Tool For Estimation Research Articles

Battery Remaining Useful Life Estimation based on Particle Swarm Optimization-Neural Network

Determining the Remaining Useful Life (RUL) of a battery is essential for several purposes, including proactive maintenance planning, optimizing resource allocation, preventing unforeseen failures, improving safety, extending battery lifespan, and achieving accurate cost savings. Concerning that matter, this study proposed hybrid Particle Swarm Optimization–Neural Network (PSO-NN) for estimating battery RUL. In the evaluation of the proposed method, the effectiveness is assessed using the metrics of Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The dataset employed for this investigation comprises eight input parameters and one output variable, representing the battery RUL. In conducting an analysis, the performance of the PSO-NN model is compared with hybrid NN with Cultural Algorithm (CA-NN) and Harmony Search Algorithm (HSA-NN), as well as the standalone Autoregressive Integrated Moving Average (ARIMA). Upon examination of the findings, it becomes evident that the PSO-NN model outperforms the alternatives with an MAE of 2.7708 and an RMSE of 4.3468, significantly lower than HSA-NN (MAE: 22.0583, RMSE: 34.5154), CA-NN (MAE: 9.1189, RMSE: 22.4646), and ARIMA (MAE: 494.6275, RMSE: 584.3098). The PSO-NN also achieves the lowest maximum error of 104.7381 compared to 490.3125 for HSA-NN, 827.0163 for CA-NN, and 1,160.0000 for ARIMA. Additionally, the low two-tail probability values (P(T≤t)), all below the significance level of 0.05, indicate that the differences between PSO-NN and the other methods (HSA-NN, CA-NN, and ARIMA) are statistically significant. These results highlight the superior accuracy and robustness of the PSO-NN model in predicting battery RUL. This study contributes to the field by presenting the PSO-NN as a highly effective tool for accurate battery RUL estimation, as evidenced by its superior performance over alternative methods.

Parameter Estimation of Proton Exchange Membrane Fuel Cells Using Chaotic Newton-Raphson-Based Optimizer

This paper presents a novel improved metaheuristic algorithm, Chaotic Newton-Raphson-Based Optimizer (CNRBO), for the Proton Exchange Membrane Fuel Cells (PEMFCs) parameter extraction problem. In this study, ten distinct chaotic maps are integrated within the Newton-Raphson-based optimizer (NRBO) to improve its performance. The chaotic maps are employed to define the probability of the trap avoidance operator (TAO). The proposed CNRBO algorithm is validated using standard benchmark optimization problems. Results proved its advantages over the standard NRBO algorithm in terms of accuracy, robustness, and convergence speed. For PEMFC parameters extraction using the proposed CNRBO algorithm, the objective function to be minimized is the sum of squared errors (SSE) between estimated and measured stack voltages across various data points. To validate the effectiveness and reliability of the proposed CNRBO, its performance is compared with recent algorithms on eight different PEMFC stack models including NedStackPS6, BCS 500W, Horizon 500W, 250W stack, Avista SR-12 500W, Temasek 1KW, Ballard Mark V 5KW and Horizon H-1000XP stack. Statistical measures are employed to assess the superiority and robustness of the proposed CNRBO. Statistical analyses demonstrate that the proposed CNRBO algorithm outperforms existing algorithms in terms of accuracy, search capability, and convergence speed, solidifying its position as a powerful tool for PEMFC parameter estimation.

Exploring sexual dimorphism through palatal rugae analysis in the Javanese population of Surabaya, Indonesia

This study investigates the potential of palatal rugae patterns as a tool for sex estimation in the Javanese population of Surabaya, Indonesia. Palatal rugae on the anterior part of the maxillary mucosa exhibit unique characteristics that make them valuable for forensic identification. Through a cross-sectional study involving 60 Javanese individuals, the research examines the prevalence of various palatal rugae patterns and their correlation with sex. Results indicate significant distinctions in rugae patterns between males and females, particularly in diverging, converging, and circular patterns. A discriminant function analysis is employed to establish an equation for sex estimation using palatal rugae patterns specific to the Javanese population. Overall, the study suggests that palatal rugae patterns hold promise as a supplementary method for sex estimation in forensic science, though further research with larger sample sizes is recommended for conclusive results.

The mouse gingiva and HIF-1α, a key gene of hypoxic environment, as tools for post-mortem time estimation.

The post-mortem interval (PMI) is the time elapsed between the death of an individual and its forensic examination. It is a crucial information for judicial authorities, but current techniques still cannot establish a precise time interval. Novel approaches are therefore required. Recently, gingival tissue has emerged as interesting for forensic analysis thanks to the protection offered by lips to this tissue, limiting the influence of environmental factors. It is also easily accessible, and its sampling is minimally invasive even in the presence of rigor mortis. Moreover, the expression of HIF-1α, a master mediator of the hypoxic environment, has been described in gingival samples at different post-mortem (PM) times. We have hypothesized that the time-dependent post-mortem expression of HIF-1α could serve as a biomarker to more accurately predict the PMI. Our analyses were performed in an animal model, the mouse, where environment can be precisely controlled. Therewith, gingival tissue morphology was evaluated through histochemical staining and HIF-1α expression was analyzed by qPCR, western blots and immunofluorescence at different post-mortem times (0h to 100h). Our results showed (a) a global post-mortem stability of gingival tissue (b) a rapid increase in HIF-1α mRNA expression in the short post-mortem times followed by a slow decrease in transcript expression until 100h PM (c) an expression of the HIF- 1α protein and its degradation products, that follows the mRNA pattern (d) the presence of HIF-1α protein in the epithelial and connective layers of the tissue, with signal accumulation in both gingival strata until at least 32h post-mortem. This pilot study thus validated the mouse and the gingival tissue as models for post-mortem analyses, as well as for studying the fate of proteins such as HIF-1α. Transferring these approaches to human subjects may provide a more accurate estimate of PMI.

A new tool for estimation of the in vivo distribution of intake radionuclides.

This study developed a more universal tool for estimating the in vivo distribution of intake radionuclides. The biokinetic models and transfer rates for intake radionuclides were cited from the publications of the International Commission on Radiological Protection (ICRP), and the models were transformed into a series of linear differential equations and numerically solved using the Scipy algorithm in Python. The user interfaces for model selection, data input and in vivo distribution calculations were designed using PyQt5. The calculation results of the new tool are completely consistent with those of the data viewer released by the ICRP and are also very similar to other reported values. The new tool allows users to select and change the biokinetic models and transfer rates and display the in vivo distribution of radionuclides in an image format. It is much more user friendly.

Large-Scale Parameter Estimation for Crystal Structure Prediction. Part 1: Dataset, Methodology, and Implementation.

Crystal structure prediction (CSP) seeks to identify all thermodynamically accessible solid forms of a given compound and, crucially, to establish the relative thermodynamic stability between different polymorphs. The conventional hierarchical CSP workflow suggests that no single energy model can fulfill the needs of all stages in the workflow, and energy models across a spectrum of fidelities and computational costs are required. Hybrid ab initio/empirical force-field (HAIEFF) models have demonstrated a good balance of these two factors, but the force-field component presents a major bottleneck for model accuracy. Existing parameter estimation tools for fitting this empirical component are inefficient and have severe limitations on the manageable problem size. This, combined with a lack of reliable reference data for parameter fitting, has resulted in development in the force-field component of HAIEFF models having mostly stagnated. In this work, we address these barriers to progress. First, we introduce a curated database of 755 organic crystal structures, obtained using high quality, solid-state DFT-D calculations, which provide a complete set of geometry and energy data. Comparisons to various theoretical and experimental data sources indicate that this database provides suitable diversity for parameter fitting. In tandem, we also put forward a new parameter estimation algorithm implemented as the CrystalEstimator program. Our tests demonstrate that CrystalEstimator is capable of efficiently handling large-scale parameter estimation problems, simultaneously fitting as many as 62 model parameters based on data from 445 structures. This problem size far exceeds any previously reported works related to CSP force-field parametrization. These developments form a strong foundation for all future work involving parameter estimation of transferable or tailor-made force-fields for HAIEFF models. This ultimately opens the way for significant improvements in the accuracy achieved by the HAIEFF models.

An optimal transformation method for inferring ocean tracer sources and sinks

Abstract. The geography of changes in the fluxes of heat, carbon, freshwater and other tracers at the sea surface is highly uncertain and is critical to our understanding of climate change and its impacts. We present a state estimation framework wherein prior estimates of boundary fluxes can be adjusted to make them consistent with the evolving ocean state. In this framework, we define a discrete set of ocean water masses distinguished by their geographical, thermodynamic and chemical properties for specific time periods. Ocean circulation then moves these water masses in geographic space. In phase space, geographically adjacent water masses are able to mix together, representing a convergence, and air–sea property fluxes move the water masses over time. We define an optimisation problem whose solution is constrained by the physically permissible bounds of changes in ocean circulation, air–sea fluxes and mixing. As a proof-of-concept implementation, we use data from a historical numerical climate model simulation with a closed heat and salinity budget. An inverse model solution is found for the evolution of temperature and salinity that is consistent with “true” air–sea heat and freshwater fluxes which are introduced as model priors. When biases are introduced into the prior fluxes, the inverse model finds a solution closer to the true fluxes. This framework, which we call the optimal transformation method, represents a modular, relatively computationally cost-effective, open-source and transparent state estimation tool that complements existing approaches.

Investigation of Radioxenon Probability Density Functions at IMS Radionuclide Stations Using a Monte Carlo Method for Background Estimation

Abstract The International Monitoring System, the primary means of verification of the Comprehensive Nuclear-Test-Ban Treaty, monitors the planet for any sign of a nuclear explosion. Regarding the International Monitoring System radionuclide stations, it is known that radioxenon released from nuclear facilities such as medical isotope production facilities and nuclear power plants influences the stations. For the purposes of monitoring nuclear explosions, it is important to better understand the radioxenon background based on these nuclear facilities. The probability density functions of background activity concentration at IMS radionuclide stations are estimated using a Monte Carlo method based on emissions from known nuclear facilities and source receptor sensitivity data. This paper describes two case studies of radioxenon detections at radionuclide stations applying the developed approach. This method could be one of several prospective approaches to predict the activity concentrations of isotopes of radioxenon at radionuclide stations in Comprehensive Nuclear Test-Ban Treaty Organization’s (CTBTO’s) prototype xenon background estimation tool software. It can also be used in characterization of CTBT-relevant nuclear events for expert technical analysis. Plain Language Summary Civil nuclear power stations and medical isotope production facilities release radioisotopes of xenon during their normal operations. These emissions would make it harder to detect xenon produced from any nuclear weapon test that might occur. A method is described that starts with information about civil releases and produces a statistical description of the concentrations of isotopes measured at stations designed to detect nuclear tests. This information makes it possible to enhance nuclear explosion detection performance.

Exploring the Relationship Between Time Series of Sentinel-1 Interferometric Coherence Data and Wild Edible Mushroom Yields in Mediterranean Forests

Edible wild mushrooms constitute a valuable marketable non-wood forest product with high relevance worldwide. There is growing interest in developing tools for estimation of mushroom yields and to evaluate the effects that global change may have on them. Remote sensing is a powerful technology for characterization of forest structure and condition, both essential factors in triggering mushroom production, together with meteo-climatic factors. In this work, we explore options to apply synthetic aperture radar (SAR) data from C-band Sentinel-1 to characterize, at the plot level, wild mushroom productive forests in the Mediterranean region, which provide saprotroph and ectomycorrhizal mushrooms. Seventeen permanent plots with mushroom yield data collected weekly during the productive season are characterized with dense time series of Sentinel-1 backscatter intensity (VV and VH polarizations) and 6-day interval interferometric VV coherence during the 2018–2021 period. Weekly-regularized series of SAR data are decomposed with a LOESS approach into trend, seasonality, and remainder. Trends are explored with the Theil-Sen test, and periodicity is characterized by the Discrete Fast Fourier transform. Seasonal patterns of SAR time-series are described and related to mycorrhizal and saprotroph guilds separately. Our results indicate that time series of interferometric coherence show cyclic patterns which might be related with annual mushroom yields and may constitute an indicator of triggering factors in mushroom production, whereas backscatter intensity is strongly correlated with precipitation, making noisy signals without a clear interpretable pattern. Exploring the potential of remotely sensed data for prediction and quantification of mushroom yields contributes to improve our understanding of fungal biological cycles and opens new ways to develop tools that improve its sustainable, efficient, and effective management.

Characterization and prediction of hydraulic properties of traffic-compacted forest soils based on soil information and traffic treatments

Key messageThe hydraulic properties of compacted and rutted soils were evaluated through in-situ infiltration experiments and predicted based on soil texture class and traffic treatments. A significant decrease in saturated soil water content and soil hydraulic conductivity at saturation was observed. The resulting soil hydraulic parameters, when integrated into a soil water transfer model, effectively simulated water dynamics in these impacted forest soils, providing a crucial first step toward developing decision support tools for real-time trafficability. This approach can assist forest managers in minimizing the extent of soil compaction.ContextTo overcome trafficability issues of forest soils induced by heavy logging machinery, planning support tools are needed to determine suitable soil moisture conditions for traffic.AimsThis study aimed to identify the soil properties that differ significantly between undisturbed and compacted soils and to provide several estimation tools to predict the hydraulic properties of compacted soils beneath the skid trails.MethodsFour hundred seventeen water infiltration tests were conducted on 19 forest sites, mostly in North-eastern France, and analysed with the BEST method to estimate the hydraulic properties of the skid trails and undisturbed soils. The hydraulic properties of the skid trails were predicted thanks to linear mixed effect models using a bulk treatment effect, a site effect, or a skid trail degradation score. The predicted hydraulic properties were tested using a water flow model to assess their relevance regarding the prediction of water dynamics in skid trails.ResultsThe compaction effect was only significant for the logarithm of the hydraulic conductivity at saturation (log10(Ksat)) and the soil water content at saturation (θsat). For the skid trails, θsat was reduced by - 0.02 and − 0.11 m3m−3 in the 0 − 10 cm and 15 − 25 cm layers respectively, compared to undisturbed topsoil (0 − 10 cm). log10(Ksat) was reduced by − 0.38 and − 0.85 for skid trails in the 0 − 10 and 15 − 25 cm soil layers respectively, compared to undisturbed topsoil. The use of a pedotransfer function, in replacement of water infiltration tests, and their combination with the same correction coefficients proved to efficiently simulate the difference in water dynamics between skid trails and undisturbed forest soils.ConclusionEstimation of soil hydraulic properties based on in situ water infiltration experiments proved efficient to simulate water dynamics in compacted and rutted forest soils. Yet, further studies are needed to identify the most adapted pedotransfer function to forest soils and to test the generalisation of our findings in different conditions, especially deeply rutted soils (rut depths > 12 cm).

A Comparison of Open Ventral Hernia Repair Risk Stratification Systems: A Call for Consensus

Background/Objectives: Ventral hernia repair (VHR) is a common surgical intervention linked to specific surgical site complications. In such occurrences, the related morbidity is often substantial. Although known risk factors have long been recognized, their systematic inclusion in risk stratification systems lacks universal validation. This study evaluates the effectiveness and correspondence of three risk assessment tools—CeDAR, VHWG, and the modified VHWG—in predicting postoperative wound complications in VHR patients. Methods: We analyzed data from 203 patients who underwent VHR for incisional midline or lateral wall hernia across two surgical departments between 2019 and 2023. Each patient was scored using CeDAR, VHWG, and the modified VHWG systems. Outcomes were assessed based on surgical site occurrences (SSOs) such as seroma formation, wound infections, and recurrences. Results: The incidence of SSOs was 8.9%, with two recorded deaths (0.89%). CeDAR scores showed a statistically significant relationship with SSOs but failed to accurately predict complication rates across subgroups. The VHWG grading system effectively predicted higher complication rates for grades III and IV compared to grades I and II, though its modified version did not show significant predictive improvements. Secondary outcomes indicated a higher SSO rate in patients requiring posterior component separation (TAR) and those with larger hernia defects, though the differences were not statistically significant. Major preoperative risk factors, including smoking, diabetes, and obesity, did not show significant correlations with SSO rates in this study. Conclusions: Current risk estimation tools inadequately predict SSOs in VHR. Enhancing prediction accuracy will require incorporating both patient-specific and surgical factors, potentially through advanced algorithms and large-scale studies.

The DQ Trace Method for Quantitative Seismic Interpretation: Theory and Application to a Synthetic AVO Data Catalog

The Distance and Quadrant (DQ) trace is a novel seismic attribute that enhances the detection and visualization of hydrocarbons in seismic data. Generated through a combination of partial near and far stack traces convolved with phase shift filters, the DQ trace offers several advantages over traditional AVO attributes and inversion methods. This study presents the DQ trace generation process, which involves quadrant optimization and the application of a modified AVO two-layer model equation. The method is computationally efficient and does not require a priori knowledge of petrophysics, basin geology, or wavelets. Concurrent phase angle analysis is used to compare DQ traces with porosity logs, demonstrating a strong correlation between the two. Synthetic models for different AVO classes are employed to evaluate the performance of DQ traces in cross-section displays. The results show that DQ traces provide enhanced clarity and delineation of gas sands, wet sands, and thin beds, as well as improved visualization of tuning effects and fluid contacts compared to conventional seismic displays. DQ histogram analysis reveals systematic trends across AVO classes and allows for the separation of gas sands, wet sands, and shales. The DQ trace is a robust tool for porosity estimation and has potential applications in various seismic processes and basin-scale mapping. This study highlights the implications of the DQ trace for fluid detection and seismic interpretation, offering a new methodology in subsurface reservoir characterization.

Improved tools for estimation of ammonia emission from field-applied animal slurry: Refinement of the ALFAM2 model and database

Ammonia volatilization from animal slurry applied to agricultural fields reduces nitrogen use efficiency in agriculture and pollutes the environment. This work presents new versions of a model and database focused on this route of N loss. The public ALFAM2 database (https://github.com/AU-BCE-EE/ALFAM2-data) was expanded with ammonia emission and ancillary measurements for >700 additional field plots. The ALFAM2 model (https://github.com/AU-BCE-EE/ALFAM2, https://zenodo.org/records/13312251) was extended with the addition of an ammonia sink for more plausible predictions over extended durations and to better reflect the expected reduction in emission rate several days after slurry application. A new parameter set was developed for the model taking into account the newly available measurement data. Model efficiency improved to 0.67 for the parameter estimation subset (0.52 for cross-validation) and mean absolute error was around 10% of applied total ammoniacal nitrogen. As in earlier versions, predicted emission is sensitive to application method, slurry dry matter and pH, air temperature, and wind speed. A collection of parameter sets for estimating uncertainty in average predictions was developed using a bootstrap approach. Predicted uncertainty is not trivial, and is high for some variable combinations, highlighting the challenge of making predictions based on available measurement data. Still, this work has resulted in more accurate, comprehensive, transparent, and flexible tools for emission inventory and related work on ammonia loss from field-applied slurry.

Maximizing similarity: using correlation coefficients to calibrate kinetic parameters in population balance models

Crystallization plays a crucial role as a separation and purification technique, particularly in the chemical and pharmaceutical industries. By adjusting process parameters, the productivity, product quality, and efficiency of downstream processes can be improved. In complex processes, model-based design becomes invaluable. Population Balance Models (PBMs) have successfully aided the chemical industry in achieving more effective production processes for decades. These models can utilize various input data sources to identify the dominant mechanisms and calibrate model parameters. While inline particle monitoring tools serve as excellent qualitative descriptors, challenges arise from experimentation and data interpretation, hindering their direct application in the kinetic parameter estimation of PBMs. In this study, we present a novel approach that utilizes information from inline particle monitoring tools for the kinetic parameter estimation of PBMs, bypassing the associated obstacles. Our pioneering approach relies on offline product size data and the correlation-based utilization of inline particle monitoring information. The paper compares this novel strategy with two parameter estimation techniques: the classical method using solute concentration and product size data and a somewhat naïve approach, which assumes that the inline particle monitoring data can directly be compared with the simulations. The prediction capabilities are evaluated through two in-silico case studies. The results indicate that the precision and predictive capability of the correlation-based technique are comparable to the classical approach, both for noisy data and for a system undergoing significant agglomeration and deagglomeration. The use of Pearson’s correlation coefficient yields the best results in the novel cases. These findings in in-silico datasets provide a foundation and motivation for the practical application of this idea, unleashing the so-far hidden model development potential of such measurements.

Heart Shape to Fracture Distance: Characterizing Hydraulic Fracture Propagation before Hits

Summary Estimating the distance from the hydraulic fracture tip to the monitor well can be useful for fracture characterization, well spacing optimization, and preventing parent-child well interference. A heart-shaped signal is referred to as the extensional precursor of a fracture hit recorded by crosswell strain measurements and can serve as a vital tool for such estimation. This study incorporates the 3D displacement discontinuity method (DDM) to understand the impact of fracture geometry and monitor well offset on the heart-shaped signal’s characteristics. Results from numerical simulation and analytical solutions reveal a strong linear correlation between the spatial extent of the heart-shaped signal and the fracture tip distance. This relationship was further developed to predict tip distance using field data from the Hydraulic Fracture Test Site 2 (HFTS2). A reasonable approximation result from field data further validates the methodology. In addition, it is worth noting that the estimation accuracy depends on the ratio between fracture dimension and tip distance. The findings of this study offer a novel approach for real-time monitoring and characterizing hydraulic fracture propagation, which can be further used for well spacing optimization in unconventional and enhanced geothermal system reservoir development, as well as caprock integrity monitoring for carbon sequestration projects.

Plant‐based protein crops and their improvement: Current status and future perspectives

AbstractThe plant‐based protein industry is rapidly growing and is projected to grow to over $27 billion by 2030. In addition to monetary benefits, plant‐based protein crops, particularly pulse crops (i.e., legume species with dry edible seed), can supplement the existing crop biodiversity and break the disease and insect pest cycle in drastically changing climatic conditions. Most commercially available plant‐based protein ingredients come from only 2% of the 150 plant species on which our food supply depends. Therefore, it is imperative to diversify the cropping system with pulse crops that provide a more nutritious, climate‐resilient, sustainable food value chain. At present, a large portion of US pulse crop production is exported, yet the shifting demographics, dietary preferences, and a rise in domestic consumption present enormous potential for existing and emerging pulse crops, as well as their breeding. Despite a rise in demand from consumers and industries, farmers are yet to fully reap the benefits of these crops due to a shortage of improved varieties. These new varieties could lead to a diverse, sustainable protein supply that satisfies the growing domestic and global demand for plant‐based foods. This review intends to comprehensively explore the geographical and cultural acceptance of plant‐based proteins, manufacturing techniques, protein products, anti‐nutritional factors, techniques and tools for protein estimation, high‐throughput estimation of seed protein, protein composition requirements in food, breeding strategies, crop improvement, and resources to improve plant‐based protein pulse crops.

Comparison of cardiovascular disease risk assessment tools in primary prevention patients with raised lipoprotein(a)

Abstract Background Genetically inherited lipoprotein (a) (lp(a)) is an independent cardiac risk factor. The approach to cardiovascular disease (CVD) risk modification is, however, uncertain. Current CVD risk calculators do not take lp(a) into account and guidance suggests binary treatment decisions based on presentation of lp(a) without considering other risk factors. A new CVD risk assessment tool has been developed which includes lp(a) concentration, Lp(a) Clinical Guidance (lpaclinicalguidance.com). Purpose The aim was to compare the CVD risk estimations and management impact, over both 10 years and lifetime, using the HEART UK consensus statement, QRISK3, Lp(a) Score, Score-2, Score-2 OP, and LIFE-CVD assessment tools in 20 primary prevention patients with raised lp(a). Methods This was a retrospective analysis from an existing database, recruited through lipid and cardiology outpatient services, with raised lp(a), and no history of CVD. A random selection with a broad range of lp(a) concentrations were chosen. The 10-year risk threshold to treat was based on current NICE guidance at 10% and, in the absence of consensus, a lifetime risk threshold of 25%. Lp(a) was measured by a reference clinical laboratory using a Roche platform (Denka Seiken reagent, isoform insensitive). Results The subset (n=20) included patients with lp(a) ranging from 64 nmol/L to >720 nmol/L, aged 20 to 78 (12 females). Risk assessment tool age restrictions prohibited risk estimation in all patients (explaining the variation in denominator below). Figure 1 shows a comparison of 10-year risk assessment tools, figure 2 lifetime risk. HEART UK guidance would indicate 90% of patients (18/20) were eligible to commence lipid lowering therapy, however, all patients would have treatment indicated based on Lp(a) Score (16/16). Using Score-2, no patients would have treatment indicated (0/6). Only 25% of patients (1/4) would have treatment indicated using Score-2 OP despite a minimum age criterion that alone introduces a major CVD risk factor. Of the remaining risk estimation tools: LIFE-CVD, QRISK3 lifetime risk, and QRISK3 10-year risk indicated 85% (11/13), 50% (8/16), and 38% (6/16) of patients, respectively, would have treatment indicated. Conclusions In primary prevention patients with raised lp(a), CVD risk estimation and decision-making is impaired by discrepancies in risk assessment tools. There may be underestimation in CVD risk, and subsequently under-treatment, with principal use of QRISK3 10-year risk to guide lipid lowering therapy. Lifetime CVD risk may be underestimated by QRISK and LIFE-CVD proportionally to the degree of elevation of lp(a). Risk assessment is imperfect; population data can only provide limited information when applied to an individual and the wide discrepancy found here calls into question the validity of risk estimation formulae in this population, or alternatively provides a range of tools for clinicians to select to suit the question asked.

Multi-modality deep learning model for prediction of chronic obstructive coronary artery disease

Abstract Background/Introduction The incidence of coronary artery disease (CAD) is on the rise with an increasing burden of stable ischemic heart disease (SIHD) and high prevalence of obesity, diabetes, hyperlipidemia, and other cardiovascular risk factors. Pre-test probability estimation for CAD based on demographic features and characterization of chest pain is insufficient to accurately assess whether further evaluation for CAD is warranted. Purpose To develop and validate a deep learning (DL) algorithm utilizing electrocardiogram (ECG) waveforms and clinical features to predict obstructive CAD. Methods Clinical data from subjects undergoing invasive angiography over a 4-year period at a quaternary care center exclusive of subjects who had concern for acute coronary syndromes were used for model training. ECGs obtained up to 5 years prior to angiography were included; ECGs were partitioned 8:1:1 for training, validation, and test datasets. Obstructive CAD was defined as receiving percutaneous coronary intervention during elective angiography. Convolutional neural network models were developed for ECG waveforms alone (DL-ECG), clinical features from standard risk scores (DL-Clinical), and the combination of ECG waveforms and clinical features (DL-ECG+Clinical); a commonly used pre-test probability estimation tool derived from the CAD Consortium study was used as a comparison (PTP). The models were evaluated based on area under the curve receiver operating characteristics (AUC). Shapley additive explanations (SHAP) analysis was performed to understand feature importance in the DL models. Results A total of 40,602 ECGs and 8,361 coronary angiograms from 7,201 patients were included in the analysis. The median age was 66 (IQR 56-75), 71.9% were men, 34.9% had hypertension, 30.6% had diabetes mellitus, and 39.0% had dyslipidemia. The PTP model (AUC 0.733 [0.717-0.750]) had similar performance as the DL-Clinical model (AUC 0.762 [0.746-0.778]). The DL-ECG model (AUC 0.741 [0.726-0.758]) had similar performance as both the clinical feature models. The DL-ECG+Clinical model (AUC 0.807 [0.793-0.822]) trained on ECG waveforms and clinical features had a superior performance (Figure 1). SHAP analysis for the DL-ECG+Clinical model revealed that ECG waveforms had the largest influence on the model’s output followed by age and chest pain type (Figure 2). Conclusions Multi-modality DL model utilizing ECG and commonly used features can improve prediction of obstructive CAD in SIHD compared to traditional pre-test probability estimates. Prospective research is warranted to determine whether incorporation of DL methods to ECG analysis effectively improves diagnosis and outcomes in obstructive CAD.Figure 1.Figure 2.

Artificial intelligence-enhanced electrocardiography predicts 10-year risk of atherosclerotic cardiovascular disease

Abstract Background The ACC/AHA pooled cohort equations (PCE) calculates the 10-year primary risk of atherosclerotic cardiovascular disease (ASCVD), an indication to initiate primary prevention statin therapy in international guidelines. The validity of PCE is limited by its overestimation of risk in high-risk cohorts and an ethnic heterogeneity. Electrocardiography (ECG) has not been incorporated in current ASCVD risk estimation tools. Artificial Intelligence (AI)-based models are capable to capture patterns that are informative for cardiovascular prognosis. Purpose We explored the predictive value of a discrete-time survival model in 10-year ASCVD risk in comparison to PCE. Methods We developed an AI-ECG model to predict the 10-year ASCVD risk in an unselected secondary care population from the USA comprised of 1,163,401 ECGs from 189,539 patients. Data was split into training/validation and hold-out test sets by patient ID. Our AI-ECG model uses deep learning with a residual convolutional neural network with a discrete-time survival loss function to output subject-specific survival curves, accounting for both time to event and censorship (i.e., loss to follow up). We compared the performance of out AI-ECG model using a subset of outpatient data (n=4590) of the BIDMC dataset to PCE and ASCVD risk factors including systolic blood pressure, total cholesterol, HDL cholesterol, hypertension, smoking history, diabetes mellitus, and ethnicity. Performances were evaluated using cox survival analysis. Our AI-ECG model was externally validated in the UKB Biobank (UKB), where we compared the performance of our AI-ECG model to predictions of existing AI-ECG models such as the Stanford Estimator of Electrocardiogram Risk (SEER) model. Results Our AI-ECG successfully predicted future ASCVD events in individuals (C-index 0.721 (0.719-0.723), 5-year AUC 0.761 (0.758-0.763), and differentiated between high and low risk group with an adjusted HR of 2.33 (2.26-2.41). Upon internal validation our AI-ECG model showed a superior performance (C-index 0.679 (0.651-0.708)) than PCE (0.605 (0.577-0.634)) and all risk factors combined (C index 0.642 (0.613-0.672)). When combining AI-ECG predictions with all risk factors, the model showed additional predictive value (0.686 (0.657-0.715)) (Figure 1). Our AI-ECG model showed modest predictive value within the UKB dataset (C-index 0.655 (0.637-0.673)), but significantly outperformed the SEER model (C-index 0.547 (0.527-0.567), p <0.0001 for comparison with AIRE). Conclusion We have shown the potential of AI-ECG models in predicting future ASCVD risks. AI-ECG models demonstrated accurate discrete time survival prediction and good classification performance superior to that of the SEER model, as well as PCE and ASCVD risk factors. . Accurate risk assessment of ASCVD may help prevent adverse events in high risk subjects and save unnecessary pharmacological interventios in low risk subjects.Figure 1

Enhancing reliability in estimating modal parameters for automotive disk Brakes: A comprehensive approach using the Eigensystem Realization algorithm and additional criteria

This paper investigates the challenges in accurately identifying and assessing vibration characteristics in automotive disk brakes, which, due to their geometric symmetry, exhibit closely spaced vibration modes. Understanding the damping characteristics is crucial due to their significant impact on dynamic stability and the potential onset of brake squeal, as damping directly influences the stability threshold and its uneven distribution can destabilize the system. Therefore, this study primarily focuses on the identification of modal parameters with an emphasis on the damping of disk brakes. Traditional Experimental Modal Analysis (EMA) techniques, which rely heavily on Frequency Response Function (FRF) measurements, encounter challenges in distinguishing closely spaced modes, thereby affecting the reliability of parameter estimation, particularly damping. These algorithms are primarily based on FRF measurements and are of multi-input – single-output type (MISO). In comparison to Operational Modal Analyses (OMA) algorithms, which are widely used in civil engineering and are of the multi-input − multi-output type and contain statistical tools for assessing the uncertainty of the estimate, EMA provides limited possibilities to assess the quality of estimating parameters. The primary contribution of this work is demonstrating that the Eigensystem Realization Algorithm (ERA), supplemented with indicators such as Extended Modal Amplitude Coherence (EMAC), Modal Phase Collinearity (MPC), and the Consistent Mode Indicator (CMI), offers a robust tool for accurate damping estimation. Additionally, the application of ERA to data originally acquired for frequency-based methods, specifically the Rational Fraction Polynomial (RFP) method, allows for a direct comparison of these two EMA algorithms using the same dataset. The results demonstrate that the proposed identification process effectively distinguishes system modes from those influenced by noise, providing a pathway to optimize test data acquisition and improve the accuracy of modal parameter estimation, especially in systems with closely spaced modes. The method can also serve as a tool for optimizing the acquisition of test data to improve the estimation of modal parameters, by varying the positions of input (SIMO) or by transitioning to MIMO identification to enhance the observability and controllability of closely spaced modes of disk brake.