Individual Models Research Articles

Triglyceride to high-density lipoprotein ratio as a predictor for 10-year cardiovascular disease in individuals with diabetes in Thailand

BackgroundCardiovascular disease (CVD) remains the leading cause of morbidity and mortality worldwide. The triglyceride to high-density lipoprotein cholesterol (TG/HDL) ratio has emerged as a potential marker for CVD risk. However, its predictive value for high 10-year predicted Cardiovascular (CV) risk remains unclear; This study evaluates the predictive value of the TG/HDL-C ratio for 10-year cardiovascular risk using the Framingham Heart Study (FHS) risk prediction model in individuals with Type 2 Diabetes Mellitus (T2DM).MethodsA cross-sectional study was conducted on 61,004 adults from 2014,2015, and 2018 aged 30–74 years with T2DM, without a history of CVD. The FHS model was used to estimate 10-year predicted CV risk, and high CVD risk was defined as ≥ 20%. ROC curve analysis was used to determine the optimal TG/HDL cutoff for high 10-year predicted CV risk in the overall population and age-specific subgroups. Logistic regression was performed to find the association between TG/HDL and high 10-year predicted CV risk, adjusting for potential confounders.ResultsThe optimal TG/HDL-C cutoff was 2.52 (AUC = 0.618, 95% CI: 0.612–0.624), with 67% sensitivity and 50% specificity. Higher TG/HDL were associated with increased odds of high predicted CVD risk in a dose-dependent manner, with an adjusted odds ratio (AOR) of 5.16 (95% CI: 4.86–5.49) in the highest TG/HDL quartile (> 4.91). Age-stratified analysis identified lower cutoffs for older adults (≥ 60 years: 2.42, AUC = 0.694) than younger individuals (< 60 years: 2.98, AUC = 0.636), indicating stronger predictive performance in older adults.ConclusionsThe TG/HDL ratio is significantly associated with 10-year predicted CVD risk in T2DM with age-specific differences in predictive value. The lower cutoff for older adults (2.42) suggests even modest elevations indicate increased risk. These findings support TG/HDL integration into routine CVD risk assessments and highlight the importance of age-specific cutoffs for improved risk stratification.

Comparison of Large Language Models' Performance on 600 Nuclear Medicine Technology Board Examination-Style Questions.

This study investigated the application of large language models (LLMs) with and without retrieval-augmented generation (RAG) in nuclear medicine, particularly their performance across various topics relevant to the field, to evaluate their potential use as reliable tools for professional education and clinical decision-making. Methods: We evaluated the performance of LLMs, including the OpenAI GPT-4o series, Google Gemini, Cohere, Anthropic, and Meta Llama3, across 15 nuclear medicine topics. The models' accuracy was assessed using a set of 600 sample questions, covering a range of clinical and technical domains in nuclear medicine. Overall accuracy was measured by averaging performance across these topics. Additional performance comparisons were conducted across individual models. Results: OpenAI's models, particularly openai_nvidia_gpt-4o_final and openai_mxbai_gpt-4o_final, demonstrated the highest overall accuracy, achieving scores of 0.787 and 0.783, respectively, when RAG was implemented. Anthropic Opus and Google Gemini 1.5 Pro followed closely, with competitive overall accuracy scores of 0.773 and 0.750 with RAG. Cohere and Llama3 models showed more variability in performance, with the Llama3 ollama_llama3 model (without RAG) achieving the lowest accuracy. Discrepancies were noted in question interpretation, particularly in complex clinical guidelines and imaging-based queries. Conclusion: LLMs show promising potential in nuclear medicine, improving diagnostic accuracy, especially in areas like radiation safety and skeletal system scintigraphy. This study also demonstrates that adding a RAG workflow can increase the accuracy of an off-the-shelf model. However, challenges persist in handling nuanced guidelines and visual data, emphasizing the need for further optimization in LLMs for medical applications.

Smart indoor monitoring for disabled individuals using an ensemble of deep learning models in an IoT environment

Indoor activity monitoring methods assurance the well-being and security of disabled and aging individuals living in their homes. These models utilize numerous technologies and sensors to monitor day-to-day work like movement, medication adherence, and sleep patterns, and provide valued perceptions of the user’s everyday life and entire health. Internet of Things (IoT) based health systems have an important part in medical assistance and help in enhancing data processing and its prediction. Communicating data or reports requires more time and energy, in addition to causing energy problems and greater latency. Currently, numerous studies focus on human activity recognition (HAR) using deep learning (DL) and machine learning (ML) methods, but more effort is needed to enhance HAR models for disabled individuals. Therefore, this article presents a Smart Indoor Monitoring for Disabled People Using an Ensemble of Deep Learning Models in an Internet of Things Environment (SIMDP-EDLIoT) technique. The SIMDP-EDLIoT model is designed to monitor and detect various conditions and activities within indoor spaces for disabled people. Initially, the SIMDP-EDLIoT approach uses linear scaling normalization (LSN) to ensure that the input data is scaled appropriately. Besides, the Improved Osprey Optimization Algorithm (IOOA)-based feature selection is employed to classify the most relevant features, enhancing the efficiency of the system by reducing dimensionality. For monitoring indoor activities, an ensemble of three DL techniques such as bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), and conditional variational autoencoder (CVAE) are employed. Experimental study is performed to underscore the importance of the SIMDP-EDLIoT method under the HAR dataset. The comparative analysis of the SIMDP-EDLIoT method demonstrated a superior performance with an accuracy of 98.85%, precision of 97.71%, sensitivity of 97.70%, specificity of 99.24%, and F-measure of 97.70%, outperforming existing approaches across all metrics.

Examination of fractional order model for the population of diabetes and the effects of changes in lifestyle on remission

ABSTRACT Diabetes can always be avoided or controlled by maintaining a balanced diet and exercising regularly. Recent studies have shown that putting a diabetic patient into remission through a strict lifestyle modification programme can help their blood glucose levels return to normal. Nesreen A. et al. introduced a mathematical model of integer order incorporating a Holling type II treatment function. This study extends their work by proposing two fractional-order mathematical models for diabetic individuals, where pre-diabetes progresses to diabetes and remission occurs at moderate-to-severe levels solely through lifestyle changes, without medical treatment. The first fractional model does not include remission, but the second fractional model does. We use the fixed point theorem to show that the suggested diabetes model has a solution. We proceed by considering the stability of the equilibrium point. Further, we employed the Adams-Bashforth-Moulton technique to demonstrate the Type 2 diabetes model’s numerical solution with the help of MATLAB software. Numerical simulation results for a fractional-order Type 2 diabetes model show a clear influence of the derivative’s order and the remission parameters on the diabetic population.

Developing an ensemble machine learning framework for enhanced climate projections using CMIP6 data in the Middle East

Climate change in the Middle East has intensified with rising temperatures, shifting rainfall patterns, and more frequent extreme events. This study introduces the Stacking-EML framework, which merges five machine learning models three meta-learners to predict maximum temperature, minimum temperature, and precipitation using CMIP6 data under SSP1-2.6, SSP2-4.5, and SSP5-8.5. The results indicate that Stacking-EML not only significantly improves prediction accuracy compared to individual models and traditional CMIP6 outputs but also enhances climate projections by integrating multiple ML models, offering more reliable, regionally refined forecasts. Findings show R² improvements to 0.99 for maximum temperature, 0.98 for minimum temperature, and 0.82 for precipitation. Under SSP5-8.5, summer temperatures in southern regions are expected to exceed 45 °C, exacerbating drought conditions due to reduced rainfall. Spatial analysis reveals that Saudi Arabia, Oman, Yemen, and Iran face the greatest heat and drought impacts, while Turkey and northern Iran may experience increased precipitation and flood risks.

Deep ensemble learning-driven fully automated multi-structure segmentation for precision craniomaxillofacial surgery

ObjectivesAccurate segmentation of craniomaxillofacial (CMF) structures and individual teeth is essential for advancing computer-assisted CMF surgery. This study developed CMF-ELSeg, a novel fully automatic multi-structure segmentation model based on deep ensemble learning.MethodsA total of 143 CMF computed tomography (CT) scans were retrospectively collected and manually annotated by experts for model training and validation. Three 3D U-Net–based deep learning models (V-Net, nnU-Net, and 3D UX-Net) were benchmarked. CMF-ELSeg employed a coarse-to-fine cascaded architecture and an ensemble approach to integrate the strengths of these models. Segmentation performance was evaluated using Dice score and Intersection over Union (IoU) by comparing model predictions to ground truth annotations. Clinical feasibility was assessed through qualitative and quantitative analyses.ResultsIn coarse segmentation of the upper skull, mandible, cervical vertebra, and pharyngeal cavity, 3D UX-Net and nnU-Net achieved Dice scores above 0.96 and IoU above 0.93. For fine segmentation and classification of individual teeth, the cascaded 3D UX-Net performed best. CMF-ELSeg improved Dice scores by 3%–5% over individual models for facial soft tissue, upper skull, mandible, cervical vertebra, and pharyngeal cavity segmentation, and maintained high accuracy Dice &amp;gt; 0.94 for most teeth. Clinical evaluation confirmed that CMF-ELSeg performed reliably in patients with skeletal malocclusion, fractures, and fibrous dysplasia.ConclusionCMF-ELSeg provides high-precision segmentation of CMF structures and teeth by leveraging multiple models, serving as a practical tool for clinical applications and enhancing patient-specific treatment planning in CMF surgery.

Optimal Forecast Combination for Japanese Tourism Demand

This study introduces a novel forecast combination method for monthly Japanese tourism demand, analyzed at both aggregated and disaggregated levels, including tourist, business, and other travel purposes. The sample period spans from January 1996 to December 2018. Initially, the time series data were decomposed into high and low frequencies using the Ensemble Empirical Mode Decomposition (EEMD) technique. Following this, Autoregressive Integrated Moving Average (ARIMA), Neural Network (NN), and Support Vector Machine (SVM) forecasting models were applied to each decomposed component individually. The forecasts from these models were then combined to produce the final predictions. Our findings indicate that the two-stage forecast combination method significantly enhances forecasting accuracy in most cases. Consequently, the combined forecasts utilizing EEMD outperform those generated by individual models.

An innovative machine learning approach for slope stability prediction by combining shap interpretability and stacking ensemble learning.

Accurate slope stability prediction is crucial for mitigating slope failures, but conventional methods are challenging due to their complexity and high data requirements. To overcome these limitations, researchers have used machine learning (ML) techniques enabled by advances in data science. This paper presents an innovative ML approach, which combines the SHapley Additive exPlanations (SHAP) and stacking ensemble learning (EL) techniques (SHAP-EL), to classify and predict slope stability. A total of 627 slope case records, which comprise geological (slope height and slope angle) and geotechnical parameters (unit weight, cohesion, friction angle, and pore pressure ratio), are utilized to build prediction models. During model construction, SHAP analysis is first performed to identify the most influential base learning models among ten different ML algorithms, including XGBoost, GBM, AdaBoost, RF, SVM, ANN, ELM, GLM, GLMnet, and CART. Then, using the stacking EL approach, the optimal ML models identified by SHAP analysis as base learners are integrated to develop a final predictive model for slope stability. The SHAP-EL model is evaluated against individual ML models to select optimum model for slope stability prediction using metrics, such as Accuracy, Kappa, Precision, Recall, and F1-Score. The results of the study indicated that the SHAP-based stacking EL model demonstrated outstanding predictive performance, reaching an accuracy of 96.24%, Kappa of 91.89%, Precision of 96.74%, Recall of 95.70%, and F1-Score of 96.22%. Based on the individual model accuracies, the models are ranked from highest to lowest as follows: SHAP-EL (96.24%) > XGBoost (94.64%) > RF (94.09%) > AdaBoost (93.55%) > GBM (82.80%). The findings of the study can contribute to enhancing the accuracy and reliability of soil slope predictions and can help mitigate the risks and damages associated with soil slope instability.

Ensemble Learning Techniques for Breast Cancer Prediction

Breast cancer is predominantly diagnosed in women and remains a leading cause of rising health concerns among females. Manual identification of the disease is often time-consuming and limited in accessibility. To address this, automated diagnostic systems using machine learning (ML) have become increasingly valuable for early detection and classification of cancer. This paper explores the use of machine learning and ensemble learning techniques for classifying tumors. Specifically, it evaluates the performance of Logistic Regression, Support Vector Machines (SVM), Decision Trees, and Random Forests on a breast cancer dataset. The study compares models based on key performance metrics, including False Positive Rate, Accuracy, Precision, and Recall. The effectiveness of ensemble learning methods is also analyzed and benchmarked against individual models. Statistical analysis reveals that the ensemble model combining Decision Tree and Random Forest algorithms achieves an accuracy of 89.3%, while the ensemble of Logistic Regression and SVM reaches an accuracy of 90.4%. These ensemble models outperform their counterparts, demonstrating the advantages of combining multiple algorithms for improved diagnostic accuracy.

Comparative evaluation of hybrid and individual models for predicting soybean yellow mosaic virus incidence

Forecasting the severity of crop diseases is crucial for agricultural productivity and can be achieved through statistical and machine learning techniques. Predictive models that consider weather conditions during critical growth stages of crops have shown promising accuracy. However, selecting the most suitable forecasting model remains a challenge. This research investigates the impact of various weather factors on Soybean Yellow Mosaic Virus (SYMV) incidence. Specifically, six multivariate models Stepwise Multiple Linear Regression (SMLR), Artificial Neural Networks (ANN), Least Absolute Shrinkage and Selection Operator (LASSO), Ridge Regression (RR), Elastic Net (ELNET), and SMLR_ANN both direct and with Principal Component Analysis (PCA)-were developed using 20 years of data (2001 to 2020) to predict the severity of soybean disease in Pantnagar, Uttarakhand. The dataset was divided into two parts, with 80% used for calibration and the remaining 20% for validation. Model accuracy was evaluated using several statistical criteria, including R², RMSE, nRMSE, MAE, PE, and EF. The results indicated that the PCA-SMLR-ANN (nRMSEval = 0.76%) model was the most effective predictor of soybean disease severity, closely followed by the PCA-ANN (nRMSEval = 3.67%) model. Hybrid models such as PCA-SMLR-ANN and PCA-ANN outperformed individual models like SMLR (nRMSEval = 47.72%) and ANN (nRMSEval = 6.82%). The performance ranking of the models is as follows: PCA-SMLR-ANN ≈ PCA-ANN ≈ SMLR-ANN ≈ ANN > PCA-ELNET > PCA-Ridge > ELNET ≈ RR > PCA-LASSO > LASSO > PCA-SMLR ≈ SMLR. These findings highlight the superior efficiency of hybrid models in predicting soybean disease severity based on weather indices in the study region.

Integrating Support Vector Machines and Deep Learning Features for Oral Cancer Histopathology Analysis

Abstract This study introduces an approach to classifying histopathological images for detecting dysplasia in oral cancer through the fusion of support vector machine (SVM) classifiers trained on deep learning features extracted from InceptionResNet-v2 and vision transformer (ViT) models. The classification of dysplasia, a critical indicator of oral cancer progression, is often complicated by class imbalance, with a higher prevalence of dysplastic lesions compared to non-dysplastic cases. This research addresses this challenge by leveraging the complementary strengths of the two models. The InceptionResNet-v2 model, paired with an SVM classifier, excels in identifying the presence of dysplasia, capturing fine-grained morphological features indicative of the condition. In contrast, the ViT-based SVM demonstrates superior performance in detecting the absence of dysplasia, effectively capturing global contextual information from the images. A fusion strategy was employed to combine these classifiers through class selection: the majority class (presence of dysplasia) was predicted using the InceptionResNet-v2-SVM, while the minority class (absence of dysplasia) was predicted using the ViT-SVM. The fusion approach significantly outperformed individual models and other state-of-the-art methods, achieving superior balanced accuracy, sensitivity, precision, and area under the curve. This demonstrates its ability to handle class imbalance effectively while maintaining high diagnostic accuracy. The results highlight the potential of integrating deep learning feature extraction with SVM classifiers to improve classification performance in complex medical imaging tasks. This study underscores the value of combining complementary classification strategies to address the challenges of class imbalance and improve diagnostic workflows.

Analysis of the features of remote control of a marine autonomous surface ship in port waters using conventional navigation technical means

The article analyzes the peculiarities of remote control of a marine autonomous surface ship in port waters using data obtained from conventional navigational technical means. It highlights that for the effective operation of an automated navigation system controlling a marine autonomous surface ship, a monitoring system must be developed. This system's task is to collect data from the technical means of the controlled object in real-time, analyze them, and subsequently determine and forecast the ship's condition (safe or unsafe) with necessary reliability. Based on these results, possible scenario variants are formed to ensure vessel safety, aiding the automated navigation system or external captain in making optimal decisions. Differences between controlling a classical vessel with a crew on the navigation bridge and remotely controlling an autonomous surface vessel by an external captain under port conditions are presented. The accuracy of classical navigation tasks is calculated based on international and national requirements for measuring capabilities of conventional navigational equipment in relation to remote control without detailing individual equipment models' characteristics. A comparison of the obtained calculation results with international and national safety requirements is made, identifying weaknesses in current technologies and providing recommendations for improving navigation data quality to successfully perform ship-to-ship operations in remote control mode within port waters. The importance of developing new technologies for autonomous ship control to overcome existing navigation aids' shortcomings and enhance safety in port conditions is emphasized.

Improving the Accuracy of Groundwater Level Forecasting by Coupling Ensemble Machine Learning Model and Coronavirus Herd Immunity Optimizer

Abstract Groundwater levels are under severe pressure globally due to over-extraction, pollution, and climate change necessitating continuous monitoring for sustainable aquifer management. This study introduces a novel ensemble machine learning (En) model that integrates shallow and deep machine learning (ML) models, optimized through the coronavirus herd immunity optimizer (CHIO), for accurate groundwater level forecasting. This En model was applied to the Ergene River Basin, Türkiye, a region facing severe groundwater depletion and contamination due to intensive agricultural and industrial activities. Groundwater level data spanning 1966 to 2023 on a weekly basis from four wells were used, split into 70% for training and 30% for testing under short- and long-term scenarios. Using the partial autocorrelation function and gamma test the best lag numbers were determined for input data, reflecting aquifer heterogeneity. Score analysis, supported by statistical metrics such as the coefficient of determination (R²) and root mean square error (RMSE), was employed alongside visual aids to assess the developed En model performance. Results demonstrated that deep ML models outperformed shallow ML models achieving R² ~ 0.99 and RMSE ~ 0.5 m. The developed En model outperformed all individual ML models, with score values exceeding 200, and its predictions closely aligned with measured water levels during both testing phases. The findings underscored the developed En model’s contribution to achieving sustainable development goals (SDGs) by enhancing water-use efficiency and addressing environmental, economic, and social sustainability challenges. The proposed approach offers a reliable and adaptable solution for groundwater level forecasting, applicable to other aquifers worldwide. Graphical Abstract

Assessment of the steady-state drug-drug interactions between dolutegravir and ritonavir-boosted darunavir in adolescents.

DTG is primarily metabolized by the UDP-glycosyltransferase (UGT) 1A1, and to a lesser extent by the cytochrome P450 (CYP) 3A4. Co-administration of DRV/r has been reported to decrease DTG plasma concentrations. Our aim was to distinguish the extent of the drug-drug interactions between DRV/r and DTG, and to evaluate the consequences of this interaction, in adolescents at steady state. SMILE (PENTA 17-ANRS152) was a phase II/III trial assessing the safety and efficacy of once-daily dual therapy, using dolutegravir (DTG) combined with ritonavir-boosted darunavir (DRV/r), in virologically suppressed adolescents aged 12 years and older. A joint population pharmacokinetic model for DTG and DRV/r was developed with prior individual drug models (involving unbound and total concentrations) using SMILE data. Unbound DRV exposure, integrated as a power function on unbound DTG clearance best described DRV/r inhibition of DTG elimination. Nevertheless, no interaction was identified between DRV/r and total DTG clearance. Moreover, the influence of unbound DRV exposures to predict unbound DTG concentrations was relatively small. Administration of DRV/r 800/100 mg and DTG 50 mg once daily provides adequate concentrations and exposures with no clinically relevant drug-drug interactions at steady-state.

ViX-MangoEFormer: An Enhanced Vision Transformer–EfficientFormer and Stacking Ensemble Approach for Mango Leaf Disease Recognition with Explainable Artificial Intelligence

Mango productivity suffers greatly from leaf diseases, leading to economic and food security issues. Current visual inspection methods are slow and subjective. Previous Deep-Learning (DL) solutions have shown promise but suffer from imbalanced datasets, modest generalization, and limited interpretability. To address these challenges, this study introduces the ViX‑MangoEFormer, which combines convolutional kernels and self-attention to effectively diagnose multiple mango leaf conditions in both balanced and imbalanced image sets. To benchmark against ViX‑MangoEFormer, we developed a stacking ensemble model (MangoNet-Stack) that utilizes five transfer learning networks as base learners. All models were trained with Grad‑CAM produced pixel‑level explanations. In a combined dataset of 25,530 images, ViX-MangoEFormer achieved an F1 score of 99.78% and a Matthews Correlation Coefficient (MCC) of 99.34%. This performance consistently outperformed individual pre-trained models and MangoNet-Stack. Additionally, data augmentation has improved the performance of every architecture compared to its non-augmented version. Cross‑domain tests on morphologically similar crop leaves confirmed strong generalization. Our findings validate the effectiveness of transformer attention and XAI in mango leaf disease detection. ViX‑MangoEFormer is deployed as a web application that delivers real‑time predictions, probability scores, and visual rationales. The system enables growers to respond quickly and enhances large-scale smart crop health monitoring.

Integrating adipsin with novel cardiometabolic and inflammatory indices for enhanced early prediction of gestational diabetes mellitus: a prospective cohort study

BackgroundEarly identification of individuals at risk for gestational diabetes mellitus (GDM) is essential for mitigating its adverse effects on both maternal and foetal health. This study aimed to evaluate the predictive value of the cardiometabolic index (CMI), systemic inflammation response index (SIRI), and serum adipsin levels for GDM.MethodsA total of 1660 pregnant women were enrolled in this study conducted in Suzhou, China. Baseline clinical data, including blood glucose levels, lipid profiles, and blood cell counts, were collected at 12 weeks of gestation. GDM was diagnosed between 24 and 28 weeks of gestation. Logistic regression and receiver operating characteristic (ROC) curve analyses were performed to assess the associations and predictive performance of CMI, SIRI, and adipsin for GDM.ResultsCompared with non-GDM participants, those with GDM exhibited significantly higher CMI and SIRI values and lower serum adipsin levels at baseline. Increased CMI and SIRI, as well as reduced adipsin levels, were independently associated with a higher risk of GDM in both unadjusted and adjusted models (all P < 0.05). The composite model incorporating all three biomarkers achieved a higher area under the curve (AUC) of 0.918 compared with the individual models for CMI (AUC = 0.825), SIRI (AUC = 0.802), and adipsin (AUC = 0.724).ConclusionsCMI, SIRI, and serum adipsin are independently associated with GDM risk, and their combination provides a promising multi-biomarker strategy for early GDM prediction. Further studies are needed to validate these findings in diverse populations.Graphical

A multi-model approach to estimate excess mortality in the Nordics, 2020-2023.

A multi-model approach to estimate excess mortality in the Nordics, 2020-2023.

EFFICIENT BOTNET DETECTION IN IOT NETWORKS USING A HYBRID MACHINE LEARNING APPROACH

As internet technology advances and becomes more widely used, cyberattacks are becoming more frequent. One of the most damaging assaults was the botnet attack. Because of the many attack channels and the constant development of viruses, botnet detection is getting more difficult. The fast development of Internet of Things (IoT) technology has resulted in botnet assaults targeting several network devices, which have caused significant losses across various industries. Network security is seriously threatened by botnets, and deep learning models have shown the ability to effectively detect botnet activity from network traffic data. This study proposes a botnet detection system based on the stacking of recurrent neural networks (RNN), convolutional neural networks (CNN), artificial neural networks (ANN), and machine learning models (ACLR). Both the individual models and the suggested ACLR model for performance comparison are used in the tests. Nine distinct attack types, including "Normal," "Generic," "Exploits," "Fuzzers," "DoS," "Reconnaissance," "Analysis," "Backdoor," "Shell code," and "Worms," are included in the UNSW-NB15 dataset, which is utilised for botnet assaults. According to experimental data, the suggested ACLR model well captures the complex patterns and features of botnet assaults, achieving a testing accuracy of 0.9698. A K-fold cross-validation accuracy score of 0.9749 for the proposed ACLR model's k values (3, 5, 7, and 10) shows that k = 5 demonstrates the model's generalisability and resilience. Furthermore, the suggested model identifies botnets with a precision-recall area under the curve (PR-AUC) of 0.9950 and a high receiver operating characteristic area under the curve (ROC-AUC) of 0.9934. The higher performance of the suggested method is further supported by a comparison with current state-of-the-art models. The findings of this study may improve cyber security protocols and provide valuable defence against changing threats.

Identifying Lung-related Factors to Improve Discrimination of Validated Atrial Fibrillation Risk Prediction Models in Tobacco-exposed Individuals

Identifying Lung-related Factors to Improve Discrimination of Validated Atrial Fibrillation Risk Prediction Models in Tobacco-exposed Individuals

Which approach better predicts diabetes: Traditional econometric methods or machine learning? Evidence from a cross-sectional study in South Korea.

Which approach better predicts diabetes: Traditional econometric methods or machine learning? Evidence from a cross-sectional study in South Korea.