High Predictive Performance Research Articles

Frequency-adjusted borders ordinal forest: A novel tree ensemble method for ordinal prediction.

Ordinal responses commonly occur in psychology, e.g., through school grades or rating scales. Where traditionally parametric statistical models like the proportional odds model have been used, machine learning (ML) methods such as random forest (RF) are increasingly employed for ordinal prediction. With new developments in assessment and new data sources yielding increasing quantities of data in the psychological sciences, such ML approaches promise high predictive performance. As RF does not inherently account for ordinality, several extensions have been proposed. A promising approach lies in assigning optimized numeric scores to the ordinal response categories and using regression RF. However, these optimization procedures are computationally expensive and have been shown to yield only situational benefit. In this work, I propose Frequency-Adjusted Borders Ordinal Forest (fabOF), a novel tree ensemble method for ordinal prediction forgoing extensive optimization while offering improved predictive performance in simulation and an illustrative example of student performance. To aid interpretation, I additionally introduce a permutation variable importance measure for fabOF tailored towards ordinal prediction. When applied to the illustrative example, an interest in higher education, mother's education, and study time are identified as important predictors of student performance. The presented methodology is made available through an accompanying R package.

The potential of insulin resistance indices to predict non-alcoholic fatty liver disease in patients with type 2 diabetes

BackgroundThe triglyceride-glucose (TyG) index and related parameters, as well as the Homeostatic Model Assessment for Insulin Resistance (HOMA-IR), have been developed as insulin resistance markers to identify individuals at risk for non-alcoholic fatty liver disease (NAFLD). However, its use for predicting NAFLD in patients with type 2 diabetes mellitus (T2DM) remains unclear. In this study, we aimed to observe the performance of insulin resistance indices in diagnosing NAFLD combined with T2DM and to compare their diagnostic values in clinical practice.Patients and methodsOverall, 268 patients with T2DM from the Endocrinology Department of Jiangsu Provincial Hospital of Traditional Chinese Medicine were enrolled in this study and divided into two groups: an NAFLD group (T2DM with NAFLD) and a T2DM group (T2DM without NAFLD). General information and blood indicators of the participants were collected, and insulin resistance indices were calculated based on these data. Receiver operating characteristic (ROC) analysis was conducted to calculate the area under the curve (AUC) for insulin resistance-related indices, aiming to assess their ability to discriminate between T2DM patients with and without NAFLD.ResultsROC analysis revealed that among the five insulin resistance-related indices, four parameters (TyG, TyG-body mass index [BMI], TyG-waist circumference [WC], and TyG- (waist–hip ratio [WHR]) exhibited high predictive performance for identifying NAFLD, except for HOMA-IR (AUCs:0.710,0.738,0.737 and 0.730, respectivly). TyG-BMI demonstrated superior predictive value, especially in males. For males, the AUC for TyG-BMI was 0.764 (95% confidence interval [CI] 0.691–0.827). The sensitivity and specificity for male NAFLD were 90.32% and 47.89%, respectively. Moreover, in the Generalized linear regression models, there were positive associations of TyG, TyG-BMI, TyG-WC, TyG-WHR, and HOMA-IR with controlled attenuation parameter (CAP), with β values of 21.30, 0.745, 0.247, and 2.549 (all P < 0.001), respectively.ConclusionTyG-BMI is a promising predictor of NAFLD combined with T2DM, particularly in lean male patients.

Machine Learning Models Decoding the Association Between Urinary Stone Diseases and Metabolic Urinary Profiles

Background: Employing advanced machine learning models, we aim to identify biomarkers for urolithiasis from 24-h metabolic urinary abnormalities and study their associations with urinary stone diseases. Methods: We retrospectively recruited 468 patients at Peking Union Medical College Hospital who were diagnosed with urinary stone disease, including renal, ureteral, and multiple location stones, and had undergone a 24-h urine metabolic evaluation. We applied machine learning methods to identify biomarkers of urolithiasis from the urinary metabolite profiles. In total, 148 (34.02%) patients were with kidney stones, 34 (7.82%) with ureter stones, and 163 (34.83%) with multiple location stones, all of whom had detailed urinary metabolite data. Our analyses revealed that the Random Forest algorithm exhibited the highest predictive accuracy, with AUC values of 0.809 for kidney stones, 0.99 for ureter stones, and 0.775 for multiple location stones. The Super Learner Ensemble Method also demonstrated high predictive performance with slightly lower AUC values compared to Random Forest. Further analysis using multivariate logistic regression identified significant features for each stone type based on the Random Forest method. Results: We found that 24-h urinary magnesium was positively associated with both kidney stones and multiple location stones (OR = 1.195 [1.06–1.3525] and 1.3258 [1.1814–1.4949]) due to its high correlation with urinary phosphorus, while 24-h urinary creatinine was a protective factor for kidney stones and ureter stones, with ORs of 0.9533 [0.9117–0.996] and 0.8572 [0.8182–0.8959]. eGFR was a risk factor for ureter stones and multiple location stones, with ORs of 1.0145 [1.0084–1.0209] and 1.0148 [1.0077–1.0223]. Conclusion: Machine learning techniques show promise in revealing the links between urological stone disease and 24-h urinary metabolic data. Enhancing the prediction accuracy of these models leads to improved dietary or pharmacological prevention strategies.

DF-BETA: An FPGA-based Memory Locality Aware Decision Forest Accelerator via Bit-Level Early Termination

Decision forests, particularly Gradient Boosted Decision Trees (GBDT), are popular due to their high prediction performance and computational efficiency, making them suitable for embedded systems with circuit size and available energy constraints. In this study, we propose a new lightweight GBDT inference acceleration mechanism through the hardware and algorithm co-design. First, we present LoADPack, a hardware-friendly GBDT algorithm that enhances memory access locality. LoADPack obtains trees where the features and thresholds used across the entire ensemble are regular regardless of a branching direction by unifying some nodes and aligning the memory access patterns. Furthermore, we present DF-BETA, a resource-efficient accelerator for the LoADPack algorithm. DF-BETA utilizes MSB-first bit-serial computation to enable early determination of comparison calculations of 32-bit floating-point numbers, optimizing the operation for determining a branch direction. The hardware complexity and computation termination speed vary with the granularity of bit-serial computation. Therefore, we conduct design space exploration of DF-BETA to identify the optimal configuration. Our findings reveal that using 4-bit-serial comparators minimizes circuit size while achieving the leading throughput. Compared to running unconstrained GBDT on a typical accelerator with 32-bit bit-parallel comparators, our accelerator achieves 1.6 times higher throughput on average while maintaining comparable accuracy.

Meteorological and satellite-based data for drought prediction using data-driven model

This work presents a data-driven model, the Artificial Neural Network-Multilayer Perceptron Neural Network (ANN-MLP), for use in meteorological drought deciles index (DDI) predictions over various climatic sub-zone. Two types of rainfall data from meteorological weather stations (WSs) and satellite-based estimates of PERSIANN (Precipitation Estimation from Remotely Sensed Information using Artificial Neural Network) were adopted. This work considered the calculated DDI (DDI original) from WSs to train and develop the proposed algorithm at three sub-zones (ANN-MLP-DDI models). The newly developed model was tested for DDI prediction using PERSIANN, and compared with the calculated DDI original from WSs. The results positively revealed that the ANN-MLP-DDI models showed high performance (Correlation coefficient r= 0.981) for DDI prediction against the DDI original from WSs. It can be concluded that data-driven models are feasible for drought prediction, and this work could help water managers in mitigating drought impacts and in providing information for policy makers

CT assessment of liver fat fraction and abdominal fat composition can predict postoperative liver metastasis of colorectal cancer

ObjectiveThe aim of this study is to investigate the clinical value of liver fat fraction assessed by CT(CT-LFF) and abdominal fat components. We focus on predicting liver metastasis (LM) after colorectal cancer (CRC) surgery. MethodsClinical and imaging data from 79 patients who underwent radical CRC surgery between January 2019 and December 2021 were retrospectively collected. Semi-automatic software was used to quantify the area of different body tissues at the level of the third lumbar vertebra, and liver fat fraction was calculated based on the CT values. Patients were grouped according to BMI, tumor grade, T stage, N stage, vascular invasion (VI), perineural invasion (PNI), and preoperative levels of CEA and CA199. A multivariate logistic regression model was used to identify independent risk factors for early LM after surgery. The diagnostic performance was assessed using the receiver operating characteristic analysis with 5-fold cross-validation. The Kaplan-Meier method was used to draw survival curves, and Log-Rank test was used for survival analysis. ResultsThe study found that the occurrence of LM after CRC surgery was significantly associated with CA199 positivity, VI, PNI, N1-2 stage, CT-LFF, VAT index (VATI). Multivariate logistic regression analysis showed that CA199 positivity (OR = 7.659), N1-2 stage (OR = 6.394), CT-LFF (OR = 1.271), VATI (OR = 1.043) were independent risk factors for predicting LM after CRC surgery. The multivariate logistic regression model, constructed using these independent risk factors, demonstrated robust predictive performance across 5-fold cross-validations, with an average AUC of 0.898 (95 % CI: 0.828–0.969). Survival analysis showed a significant difference in liver metastasis-free survival rates between the high-risk and low-risk groups (P < 0.001). ConclusionCT-LFF and VATI assessed by CT are independent risk factors for predicting LM after CRC surgery. The multivariate prediction model combining CA199 and N stage shows high predictive performance.

Service Life Prediction of High-Performance and Ultra‑High-Performance Concrete Structures with Corrosion-Resistant Steels

Service Life Prediction of High-Performance and Ultra‑High-Performance Concrete Structures with Corrosion-Resistant Steels

Leveraging Shapley Additive Explanations for Feature Selection in Ensemble Models for Diabetes Prediction

Diabetes, a significant global health crisis, is primarily driven in India by unhealthy diets and sedentary lifestyles, with rapid urbanization amplifying these effects through convenience-oriented living and limited physical activity opportunities, underscoring the need for advanced preventative strategies and technology for effective management. This study integrates Shapley Additive explanations (SHAPs) into ensemble machine learning models to improve the accuracy and efficiency of diabetes predictions. By identifying the most influential features using SHAP, this study examined their role in maintaining high predictive performance while minimizing computational demands. The impact of feature selection on model accuracy was assessed across ten models using three feature sets: all features, the top three influential features, and all except these top three. Models focusing on the top three features achieved superior performance, with the ensemble model attaining a better performance in most of the metrics, outperforming comparable approaches. Notably, excluding these features led to a significant decline in performance, reinforcing their critical influence. These findings validate the effectiveness of targeted feature selection for efficient and robust clinical applications.

Innovative automatic optimization method for ejectors in fuel cell vehicles based on a combined optimization strategy

Ejectors exhibit significant advantages in the field of fuel cell vehicles, playing a crucial role in promoting their development. Their fixed structure results in non-parasitic power consumption, yet this also poses greater challenges for optimizing their structural parameters across different application scenarios. However, most of the research focuses on the positions such as the nozzle and mixing section, and there is no effective method to determine the values of all parameters. In order to solve the above problems, an innovative automatic optimization method using a combined optimization strategy (COS) with a weight factor is proposed for achieving multi-objective optimization of ejectors. The COS combines parametric modeling, computational fluid dynamics, approximate modeling techniques, and multi-objective optimization to tune the full parameters. The results indicate that the COS achieves a high performance prediction accuracy with an R2 value of 0.9711 and a root mean square error of 9.23E-6. Furthermore, in the case of 300 computational samples, the computational time is reduced by 54.7%. The entrainment ratio has been increased to 4.17 times its pre-optimization level. The novel method not only ensures the simulation accuracy but also significantly enhances computational efficiency, making it a powerful tool for guiding the production and optimization of ejectors.

Using machine learning towards enhancement of electrochemical activity in OER/ORR half-reactions of MXene cathode materials for Li-air batteries

Metal-air batteries are the target of the ever-growing interest as considering as the new “lead” technology among the most promising electrochemical energy storage solutions. The projected energy density of lithium-air batteries considered in this study exceeds current commercial lithium-ion batteries by more than three times. In this study, we consider the characteristics of MXenes, 2D layered phases with such attractive characteristics as a high specific surface area with the numerous active reaction centers, mechanical strength, the diverse functional characteristics and the perspectives of scalability of their production, which are of importance for the practical realization of Li-air batteries of different architecture. The formation of the phases of complex content and structure inherent to pseudomorphism at the interface, as it is actual for the objects of our study, allows one to conclude that it is necessary to consider the processes that occur at the interfaces of lithium-air battery cathodes in direct relation to the cathode material used. Machine learning methods were involved in model development for (i) MXenes predicting the electrochemical phase diagrams, Pourbaix diagrams, which circumscribe the stability window of MXenes of certain composition formed with synthesis-defined terminations as a function of pH and USHE for single and double MXenes and (ii) the elastic characteristics of MAX phases, precursors of MXenes, to assess the commensurability of the interface of MXene cathode materials and Li2O2 phase as well as the prospects of using target MXene compositions combined with the solid electrolyte materials of different families for employing in all-solid-state Li-air batteries. The obtained models demonstrate high predictive performance that argue on the possibility to use them for rational screening of new phases with desired functional characteristics.

Development and validation of Galectin-3 and CVAI-based model for predicting cognitive impairment in type 2 diabetes.

The objective of this study is to develop a predictive model combining multiple indicators to quantify the risk of mild cognitive impairment (MCI) in T2DM patients. This study included Chinese T2DM patients who were hospitalized at Zhongda Hospital between November 2021 and May 2023. Clinical data, including demographics, medical history, biochemical tests, and cognitive status, were collected. Cognitive assessment was performed using neuropsychological tests, and MCI was diagnosed based on the Montreal Cognitive Assessment (MoCA) scores. The dataset was randomly divided into a training set and a validation set in a 7:3 ratio. Logistic regression analysis was conducted to identify factors influencing MCI in the training set. A nomogram-based scoring model was then developed by integrating these findings with high-risk clinical variables, and its performance was validated in the validation set. In this study, T2DM patients were divided into a training set and a validation set in a 7:3 ratio. There were no significant differences in MCI incidence, demographics, or clinical characteristics between the two groups, confirming the appropriateness of model construction. In the training set, Galectin-3 and CVAI were significantly negatively correlated with cognitive function (MoCA and MMSE scores), and this negative correlation remained after adjusting for confounding variables. Logistic regression analysis revealed that age, CVAI, and Galectin-3 significantly increased the risk of MCI, while years of education had a protective effect. The constructed nomogram model, which integrated age, sex, education level, hypertension, CVAI, and Galectin-3 levels, exhibited high predictive performance (C-index of 0.816), with AUCs of 0.816 in the training set and 0.858 in the validation set, outperforming single indicators. PR curve analysis further validated the superiority of the nomogram model. The straightforward, highly accurate, and interactive nomogram model developed in this study facilitate the early risk prediction of MCI in individuals with T2DM by incorporating Galectin-3, CVAI, and other common clinical risk factors.

DAPNet: multi-view graph contrastive network incorporating disease clinical and molecular associations for disease progression prediction

BackgroundTimely and accurate prediction of disease progress is crucial for facilitating early intervention and treatment for various chronic diseases. However, due to the complicated and longitudinal nature of disease progression, the capacity and completeness of clinical data required for training deep learning models remains a significant challenge. This study aims to explore a new method that reduces data dependency and achieves predictive performance comparable to existing research.MethodsThis study proposed DAPNet, a deep learning-based disease progression prediction model that solely utilizes the comorbidity duration (without relying on multi-modal data or comprehensive medical records) and disease associations from biomedical knowledge graphs to deliver high-performance prediction. DAPNet is the first to apply multi-view graph contrastive learning to disease progression prediction tasks. Compared with other studies on comorbidities, DAPNet innovatively integrates molecular-level disease association information, combines disease co-occurrence and ICD10, and fully explores the associations between diseases;ResultsThis study validated DAPNet using a de-identified clinical dataset derived from medical claims, which includes 2,714 patients and 10,856 visits. Meanwhile, a kidney dataset (606 patients) based on MIMIC-IV has also been constructed to fully validate its performance. The results showed that DAPNet achieved state-of-the-art performance on the severe pneumonia dataset (F1=0.84, with an improvement of 8.7%), and outperformed the six baseline models on the kidney disease dataset (F1=0.80, with an improvement of 21.3%). Through case analysis, we elucidated the clinical and molecular associations identified by the DAPNet model, which facilitated a better understanding and explanation of potential disease association, thereby providing interpretability for the model.ConclusionsThe proposed DAPNet, for the first time, utilizes comorbidity duration and disease associations network, enabling more accurate disease progression prediction based on a multi-view graph contrastive learning, which provides valuable insights for early diagnosis and treatment of patients. Based on disease association networks, our research has enhanced the interpretability of disease progression predictions.

Establishment and validation of predictive model of prostate cancer

Prostate cancer is a prevalent malignant disease among middle-aged and elderly men. Its prevention and detection are significant public health issues. We aimed to construct an interpretable model for predicting death risk in prostate cancer patients. We performed model development using the Cancer Genome Atlas and the Genotype-Tissue Expression databases. In comparison among models, the SVM model has the highest prediction performance among the eight models. The SHAP method, sorted by importance, reveals the top eight predictors of prostate cancer disease. This effective computer-aided approach can facilitate frontline clinicians in the diagnosis and management of patients with prostate cancer.

Collision causal discovery and real-time prediction of freeway tunnels: A novel dual-task approach

Although tunnels are critical traffic nodes in freeway networks, academic research addressing their real-time traffic safety is noticeably lacking. This study proposes a novel dual-task approach to analyze causal precursors and predict real-time collision risks in freeway tunnels. Unlike traditional models, which often trade off between predictive accuracy and causal depth, the proposed approach achieves both high causal interpretability and predictive performance. The approach utilizes a structural agnostic model (SAM) to discover causal precursors of freeway tunnel collisions using observational data. The collision causal graph data is then constructed based on the causal relationships identified by SAM. Additionally, the Causal Directed Graph Convolutional Networks (CDGCN) model is developed to capture causal relationships in the graph for real-time collision prediction. Utilizing freeway tunnel collision analysis data collected from the Caltrans Performance Measurement System, the approach performs dual tasks: identifying causal precursors of collisions and predicting future collisions in real time. The SAM results reveal five critical causal precursors influencing the likelihood of collisions. Comparative analyses with existing interpretable machine learning models show similarities between the causal precursors of tunnel collision risk revealed by SAM and the important correlation precursors identified by the comparative models. However, correlation is not the same as causation. When tested against current state-of-the-art real-time collision predictive models, the proposed CDGCN model demonstrates superior accuracy, especially on datasets containing causally relevant precursors, highlighting the potential of this approach for feature selection and risk prediction. This advancement not only provides a practical framework for mitigating collision risks in freeway tunnels but also makes a significant contribution to traffic safety research.

Prediction of Floor Failure Depth in Coal Mines: A Case Study of Xutuan Mine, China

Accurately predicting the failure depth of coal seam floors is crucial for preventing water damage, ensuring the safe and efficient mining of coal seams, and protecting the ecological environment of mining areas. In order to improve the prediction accuracy of the coal seam floor failure depth, an improved support vector regression (SVR) model is proposed to predict the floor failure depth by taking the 3234 working face in Xutuan Mine as an example. This improved model incorporates principal component analysis (PCA) and slime mould algorithm (SMA) optimization techniques. First, based on the measured data of seam floor failure depth in several mining areas, a prediction index system of floor failure depth was constructed. Subsequently, the PCA method was used to reduce the dimension of the measured data of the coal seam floor failure depth, and the input structure of the SVR model was optimized. Then, the SMA was used to optimize the key parameters, namely the penalty factor (C) and kernel function parameter (g), in the SVR model, achieving automatic parameter selection and obtaining the optimal parameter combination. This process led to the establishment of a coal seam floor failure depth prediction model based on PCA-SMA-SVR. The predictive performance of the PCA-SMA-SVR model, SMA-SVR model, and SVR model was quantitatively evaluated and compared using four quantitative indicators, and the results showed that the PCA-SMA-SVR model had the smallest MAE, RMSE, MRE, and TIC values, which were 1.0470 m, 1.2928 m, 0.0628, and 0.0374, respectively. Finally, the PCA-SMA-SVR model was used to predict that the floor failure depth of the 3234 working face in Xutun Mine was 17.09 m, and the predicted result was compared and analyzed with the results of four commonly used empirical formulas (16.03–21.74 m). The results show that the model is close to the results of four commonly used empirical formulas, indicating that the model has high predictive performance and good practicality. This study is of great significance for the safety, green mining, and ecological environment protection of coal mines.

Evaluation of Electrical Properties and Uniformity of Single Wall Carbon Nanotube Dip-Coated Conductive Fabrics Using Convolutional Neural Network-Based Image Analysis

This study proposes a convolutional neural network (CNN)-based image analysis method to evaluate the electrical properties and uniformity of conductive fabrics treated with single-walled carbon nanotube (SWCNT) dip-coating. The conductive fabric was produced by dip-coating cotton-blended spandex with SWCNT, and the surface images were scanned and preprocessed to obtain image data, while resistance measurements were conducted to obtain labels and build the dataset. SEM analysis revealed that as the number of dip-coating cycles increased, particle density and path formation improved. The CNN model learned the relationship between surface images and resistance values, achieving a high predictive performance, with an R-squared (R²) value of 0.9422. The model demonstrated prediction accuracies of 99.1792% for the coefficient of variation (CV) of uniformly coated fabrics and 96.8877% for non-uniformly coated fabrics. Additionally, p-value analysis of all fabric samples yielded a result of 0.96044, indicating no statistically significant difference between the predicted and actual values. The proposed CNN-based model can accurately evaluate the electrical uniformity of conductive fabrics, showing potential for contributing to quality control and process optimization in production.

Adrenal indeterminate nodules: CT-based radiomics analysis of different machine learning models for predicting adrenal metastases in lung cancer patients.

There is a paucity of research using different machine learning algorithms for distinguishing between adrenal metastases and benign tumors in lung cancer patients with adrenal indeterminate nodules based on plain and biphasic-enhanced CT radiomics. This study retrospectively enrolled 292 lung cancer patients with adrenal indeterminate nodules (training dataset, 205 (benign, 96; metastases, 109); testing dataset, 87 (benign, 42; metastases, 45)). Radiomics features were extracted from the plain, arterial, and portal CT images, respectively. The independent risk radiomics features selected by least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression (LR) were used to construct the single-phase and combined-phase radiomics models, respectively, by support vector machine (SVM), decision tree (DT), random forest (RF), and LR. The independent clinical-pathological and radiological risk factors for predicting adrenal metastases selected by using univariate and multivariate LR were used to develop the traditional model. The optimal model was selected by ROC curve, and the models' clinical values were estimated by decision curve analysis (DCA). In the testing dataset, all SVM radiomics models showed the best robustness and efficiency, and then RF, LR, and DT models. The combined radiomics model had the best ability in predicting adrenal metastases (AUC=0.938), and then the plain (AUC=0.935), arterial (AUC=0.870), and portal radiomics model (AUC=0.851). Besides, compared to clinical-pathological-radiological model (AUC=0.870), the discriminatory capability of the plain and combined radiomics model were further improved. All radiomics models had good calibration curves and DCA showed the plain and combined radiomics models had more optimal clinical efficacy compared to other models, with the combined radiomics model having the largest net benefit. The combined SVM radiomics model can non-invasively and efficiently predict adrenal metastatic nodules in lung cancer patients. In addition, the plain radiomics model with high predictive performance provides a convenient and accurate new method for patients with contraindications in enhanced CT.

An interpretable electrocardiogram-based model for predicting arrhythmia and ischemia in cardiovascular disease

IntroductionCardiovascular disease (CVD) is a leading cause of death and disability globally, with ischemia and arrhythmias being critical contributors. Ischemia, due to reduced myocardial blood flow, can lead to sudden cardiac death, while arrhythmias, marked by abnormal heart rhythms, are common in the elderly. Electrocardiography (ECG) is essential for the diagnosis of these conditions. This study aims to develop a clinically interpretable diagnostic framework for ischemia and arrhythmias using key ECG fiducial features. MethodsTo develop a robust ECG-based model for predicting cardiovascular diseases, we integrated data from three well-established ECG datasets: MIT-BIH Arrhythmia, European ST-T, and Fantasia. This aggregated dataset was employed to train multiple machine learning (ML) models aimed at automatically classifying heart conditions, including arrhythmia, ischemia, and healthy states. We designed a predictive framework utilizing boosting ML algorithms, enhanced by explainable artificial intelligence (XAI) techniques, to ensure high predictive performance in model interpretation. ResultsThe histogram gradient boosting classifier demonstrated superior classification performance, achieving an overall accuracy of 90 % in predicting heart disease based on ECG fiducial features. The model achieved area under the curve (AUC) scores of 0.99, 0.99, and 0.89 for the healthy, ischemic, and arrhythmic classes, respectively. XAI methods revealed that ECG fiducial features, such as the P-H, R-H, RR interval, QRS duration, QT interval, and ST segment, were significant diagnostic indicators for heart disease. ConclusionsThis study uses machine learning and XAI models to classify arrhythmia and ischemia from ECG data, enhancing interpretability clinical diagnostics for prevention and intervention to reduce disabilities.

Plastic Injection Molding Process Analysis: Data Integration and Modeling for Improved Production Efficiency

This paper presents a comprehensive analysis of the plastic injection molding process through the integration of data acquisition technologies and classification models. In collaboration with a company specializing in plastic injection, data were extracted directly from the machine during a specific period at the beginning of a shift change. These data were subjected to exploratory analysis to identify correlations between important variables, such as injection time, cycle time, and mold pressures. Additionally, classification models, including Random Forest and Logistic Regression, were constructed to predict and classify the process state based on these variables. The model results demonstrated high predictive performance, with 99.5% accuracy for Random Forest and 97% for Logistic Regression. These results provide a strong foundation for the early identification of potential problems and informed decision making to improve the efficiency of the plastic injection molding process. This study contributes to the advancement of the integration of intelligent technologies in industrial process optimization, aligned with the principles of Industry 4.0.

M-NET: Transforming Single Nucleotide Variations into Patient Feature Images for the Prediction of Prostate Cancer Metastasis and Identification of Significant Pathways.

High-performance prediction of prostate cancer metastasis based on single nucleotide variations remains a challenge. Therefore, we developed a novel biologically informed deep learning framework, named M-NET, for the prediction of prostate cancer metastasis. Within the framework, we transformed single nucleotide variations into patient feature images that are optimal for fitting convolutional neural networks. Moreover, we identified significant pathways associated with the metastatic status. The experimental results showed that M-NET significantly outperformed other comparison methods based on single nucleotide variations, achieving improvements in accuracy, precision, recall, F1-score, area under the receiver operating characteristics curve, and area under the precision-recall curve by 6.3%, 8.4%, 5.1%, 0.070, 0.041, and 0.026, respectively. Furthermore, M-NET identified some important pathways associated with the metastatic status, such as signaling by the hedgehog pathway. In summary, compared with other comparative methods, M-NET exhibited a better performance in the prediction of prostate cancer metastasis.