Model Predictions Research Articles

The cool brown dwarf Gliese 229 B is a close binary.

Owing to their similarities with giant exoplanets, brown dwarf companions of stars provide insights into the fundamental processes of planet formation and evolution. From their orbits, several brown dwarf companions are found to be more massive than theoretical predictions given their luminosities and the ages of their host stars1-3. Either the theory is incomplete or these objects are not single entities. For example, they could be two brown dwarfs each with a lower mass and intrinsic luminosity1,4. The most problematic example is Gliese 229 B (refs. 5,6), which is at least 2-6 times less luminous than model predictions given its dynamical mass of 71.4 ± 0.6 Jupiter masses (MJup) (ref. 1). We observed Gliese 229 B with the GRAVITY interferometer and, separately, the CRIRES+ spectrograph at the Very Large Telescope. Both sets of observations independently resolve Gliese 229 B into two components, Gliese 229 Ba and Bb, settling the conflict between theory and observations. The two objects have a flux ratio of 0.47 ± 0.03 at a wavelength of 2 μm and masses of 38.1 ± 1.0 and 34.4 ± 1.5 MJup, respectively. They orbit each other every 12.1 days with a semimajor axis of 0.042 astronomical units (AU). The discovery of Gliese 229 BaBb, each only a few times more massive than the most massive planets, and separated by 16 times the Earth-moon distance, raises new questions about the formation and prevalence of tight binary brown dwarfs around stars.

Multiparametric MRI Radiomics With Machine Learning for Differentiating HER2-Zero, -Low, and -Positive Breast Cancer: Model Development, Testing, and Interpretability Analysis.

BACKGROUND: MRI radiomics has been explored for three-tiered classification of breast cancer HER2 expression (i.e., HER2-zero, HER2-low, or HER2-positive), although understanding of how such models reach their predictions is lacking. OBJECTIVE: To develop and test multiparametric MRI radiomics machine-learning models for differentiating three-tiered HER2 expression levels in patients with breast cancer, and to explain the contributions of model features through local and global interpretations using SHapley Additive exPlanation (SHAP) analysis. METHODS: This retrospective study included 737 patients (mean age, 54.1±10.6 years) with breast cancer from two centers (center 1: n=578; center 2: n=159), who underwent breast MRI and had HER2 expression determined after excisional biopsy. Analysis entailed two tasks: differentiating HER2-negative (i.e., HER2-zero or HER2-low) from HER2-positive tumors (task 1), and differentiating HER2-zero from HER2-low tumors (task 2). For each task, patients from center 1 were randomly assigned in 7:3 ratio to training (task 1: n=405; task 2: n=284) or internal test (task 1: n=173; task 2: n=122) sets; those from center 2 formed an external test set (task 1: n=159; task 2: n=105). Radiomics features were extracted from early-phase dynamic contrast-enhanced images (DCE), T2-weighted images (T2WI), and DWI. For each task, a support vector machine (SVM) was used for feature selection; a multiparametric radiomics score (radscore) was computed using feature weights from SVM correlation coefficients; conventional MRI and combined models were constructed; and model performances were evaluated. SHAP analysis was used to provide local and global interpretations for model outputs. RESULTS: In the external test set, for task 1, AUCs for the conventional MRI model, radscore, and combined model were 0.624, 0.757, and 0.762, respectively; for task 2, AUC for radscore was 0.754, and no conventional MRI model or combined model could be constructed. SHAP analysis identified early-phase DCE features as having the strongest influence for both tasks; T2WI features also had a prominent role for task 2. CONCLUSION: The findings indicate suboptimal performance of MRI radiomics models for noninvasive characterization of HER2 expression. CLINICAL IMPACT: The study provides an example of the use of SHAP interpretation analysis to better understand predictions of imaging-based machine learning models.

Updating assembly parameters for spacecraft assembly process state changes: based on data fusion method

Thermal protection systems (TPSs) are important components of reusable spacecraft, and their assembly quality has a crucial impact on flight safety. Owing to the complex assembly process and variable states of spacecraft thermal protection systems, assembly parameters may vary under different assembly states. Therefore, to obtain assembly parameters accurately and efficiently under different assembly states, in this study, 3D point cloud data and fiber optic sensor data were fused to develop an assembly parameter update method for assembly process state changes. Firstly, based on the measured data of thermal protection components and load-bearing structure, the gap, flush and matching parameters solution model are proposed. Secondly, to address the deformation problem of the load-bearing structure caused by changes in assembly status, a fusion method based on laser scanning and sensor detection was devised to achieve deformation prediction of the assembly structure during the assembly process. Thirdly, based on the assembly parameter solution model and point cloud prediction model, a constraint-based assembly parameter optimisation model was established, and an improved quantum particle swarm optimisation (LQPSO) algorithm was employed to achieve assembly parameter updates oriented toward changes in assembly status. Finally, an experimental system for array-based thermal protection structure simulation was established to validate the proposed method. The results show that the proposed parameter update method can achieve ideal results for different assembly state simulation components.

What explains rice exports? An analysis of major rice‐exporting countries

AbstractThis study examines the drivers of rice trade. The analysis uses the standard comparative advantage model, the Heckscher–Ohlin–Vanek (HOV) framework, supplemented with a gravity‐type equation. Using the Poisson pseudo‐maximum likelihood (PPML) estimation for data from 2002 to 2020, the analysis broadly confirms HOV model predictions. Results indicate that arable land, along with GDP, distance, precipitation and crop season temperature, significantly influences rice trade dynamics. The results showed that the precipitation play a key role in influencing the rice trade rather than the blue water availability. However, agricultural water stress discouraged exports and encouraged imports.

Evolution of Virulence in Emerging Epidemics: From Theory to Experimental Evolution and Back

Abstract The experimental validation of theoretical predictions is a crucial step in demonstrating the predictive power of a model. While quantitative validations are common in infectious diseases epidemiology, experimental microbiology primarily focuses on the evaluation of a qualitative match between model predictions and experiments. In this study, we develop a method to deepen the quantitative validation process with a polymorphic viral population. We analyse the data from an experiment carried out to monitor the evolution of the temperate bacteriophage λ spreading in continuous cultures of Escherichia coli. This experimental work confirmed the influence of the epidemiological dynamics on the evolution of transmission and virulence of the virus. A variant with larger propensity to lyse bacterial cells was favoured in emerging epidemics (when the density of susceptible cells was large), but counter-selected when most cells were infected. Although this approach qualitatively validated an important theoretical prediction, no attempt was made to fit the model to the data nor to further develop the model to improve the goodness of fit. Here, we show how theoretical analysis – including calculations of the selection gradients – and model fitting can be used to estimate key parameters of the phage life cycle and yield new insights on the evolutionary epidemiology of the phage λ. First, we show that modelling explicitly the infected bacterial cells which will eventually be lysed improves the fit of the transient dynamics of the model to the data. Second, we carry out a theoretical analysis that yields useful approximations that capture at the onset and at the end of an epidemic the effects of epidemiological dynamics on selection and differentiation across distinct life stages of the virus. Finally, we estimate key phenotypic traits characterizing the two strains of the virus used in our experiment such as the rates of prophage reactivation or the probabilities of lysogenization. This study illustrates the synergy between experimental, theoretical and statistical approaches; and especially how interpreting the temporal variation in the selection gradient and the differentiation across distinct life stages of a novel variant is a powerful tool to elucidate the evolutionary epidemiology of emerging infectious diseases.

Forecasting residential real estate prices and energy usage in Flanders

Purpose Currently, residential forecasting literature is limited with few to no forecasting papers that consider residential prices and energy consumption for the selling and rental market within a single study. The purpose of this paper is to study the prices and energy usage for both markets by combining an explanatory model with the predictions of a predictive model, which will lead to a better understanding of the forecasting results. Design/methodology/approach This study presents an econometric comparison between 508,612 selling properties and 174,007 rental properties transacted in Flanders between January 2019 and December 2023. The authors study their prices and energy usage by combining the causal results of a hedonic price model (HPM) with the predictions of an autoregressive integrated moving average model (ARIMA). Findings The authors find that both markets are extremely sensitive to changes in related factors, whereby selling prices are primarily influenced by macroeconomic factors, but rental prices and especially energy usage are also sensitive to market standards. Policies that target energy efficiency can therefore steer its future trend. In addition, in line with previous literature, the HPM shows an increasingly strong relationship between residential prices and energy efficiency over the years, indicating that these steering energy policies also indirectly monitor residential prices. Originality/value This study underscores the importance of integrating the results of an explanatory model with a predictive model. It demonstrates that combining them provides a more comprehensive understanding which is helpful for policymakers, real estate professionals and investors during their decision-making process.

Strain rate controls alignment in growing bacterial monolayers.

Growing monolayers of rod-shaped bacteria exhibit local alignment similarly to extensile active nematics. When confined in a channel or growing inward from a ring, the local nematic order of these monolayers changes to a global ordering with cells throughout the monolayer orienting in the same direction. The mechanism behind this phenomenon is so far unclear, as previously proposed mechanisms fail to predict the correct alignment direction in one or more confinement geometries. We present a strain-based model relating net deformation of the growing monolayer to the cell-level deformation resulting from single-cell growth and rotation, producing predictions of cell orientation behavior based on the velocity field in the monolayer. This model correctly predicts the direction of preferential alignment in channel-confined, inward growing, and unconfined colonies. The model also quantitatively predicts orientational order when the velocity field has no net negative strain rate in any direction. We further test our model in simulations of expanding colonies confined to spherical surfaces. Our model and simulations agree that cells away from the origin cell orient radially relative to the colony's center. Additionally, our model's quantitative prediction of the orientational order agrees with the simulation results in the top half of the sphere but fails in the lower half where there is a net negative strain rate. The success of our model bridges the gap between previous works on cell alignment in disparate confinement geometries and provides insight into the underlying physical effects responsible for large-scale alignment.

On the role of the retained porosity on the shock response of additively manufactured high-performance steel: Experiments, constitutive model and finite-element predictions

Experiments have shown that for quasi-static and moderate strain-rates (of the order of 102–103/s) the mechanical response of additively manufactured (AM) and traditionally processed high-strength steels is similar whereas the impact behavior is markedly different. In this paper, we reveal that the main reason for this difference is the retained porosity in the AM material. Fully-implicit finite element calculations are presented in which we simulate both the launching of the impact plate and the impact between the two plates. The constitutive model used is the elastic/plastic model for porous ductile materials with matrix displaying tension-compression asymmetry and Johnson-Cook hardening law that accounts for both strain-rate effects and plastic history. It is shown that even a very small initial porosity changes the wave front, decreases the Hugoniot while increasing the shock rise time, when compared to a void free material. Furthermore, quantitative comparisons between simulation results and plate impact data for both the AM and the wrought AF9628 steel are provided. The good agreement show that the model captures the impact response and illustrates the model capabilities to provide information on field variables that cannot be directly measured.Additive manufacturing (AM) of metals is rapidly advancing as a robust method for production of geometrically complex parts. To enhance understanding of material performance and open up additional application opportunities, dynamic characterization of newly printed alloys is required to validate their effectiveness. In this paper, we present results from plate impact testing of AF9628 steel, a newly developed high-strength low alloy martensitic steel for structural applications which require resistance to high-rate deformation. We put into evidence differences in the shock structure between the AM and the traditionally processed material. To gain understanding, we conduct fully-implicit finite element (FE) calculations in which we model both the launching of the impact plate and the impact between the two plates, respectively. An elastic/plastic damage model that accounts for the effects of the tension-compression asymmetry in plastic deformation and its influence on porosity evolution is used. The FE results reveal that even a very small amount of initial porosity leads to an increase in the shock rise time, explaining the observed trends. Furthermore, quantitative comparisons between simulation results and plate impact data for both the AM and the wrought AF9628 are provided. The good agreement show that the model captures the impact response and illustrates the model capabilities to provide information on field variables that cannot be directly measured.

Construction and interpretation of machine learning-based prognostic models for survival prediction among intestinal-type and diffuse-type gastric cancer patients

BackgroundGastric cancer is one of the most common malignant tumors worldwide, with high incidence and mortality rates, and it has a complex etiology and complex pathological features. Depending on the tumor type, gastric cancer can be classified as intestinal-type and diffuse-type gastric cancer, each with distinct pathogenic mechanisms and clinical presentations. In recent years, machine learning techniques have been widely applied in the medical field, offering new perspectives for the diagnosis, treatment, and prognosis of gastric cancer patients.MethodsThis study recruited 2158 gastric cancer patients and constructed prognostic prediction models for both intestinal-type and diffuse-type gastric cancer. Clinical pathological data were collected from patients, and machine learning algorithms were used for feature selection and model construction. The performance of the models was validated with training and testing datasets. The Shapley additive explanations (SHAP) values were used to interpret the model predictions and identify the main factors that influence patient survival.ResultsIn the prognostic model for intestinal-type gastric cancer, the gradient boosting decision tree (GBDT) model demonstrated the best performance, with key features including pTNM, CA125, tumor size, CA199, and PALB. Similarly, in the prognostic model for diffuse-type gastric cancer, the GBDT model was utilized, with key features comprising pTNM, Borrmann type IV disease, lymphocyte (LYM), lactate dehydrogenase (LDH), potassium (K), perineural invasion (PNI), tumor size, and whole stomach location. Risk stratification analysis revealed that the prognosis of high-risk patients was significantly worse than that of low-risk patients.ConclusionMachine learning shows great potential in predicting survival outcomes of gastric cancer patients, providing strong support for the development of personalized treatment plans.

Evaluating the significance of latent tuberculosis infection treatment in high‐incidence countries

Tuberculosis (TB) caused by Mycobacterium tuberculosis (Mtb) is a devastating and rapidly spreading disease. Despite years of scientific research and numerous efforts, it is still a major and resurgent health problem worldwide, with high mortality rates. Added to the concern is that TB persists as a latent infection, an occult face of TB, that becomes a potential reservoir for active tuberculosis. Since latent TB‐infected patients may eventually advance to the active form of TB, an accurate diagnosis and effective treatment of latent tuberculosis are essential for TB control. Latent tuberculosis infection (LTBI) treatment is a prominent component of TB control in low‐prevalence countries like the United States; however, its implication in high‐incidence countries like India is still challenging. Therefore, the present study aimed to evaluate the impact of implementing diagnosis and treatment of LTBI in high‐incidence countries using a mathematical model‐based approach. Through our model, we predicted the incidence rate based on the current treatment regimen in India for the year 2035, which is one of the milestones of WHO for a substantial reduction in TB incidence. We observed demographic variability in the effects of various parameters on the TB incidence rate. Finally, we formulated the putative treatment strategies to reduce the TB burden in high‐incidence scenarios. Further, we estimated the impact of these proposed treatment strategies on the drug‐resistant population in high‐incidence scenarios. The model predictions suggested molding the current treatment strategies and focused implementation of LTBI diagnosis and treatment in high‐incidence scenarios.

Prediction of Cardiac ATTR Depletion by NI006 (ALXN2220) Using Mechanistic PK/PD Modeling.

NI006 (aka ALXN2220) is a therapeutic antibody candidate in phase III clinical development for the depletion of amyloid transthyretin (ATTR) in patients with ATTR cardiomyopathy, an infiltrative cardiomyopathy leading to increased left ventricular wall thickness (LVWT). The mode-of-action consists in removal of disease-causing amyloid accumulations by activating phagocytic immune cells, a mechanism without precedent in cardiology. To select a safe and potentially efficacious dose range and treatment duration for a combined first-in-human and proof-of-concept clinical phase Ib study, we developed a mechanistic pharmacokinetic and pharmacodynamic (PK/PD) model that can predict NI006 exposure, its effects on cardiac amyloid load and on LWVT, which is a predictor of heart failure in this disease. The PK/PD model predictions supported 0.3 mg/kg monthly dosing as a safe starting dose and identified 10-60 mg/kg monthly as the potentially efficacious dose range with substantial and dose dependent cardiac amyloid burden reduction within 4 months for 60 mg/kg and 10 months for 10 mg/kg. These predictions were in good agreement with the observed primary results of the clinical phase Ib study where amyloid burden was measured by imaging. This novel translational PK/PD model provided important predictions to guide the design of the phase Ib study of NI006, indicating the value of this approach to integrate preclinical results into clinical trial design and increase translational success.

Exploring online public survey lifestyle datasets with statistical analysis, machine learning and semantic ontology

Lifestyle diseases significantly contribute to the global health burden, with lifestyle factors playing a crucial role in the development of depression. The COVID-19 pandemic has intensified many determinants of depression. This study aimed to identify lifestyle and demographic factors associated with depression symptoms among Indians during the pandemic, focusing on a sample from Kolkata, India. An online public survey was conducted, gathering data from 1,834 participants (with 1,767 retained post-cleaning) over three months via social media and email. The survey consisted of 44 questions and was distributed anonymously to ensure privacy. Data were analyzed using statistical methods and machine learning, with principal component analysis (PCA) and analysis of variance (ANOVA) employed for feature selection. K-means clustering divided the pre-processed dataset into five clusters, and a support vector machine (SVM) with a linear kernel achieved 96% accuracy in a multi-class classification problem. The Local Interpretable Model-agnostic Explanations (LIME) algorithm provided local explanations for the SVM model predictions. Additionally, an OWL (web ontology language) ontology facilitated the semantic representation and reasoning of the survey data. The study highlighted a pipeline for collecting, analyzing, and representing data from online public surveys during the pandemic. The identified factors were correlated with depressive symptoms, illustrating the significant influence of lifestyle and demographic variables on mental health. The online survey method proved advantageous for data collection, visualization, and cost-effectiveness while maintaining anonymity and reducing bias. Challenges included reaching the target population, addressing language barriers, ensuring digital literacy, and mitigating dishonest responses and sampling errors. In conclusion, lifestyle and demographic factors significantly impact depression during the COVID-19 pandemic. The study’s methodology offers valuable insights into addressing mental health challenges through scalable online surveys, aiding in the understanding and mitigation of depression risk factors.

Fiducial and differential cross-section measurements of electroweak Wγjj\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$W\\gamma jj$$\\end{document} production in pp collisions at s=13\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sqrt{s} = 13$$\\end{document} TeV with the ATLAS detector

The observation of the electroweak production of a W boson and a photon in association with two jets, using pp collision data at the Large Hadron Collider at a centre of mass energy of s=13\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\sqrt{s}=13$$\\end{document} TeV, is reported. The data were recorded by the ATLAS experiment from 2015 to 2018 and correspond to an integrated luminosity of 140 fb-1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^{-1}$$\\end{document}. This process is sensitive to the quartic gauge boson couplings via the vector boson scattering mechanism and provides a stringent test of the electroweak sector of the Standard Model. Events are selected if they contain one electron or muon, missing transverse momentum, at least one photon, and two jets. Multivariate techniques are used to distinguish the electroweak Wγjj\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$W\\gamma jj$$\\end{document} process from irreducible background processes. The observed significance of the electroweak Wγjj\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$W\\gamma jj$$\\end{document} process is well above six standard deviations, compared to an expected significance of 6.3 standard deviations. Fiducial and differential cross sections are measured in a fiducial phase space close to the detector acceptance, which are in reasonable agreement with leading order Standard Model predictions from MadGraph5+Pythia8 and Sherpa. The results are used to constrain new physics effects in the context of an effective field theory.

Linking Thermal Conductivity to Equations of State Using the Residual Entropy Scaling Theory.

In recent years, the application of the residual entropy scaling (RES) method for modeling transport properties has become increasingly prominent. Based on Yang et al. (Ind. Eng. Chem. Res. 2021, 60, 13052) in modeling the thermal conductivity of refrigerants, we present here an RES model that extends Yang et al.'s approach to a wider range of pure fluids and their mixtures. All fluids available in the REFPROP 10.0 software, i.e., those with reference equations of state (EoS), were studied. A total of 71,554 experimental data of 125 pure fluids and 16,702 experimental data of 164 mixtures were collected from approximately 647 references, mainly based on the NIST ThermoData Engine (TDE) database 10.1. As a result, over 68.2% (corresponding to the standard deviation of a normal distribution) of the well-screened experimental data agree with the developed RES model within 3.1% and 4.6% for pure fluids and mixtures, respectively. Comparative analysis against the various models implemented in the REFPROP 10.0 (one of the state-of-the-art software packages for thermophysical property calculations) reveals that our RES model demonstrates analogous statistical agreement with experimental data yet with much fewer parameters. Regarding the average absolute value of the relative deviation (AARD) from experimental values to model predictions, the developed RES model shows a smaller or equal AARD for 74 pure fluids out of 125 and 76 mixtures out of 164. Besides, a detailed examination of the impact of the critical enhancement term on mixture calculations was conducted. To use our model easily, a software package written in Python is provided in the Supporting Information.

Probabilistic Tide Calculation for Multi-Wind Farm Distribution Network Based on CATTSTS Model

Traditional probabilistic tide calculation methods often fall short in capturing the dynamic nature of these systems, leading to discrepancies between calculated and actual data. To address this, a dynamic probabilistic tide calculation model is proposed in this study, incorporating a wind farm probabilistic model enhanced by the CATTSTS model. This integration aims to optimize prediction accuracy by improving feature focusing and data fitting, thereby reducing prediction errors and providing more reliable data for power system adjustments and optimizations. Experimental results demonstrate that the model's predictions for wind speed series in multi-wind farm distribution networks closely match actual conditions, underscoring its practical applicability and reliability in real-world settings. Furthermore, the study highlights the impact of spatial and temporal correlations on model performance. This research contributes to advancing the management of renewable energy integration in power systems, offering insights for more informed decision-making and operational efficiency.

Machine learning-based prediction of mortality in acute myocardial infarction with cardiogenic shock.

In the ICU, patients with acute myocardial infarction and cardiogenic shock (AMI-CS) often face high mortality rates, making timely and precise mortality risk prediction crucial for clinical decision-making. Despite existing models, machine learning algorithms hold the potential for improved predictive accuracy. In this study, a predictive model was developed using the MIMIC-IV database, with external validation performed on the eICU-CRD database. We included ICU patients diagnosed with AMI-CS. Feature selection was conducted using the Boruta algorithm, followed by the construction and comparison of four machine learning models: Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Gaussian Naive Bayes (GNB). Model performance was evaluated based on metrics such as AUC (Area Under the Curve), accuracy, sensitivity, specificity, and so on. The SHAP method was employed to visualize and interpret the importance of model features. Finally, we constructed an online prediction model and conducted external validation in the eICU-CRD database. In this study, a total of 570 and 391 patients with AMI-CS were included from the MIMIC-IV and eICU-CRD databases, respectively. Among all machine learning algorithms evaluated, LR exhibited the best performance with a validation set AUC of 0.841(XGBoost: 0.835, AdaBoost: 0.839, GNB: 0.826). The model incorporated five variables: prothrombin time, blood urea nitrogen, age, beta-blockers and Angiotensin-Converting Enzyme Inhibitors or Angiotensin II Receptor Blockers. SHAP plots are employed to visualize the importance of model features and to interpret the results. An online prediction tool was developed, externally validated with the eICU-CRD database, achieving an AUC of 0.755. Employing the LR algorithm, we developed a predictive model for assessing the mortality risk among AMI-CS patients in the ICU setting. Through model predictions, this facilitates early detection of high-risk individuals, ensures judicious allocation of healthcare resources.

Ensemble Learning for Stellar Classification and Radius Estimation from Multimodal Data

Abstract Stellar classification and radius estimation are crucial for understanding the structure of the universe and stellar evolution. With the advent of the era of astronomical big data, multimodal data are available and theoretically effective for stellar classification and radius estimation. A problem is how to improve the performance of this task by jointly using the multimodal data. However, existing research primarily focuses on using single-modal data. To this end, this paper proposes a model, Multi-Modal SCNet (MMSCNet), and its ensemble model Multimodal Ensemble for Stellar Classification and Regression (MESCR) for improving stellar classification and radius estimation performance by fusing two modality data. In this problem, a typical phenomenon is that the sample numbers of some type stars are evidently more than others. This imbalance has negative effects on model performance. Therefore, this work utilize a weighted sampling strategy to deal with the imbalance issues in MESCR. Some evaluation experiments are conducted on a test set for MESCR and the classification accuracy is 96.1\%, the radius estimation performance Mean of Absolute Error (MAE) and $\sigma$ are 0.084 dex and 0.149 \(R_{\odot}\) respectively. Moreover, we assessed the uncertainty of model predictions, confirming good consistency within a reasonable deviation range. Finally, we applied our model to 50,871,534 SDSS stars without spectra and published a new catalog.

Study on risk factor analysis and model prediction of hyperuricemia in different populations.

The purpose of the present study was to explore the influencing factors of hyperuricemia (HUA) in different populations in Shandong Province based on clinical biochemical indicators. A prediction model for HUA was constructed to aid in the early prevention and screening of HUA. In total, 705 cases were collected from five hospitals, and the risk factors were analyzed by Pearson correlation analysis, binary logistic regression, and receiver operating characteristic (ROC) curve in the gender and age groups. All data were divided into a training set and test set (7:3). The training set included age, gender, total protein (TP), low-density lipoprotein cholesterol (LDL-C), and 15 other indicators. The random forest (RF) and support vector machine (SVM) methods were used to build the HUA model, and model performances were evaluated through 10-fold cross-validation to select the optimal method. Finally, features were extracted, and the ROC curve of the test set was generated. TP, LDL-C, and glucose (GLU) were risk factors for HUA, and the area under the curve (AUC) value of the SVM validation set was 0.875. The SVM model based on clinical biochemical indicators has good predictive ability for HUA, thus providing a reference for the diagnosis of HUA and the development of an HUA prediction model.

Passenger flow prediction at rail transit station entrances and exits: A case study of Beijing

Accurate prediction of passenger flow at station entrances and exits is a hot topic in rail transit passenger flow prediction work, and provides important support for the refined and humanized design of stations. This paper comprehensively considers factors such as land use around the station, traffic connection conditions, station attributes and attractiveness, and constructs a two-layer passenger flow prediction model, including traffic zone layer passenger flow prediction based on multivariate nonlinear regression and entrance and exit layer passenger flow prediction based on the CRITIC method. Based on available data, the model first predicts the total passenger flow at all entrances and exits in the traffic zone, and then distributes the total passenger flow to each entrance and exit of the traffic zone. Different types of rail transit stations were randomly selected to verify the effectiveness of the model. The results show that the error between the model prediction value and the actual value of the daily entrance and exit volume is within , and the average error is , which has a high prediction accuracy.

A Systematic Review of AI-Driven Prediction of Fabric Properties and Handfeel

Artificial intelligence (AI) is revolutionizing the textile industry by improving the prediction of fabric properties and handfeel, which are essential for assessing textile quality and performance. However, the practical application and translation of AI-predicted results into real-world textile production remain unclear, posing challenges for widespread adoption. This paper systematically reviews AI-driven techniques for predicting these characteristics by focusing on model mechanisms, dataset diversity, and prediction accuracy. Among 899 papers initially identified, 39 were selected for in-depth analysis through both bibliometric and content analysis. The review categorizes and evaluates various AI approaches, including machine learning, deep learning, and hybrid models, across different types of fabric. Despite significant advances, challenges remain, such as ensuring model generalization and managing complex fabric behavior. Future research should focus on developing more robust models, integrating sustainability, and refining feature extraction techniques. This review highlights the critical gaps in the literature and provides practical insights to enhance AI-driven prediction of fabric properties, thus guiding future textile innovations.