used published utilities (stable disease, 0.77; progressed disease, 0.61), adopted a healthcare sector perspective and lifetime time horizon, and discounted costs and benefits at 3% annually. We examined sensitivity to survival extrapolation and modeled octreotide long-acting release (LAR) ($6,183 per 30 mg). We conducted one-way, multiway, and probabilistic sensitivity analyses. Upfront lanreotide led to 5.21 QALYs and a cost of $804,600. Active surveillance followed by lanreotide after progression led to 4.84 QALYs and a cost of $590,200, giving an ICER of $578,500/QALY gained. Reducing lanreotide's price by 95% (to $370) or 85% (to $1,128) per 120 mg would allow upfront lanreotide to reach ICERs of $100,000/QALY or $150,000/QALY. Across a range of survival curve extrapolation scenarios, pricing lanreotide at $370 to $4,000 or $1,130 to $5,600 per 120 mg would reach ICERs of $100,000/QALY or $150,000/QALY, respectively. Our findings were robust to extensive sensitivity analyses. The ICER modeling octreotide LAR is $482,700/QALY gained. At its current price, lanreotide is not cost-effective as initial therapy for patients with metastatic enteropancreatic NETs and should be reserved for postprogression treatment. To be cost-effective as initial therapy, the price of lanreotide would need to be lowered by 48% to 95% or 27% to 86% to reach ICERs of $100,000/QALY or $150,00/QALY, respectively.

A Kernel Design Approach to Improve Kernel Subspace Identification

Subspace identification methods, such as canonical variate analysis (CVA), are noniterative tools suitable for the state-space modeling of multi-input, multi-output processes, e.g., industrial processes, using input-output data. To learn nonlinear system behavior, kernel subspace techniques are commonly used. However, the issue of kernel design must be given more attention because the type of kernel can influence the kind of nonlinearities that the model can capture. In this article, a new kernel design is proposed for CVA-based identification, which is a mixture of a global and local kernel to enhance generalization ability and includes a mechanism to vary the influence of each process variable into the model response. During validation, model hyper-parameters were tuned using random search. The overall method is called feature-relevant mixed kernel CVA (FR-MKCVA). Using an evaporator case study, the trained FR-MKCVA models show a better fit to observed data than those of single-kernel CVA, linear CVA, and neural net models under both interpolation and extrapolation scenarios. This work provides a basis for future exploration of deep and diverse kernel designs for system identification.

A comparison of the effect of empirical and physical modeling approaches to extrapolation capability of compressor models by uncertainty analysis: A case study with common semi-empirical compressor mass flow rate models

Some semi-empirical compressor models are claimed to be more accurate at extrapolation conditions than their empirical counterparts which have a long history of industrial applications due to their uses of physical principles, but it is unknown how much improvement the principles can bring to the modeling of extrapolation scenarios quantitatively. This paper studies the effect of the number of empirical coefficients and physical principles on model accuracy and uncertainty by comparing the estimation of five regression models of compressor mass flow rates. The choice of model training data follows the industrial norm, and model accuracy and uncertainty are calculated. The quantitative results show that the use of neither empirical coefficients nor physical principles guarantees good accuracy and reliability. If a coefficient is redundant to explain the behavior of the phenomenon, regardless of its empirical or physical origin, it should be removed to reduce model inaccuracy in extrapolation scenarios.

Sediment quality in a metal-contaminated tropical bay assessed with a multiple lines of evidence approach

A sediment quality assessment was performed near to the main industrial source of metal contamination in Sepetiba Bay, Brazil, which represents one of the worst cases of trace metal contamination reported for coastal areas. Acute and chronic toxicity tests, benthic fauna community analysis and metal bioavailability evaluations were applied to identify risks to the benthic community. Significant amphipod mortality was observed close to the major pollution source and lower copepod fertility was observed for all stations. Equilibrium-partitioning and biotic-ligand models to predict pore water metal toxicity, which were based on acid-volatile sulfide (AVS) and organic carbon fraction (fOC) normalization approaches, suggested that metals are not likely to be available in sediment pore water. However, Cd, Pb and Zn concentrations were mainly (>50%) weakly bound to sediments, suggesting high potential bioavailability. Linking the chemical results with ecotoxicological responses, we observed that sediment-feeding organisms presented acute and chronic toxicities that were positively correlated to the metal concentrations in the sediments. Additionally, benthic fauna composition was dominated by tolerant species, revealing a trophic structure response to environmental contamination. These results reinforce the necessity of a multiple lines of evidence approach to establish sediment quality and to support environmental management decisions that are based on observed effects and potential extrapolation scenarios into the future.

Ensemble engineering and statistical modeling for parameter calibration towards optimal design of microbial fuel cells

Abstract Mathematical modeling is an important tool to investigate the performance of microbial fuel cell (MFC) towards its optimized design. To overcome the shortcoming of traditional MFC models, an ensemble model is developed through integrating both engineering model and statistical analytics for the extrapolation scenarios in this study. Such an ensemble model can reduce laboring effort in parameter calibration and require fewer measurement data to achieve comparable accuracy to traditional statistical model under both the normal and extreme operation regions. Based on different weight between current generation and organic removal efficiency, the ensemble model can give recommended input factor settings to achieve the best current generation and organic removal efficiency. The model predicts a set of optimal design factors for the present tubular MFCs including the anode flow rate of 3.47 mL min −1 , organic concentration of 0.71 g L −1 , and catholyte pumping flow rate of 14.74 mL min −1 to achieve the peak current at 39.2 mA. To maintain 100% organic removal efficiency, the anode flow rate and organic concentration should be controlled lower than 1.04 mL min −1 and 0.22 g L −1 , respectively. The developed ensemble model can be potentially modified to model other types of MFCs or bioelectrochemical systems.

Filling Disocclusions in Extrapolated Virtual Views Using Hybrid Texture Synthesis

For glasses-free 3-D viewing, autostereoscopic displays provide a dense set of views showing a scene from slightly different viewpoints. As the number of views and their spatial positions are display dependent, a generic depth-enhanced multiview video plus depth format is used for coding and transmission. From this, the required views are generated via depth image-based rendering (DIBR) techniques by using original views and associated depth information. A critical problem in the DIBR techniques is that texture regions, which are covered by foreground objects in the original image, may become visible in the synthesized view, especially in extrapolation scenarios. To cover these disoccluded areas, a novel hybrid texture synthesis method is described in this paper. Our approach combines a new patch-based and a novel fast parametric texture synthesis method in an innovative way to compute the disoccluded image areas. The proposed method outperforms state-of-the-art approaches in terms of peak signal-to-noise ratio, structural similarity, visual saliency induced index, feature similarity index (color), and run-time.

Cost-effectiveness of adjunctive eptifibatide in patients undergoing coronary stenting in Germany

To determine the cost-effectiveness of adding eptifibatide to the standard treatment for selected high-risk patients undergoing coronary stenting in Germany. Furthermore, to investigate the impact of several extrapolation methods on the results. A Markov model was developed to reflect the clinical events in this specific patient population, including target vessel revascularization, myocardial infarction, and death. To extrapolate clinical data beyond 1 year, a linear, an exponential, and a Weibull survival curves were estimated. Patient characteristics and transition probabilities were derived from a high-risk subgroup of the ESPRIT trial; patient-level utility data came from a published Dutch study. Costs were calculated from a hospital and from a third-party payer perspective. For both perspectives, the additional treatment with eptifibatide is the considered dominant alternative. The incremental net benefit of its use exceeds €10,000 for both perspectives. Results proved stable in probabilistic sensitivity analysis as well as under the different extrapolation scenarios. Eptifibatide is likely to be dominant strategy with 77.7 and 96.7% of the simulations leading to QALYs gained and generating cost savings from both the hospital and the third-party payer perspective. Eptifibatide offsets its additional treatment costs by avoiding costly repeat procedures and leads to positive QALY gains by preventing cardiovascular events lending themselves to transient or permanent lower quality of life. The method used to extrapolate the short-term risks did not impact on results, mainly due to similar clinical risk profiles between the two treatment groups in the long term.