Synthetic Minority Oversampling Technique Research Articles

Identifying predictors of stroke in young adults: a machine learning analysis of sex-specific risk factors

IntroductionStroke among Americans under age 49 is increasing. While the risk factors for stroke among older adults are well-established, evidence on stroke causes in young adults remains limited. This study used machine learning techniques to explore the predictors of stroke in young men and women.MethodsThe least absolute shrinkage and selection operator algorithm (LASSO) was applied to data from Wave V of the National Longitudinal Survey of Adolescent to Adult Health (N = 12,300)—nationally representative, longitudinal panel containing demographic, lifestyle, and clinical information for individuals aged 33–43—to identify the key factors associated with stroke in men and women. The resulting LASSO model was tested and validated on an independent sample and model performance was assessed using the area under the receiver operating characteristic curve (AUC) and calibration. For robustness, synthetic minority over sampling technique (SMOTE) was applied to address data imbalance and analyses were repeated on the balanced sample.ResultsApproximately 1.1% (N = 59) and 1.3% (N = 90) of the 5,318 and 6,970 men and women in the sample reported having a stroke. LASSO was used to predict stroke using demographic, lifestyle, and clinical predictors on both balanced and imbalanced data sets. LASSO performed slightly better on the balanced data set for women compared to the unbalanced set (Female AUC: 0.835 vs. 0.842), but performance for men was nearly identical (Male AUC: 0.820 vs. 0.822). Predictor identification was similar across both sets. For females, marijuana use, receipt of health services, education, self-rated health status, kidney disease, migraines, diabetes, depression, and PTSD were predictors. Among males, income, kidney disease, heart disease, diabetes, PTSD, and anxiety were risk factors.ConclusionsThis study showed similar clinical risk factors among men and women. However, variations in the behavioral and lifestyle determinants between sexes highlight the need for tailored interventions and public health strategies to address sex-specific stroke risk factors among young adults.

Predictive models for secondary epilepsy in patients with acute ischemic stroke within one year.

Post-stroke epilepsy (PSE) is a critical complication that worsens both prognosis and quality of life in patients with ischemic stroke. An interpretable machine learning model was developed to predict PSE using medical records from four hospitals in Chongqing. Medical records, imaging reports, and laboratory test results from 21,459 ischemic stroke patients were collected and analyzed. Univariable and multivariable statistical analyses identified key predictive factors. The dataset was split into a 70% training set and a 30% testing set. To address the class imbalance, the Synthetic Minority Oversampling Technique combined with Edited Nearest Neighbors was employed. Nine widely used machine learning algorithms were evaluated using relevant prediction metrics, with SHAP (SHapley Additive exPlanations) used to interpret the model and assess the contributions of different features. Regression analyses revealed that complications such as hydrocephalus, cerebral hernia, and deep vein thrombosis, as well as specific brain regions (frontal, parietal, and temporal lobes), significantly contributed to PSE. Factors such as age, gender, NIH Stroke Scale (NIHSS) scores, and laboratory results like WBC count and D-dimer levels were associated with increased PSE risk. Tree-based methods like Random Forest, XGBoost, and LightGBM showed strong predictive performance, achieving an AUC of 0.99. The model accurately predicts PSE risk, with tree-based models demonstrating superior performance. NIHSS score, WBC count, and D-dimer were identified as the most crucial predictors. The research is funded by Central University basic research young teachers and students research ability promotion sub-projec t(2023CDJYGRH-ZD06), and by Emergency Medicine Chongqing Key Laboratory Talent Innovation and development joint fund project (2024RCCX10).

Enhancing Cover Management Factor Classification Through Imbalanced Data Resolution

This study addresses the persistent challenge of class imbalance in land use and land cover (LULC) classification within the Shihmen Reservoir watershed in Taiwan, where LULC is used to map the Cover Management factor (C-factor). The dominance of forests in the LULC categories leads to an imbalanced dataset, resulting in poor prediction performance for minority classes when using machine learning techniques. To overcome this limitation, we applied the Synthetic Minority Over-sampling Technique (SMOTE) and the 90-model SMOTE-variants package in Python to balance the dataset. Due to the multi-class nature of the data and memory constraints, 42 models were successfully used to create a balanced dataset, which was then integrated with a Random Forest algorithm for C-factor classification. The results show a marked improvement in model accuracy across most SMOTE variants, with the Selected Synthetic Minority Over-sampling Technique (Selected_SMOTE) emerging as the best-performing method, achieving an overall accuracy of 0.9524 and a sensitivity of 0.6892. Importantly, the previously observed issue of poor minority class prediction was resolved using the balanced dataset. This study provides a robust solution to the class imbalance issue in C-factor classification, demonstrating the effectiveness of SMOTE variants and the Random Forest algorithm in improving model performance and addressing imbalanced class distributions. The success of Selected_SMOTE underscores the potential of balanced datasets in enhancing machine learning outcomes, particularly in datasets dominated by a majority class. Additionally, by addressing imbalance in LULC classification, this research contributes to Sustainable Development Goal 15, which focuses on the protection, restoration, and sustainable use of terrestrial ecosystems.

Abstract 4136459: Machine Learning in Time-to-Event Prediction of Ventricular Arrhythmias among Older Adults with Type 2 Diabetes and Coronary Artery Disease

Introduction: Patients with Type 2 diabetes mellitus (T2DM) have an increased risk for coronary artery disease (CAD) compared to patients without T2DM. Ventricular arrhythmias (VA), such as ventricular fibrillation and ventricular tachycardia, are the major causes of mortality among patients with CAD. Thus, T2DM patients with CAD, especially older adults, have a higher risk of VA compared to patients without T2DM. The time-to-event prediction can contribute to decreasing mortality due to VA in older adults with T2DM and CAD by providing an estimated time and probability of diagnosis at specific time points. However, the limited number of older T2DM patients with CAD, who are diagnosed with ventricular arrhythmias, lowers the performance of a traditional time-to-event analysis model. Hypothesis: We hypothesize that machine learning can improve performance in time-to-event prediction. Methods: This study includes 3975 participants aged >65 years, diagnosed with T2DM and CAD in the All of US database. The baseline time was the earliest date when the patients were older than 65 years and diagnosed with T2DM and CAD. Of all participants, 379 were diagnosed with VA within 5 years from baseline. We compared the machine learning–based time-to-event analysis models to the Cox Proportional Hazards model to explore the potential of machine learning in time-to-event analysis. Additionally, the Synthetic Minority Oversampling Technique was applied to resolve the imbalanced data issue. The model performance was evaluated based on the concordance index, which calculates the correlation between predicted risk scores and actual observations, after 5-fold cross-validation. Results: The average concordance index of the Gradient Boosting Machines model was the highest among the five models, including the Cox Proportional Hazards model, with balanced data (Table). Conclusion: We identified that machine learning could improve the performance of prediction models in time-to-event analysis. The Synthetic Minority Oversampling Technique could mitigate the issue of imbalanced data. In addition, machine learning-based survival models showed higher concordance index values compared to the Cox Proportional Hazards model.

Abstract 4139194: Predicting Cholesterol Screening Behavior After Age 50 Using Machine Learning: Insights from the Health and Retirement Study

Background: In the U.S., about 8% of adults never received cholesterol screening. Although machine learning (ML) has been used to develop decision tools for Atherosclerotic Cardiovascular Disease (ASCVD) risk prediction, its application in behavioral forecasting has not yet been explored in the context of cholesterol screening behaviors. This study aimed to examine the performance and accuracy of ML algorithms in forecasting cholesterol screening behaviors in adults after age 50. Methods: This analysis used deidentified data from the Health and Retirement Study (HRS) 2004-2018. HRS is a longitudinal survey among 23,000 households in the U.S. Participants were excluded from the current analysis if they passed away by 2019, ever had ASCVD or stroke, were under age 50 at baseline, or had missing data in self-reported cholesterol screening. In total, 7176 participants (mean age [SD]=62 [8]) met the inclusion criteria; participants were randomly split into a training set (80%) and a testing set (20%). The synthetic minority oversampling technique was used to solve the imbalance distribution of the rare event. Five ML algorithms were used: random forest, gradient boosting machine (GBM), XGBoost, Support Vector Machine (SVM), and logistic regression. Accuracy, AUROC, and positive predictive value (PPV) were used to compare model performance. The average gain was evaluated for feature importance in the demographic and health domains. Results: In total, 232 (3.2%) respondents did not receive any cholesterol screening from 2008 to 2018. Experiments with five ML algorithms suggested that XGBoost with deeper trees and learning rate performed better in classifying those who did not screen for cholesterol levels over 10 years. Adding prior cholesterol screening history (2004-2006) into the model significantly improved model performance. Hypertension, self-rated health, and smoking were the major health features, while insurance, poverty, and work status were the major demographic features in the predictive model (accuracy=0.97; AUROC=0.88; PPV=0.42). Conclusion: Findings underscore the potential utility of ML models in predicting cholesterol screening behaviors after age 50. This could be the basis for developing decision tools for clinicians to identify those with a lower chance of cholesterol screening or make reminders accordingly. The low-cost predictive model might improve the uptake of preventive screening behaviors in middle-aged and older adults.

Analysing crash severity on expressways in India using statistical and ML approaches

The high injury severity of traffic crashes on Indian expressways is a significant concern for road safety experts, although studies dedicated to this critical issue are limited. The present study investigates the factors influencing crash severity using multinomial logit (MNL), decision tree (DT) and random forest (RF) models on a dataset of 2,747 crashes on three selected expressways. The dependent variable, crash severity, had four injury severity categories: fatal, severe, minor, and property damage only (PDO). Various explanatory variables, included traffic and speed characteristics, temporal and geometric characteristics, primary contributing factors, crash type, and the vehicles involved. Synthetic minority oversampling (SMOTE) and randomise class balancing (RCB) techniques were also employed to tackle the class imbalance issue in the dataset. The predictive performance of models was evaluated using classification accuracy and Kappa value. The RF model showed the highest predictive accuracy on the RCB dataset. The key findings highlight the critical need for enforcement of speed limits and entry restrictions, lane discipline, and improvement of design deficiencies such as provisions of truck laybys and bus bays. These measures can help in policy-making and engineering improvements to enhance road safety on expressways in India.

KOC_Net: Impact of the Synthetic Minority Over-Sampling Technique with Deep Learning Models for Classification of Knee Osteoarthritis Using Kellgren–Lawrence X-Ray Grade

One of the most common diseases afflicting humans is knee osteoarthritis (KOA). KOA occurs when the knee joint cartilage breaks down, and knee bones start rubbing together. The diagnosis of KOA is a lengthy process, and missed diagnosis can have serious consequences. Therefore, the diagnosis of KOA at an initial stage is crucial which prevents the patients from Severe complications. KOA identification using deep learning (DL) algorithms has gained popularity during the past few years. By applying knee X-ray images and the Kellgren–Lawrence (KL) grading system, the objective of this study was to develop a DL model for detecting KOA. This study proposes a novel model based on CNN called knee osteoarthritis classification network (KOC_Net). The KOC_Net model contains 05 convolutional blocks, and each convolutional block has three components such as Convlotuioanl2D, ReLU, and MaxPooling 2D. The KOC_Net model is evaluated on two publicly available benchmark datasets which consist of X-ray images of KOA based on the KL grading system. Additionally, we applied contrast-limited adaptive histogram equalization (CLAHE) methods to enhance the contrast of the images and utilized SMOTE Tomek to deal with the problem of minority classes. For the diagnosis of KOA, the classification performance of the proposed KOC_Net model is compared with baseline deep networks, namely Dense Net-169, Vgg-19, Xception, and Inception-V3. The proposed KOC_Net was able to classify KOA into 5 distinct groups (including Moderate, Minimal, Severe, Doubtful, and Healthy), with an AUC of 96.71%, accuracy of 96.51%, recall of 91.95%, precision of 90.25%, and F1-Score of 96.70%. Dense Net-169, Vgg-19, Xception, and Inception-V3 have relative accuracy rates of 84.97%, 81.08%, 87.06%, and 83.62%. As demonstrated by the results, the KOC_Net model provides great assistance to orthopedics in making diagnoses of KOA.

Proto-DS: A Self-Supervised Learning-Based Nondestructive Testing Approach for Food Adulteration with Imbalanced Hyperspectral Data

Conventional food fraud detection using hyperspectral imaging (HSI) relies on the discriminative power of machine learning. However, these approaches often assume a balanced class distribution in an ideal laboratory environment, which is impractical in real-world scenarios with diverse label distributions. This results in suboptimal performance when less frequent classes are overshadowed by the majority class during training. Thus, the critical research challenge emerges of how to develop an effective classifier on a small-scale imbalanced dataset without significant bias from the dominant class. In this paper, we propose a novel nondestructive detection approach, which we call the Dice Loss Improved Self-Supervised Learning-Based Prototypical Network (Proto-DS), designed to address this imbalanced learning challenge. The proposed amalgamation mitigates the label bias on the most frequent class, further improving robustness. We validate our proposed method on three collected hyperspectral food image datasets with varying degrees of data imbalance: Citri Reticulatae Pericarpium (Chenpi), Chinese herbs, and coffee beans. Comparisons with state-of-the-art imbalanced learning techniques, including the Synthetic Minority Oversampling Technique (SMOTE) and class-importance reweighting, reveal our method’s superiority. Notably, our experiments demonstrate that Proto-DS consistently outperforms conventional approaches, achieving the best average balanced accuracy of 88.18% across various training sample sizes, whereas the Logistic Model Tree (LMT), Multi-Layer Perceptron (MLP), and Convolutional Neural Network (CNN) approaches attain only 59.42%, 60.38%, and 66.34%, respectively. Overall, self-supervised learning is key to improving imbalanced learning performance and outperforms related approaches, while both prototypical networks and the Dice loss can further enhance classification performance. Intriguingly, self-supervised learning can provide complementary information to existing imbalanced learning approaches. Combining these approaches may serve as a potential solution for building effective models with limited training data.

Leveraging Mixture of Experts and Deep Learning-Based Data Rebalancing to Improve Credit Fraud Detection

Credit card fraud detection is a critical challenge in the financial sector due to the rapidly evolving tactics of fraudsters and the significant class imbalance betweenegitimate and fraudulent transactions. Traditional models, while effective to some extent, often suffer from high false positive rates and fail to generalize well to emerging fraud patterns. In this paper, we propose a novel approach that integrates a Mixture of Experts (MoE) model with a Deep Neural Network-based Synthetic Minority Over-sampling Technique (DNN-SMOTE) to enhance fraud detection performance. The MoE modeleverages multiple specialized expert networks, each trained to detect specific types of fraud, while the DNN-SMOTE generates high-quality synthetic samples to address the class imbalance. Our experimental results on a publicly available dataset demonstrate that the proposed method achieves a classification accuracy of 99.93%, a true positive rate of 84.69%, and a true negative rate of 99.95%. The Matthews Correlation Coefficient (MCC) of 0.7883 further highlights the model’s balanced performance in detecting fraudulent transactions. These results underscore the effectiveness of combining MoE with DNN-SMOTE, offering a robust solution for real-world credit card fraud detection scenarios.

Machine Learning Framework for Conotoxin Class and Molecular Target Prediction

Conotoxins are small and highly potent neurotoxic peptides derived from the venom of marine cone snails which have captured the interest of the scientific community due to their pharmacological potential. These toxins display significant sequence and structure diversity, which results in a wide range of specificities for several different ion channels and receptors. Despite the recognized importance of these compounds, our ability to determine their binding targets and toxicities remains a significant challenge. Predicting the target receptors of conotoxins, based solely on their amino acid sequence, remains a challenge due to the intricate relationships between structure, function, target specificity, and the significant conformational heterogeneity observed in conotoxins with the same primary sequence. We have previously demonstrated that the inclusion of post-translational modifications, collisional cross sections values, and other structural features, when added to the standard primary sequence features, improves the prediction accuracy of conotoxins against non-toxic and other toxic peptides across varied datasets and several different commonly used machine learning classifiers. Here, we present the effects of these features on conotoxin class and molecular target predictions, in particular, predicting conotoxins that bind to nicotinic acetylcholine receptors (nAChRs). We also demonstrate the use of the Synthetic Minority Oversampling Technique (SMOTE)-Tomek in balancing the datasets while simultaneously making the different classes more distinct by reducing the number of ambiguous samples which nearly overlap between the classes. In predicting the alpha, mu, and omega conotoxin classes, the SMOTE-Tomek PCA PLR model, using the combination of the SS and P feature sets establishes the best performance with an overall accuracy (OA) of 95.95%, with an average accuracy (AA) of 93.04%, and an f1 score of 0.959. Using this model, we obtained sensitivities of 98.98%, 89.66%, and 90.48% when predicting alpha, mu, and omega conotoxin classes, respectively. Similarly, in predicting conotoxins that bind to nAChRs, the SMOTE-Tomek PCA SVM model, which used the collisional cross sections (CCSs) and the P feature sets, demonstrated the highest performance with 91.3% OA, 91.32% AA, and an f1 score of 0.9131. The sensitivity when predicting conotoxins that bind to nAChRs is 91.46% with a 91.18% sensitivity when predicting conotoxins that do not bind to nAChRs.

Analysis of ensemble machine learning classification comparison on the skin cancer MNIST dataset

This study aims to analyze the performance of various ensemble machine learning methods, such as Adaboost, Bagging, and Stacking, in the context of skin cancer classification using the skin cancer MNIST dataset. We also evaluate the impact of handling dataset imbalance on the classification model’s performance by applying imbalanced data methods such as random under sampling (RUS), random over sampling (ROS), synthetic minority over-sampling technique (SMOTE), and synthetic minority over-sampling technique with edited nearest neighbor (SMOTEENN). The research findings indicate that Adaboost is effective in addressing data imbalance, while imbalanced data methods can significantly improve accuracy. However, the selection of imbalanced data methods should be carefully tailored to the dataset characteristics and clinical objectives. In conclusion, addressing data imbalance can enhance skin cancer classification accuracy, with Adaboost being an exception that shows a decrease in accuracy after applying imbalanced data methods.

Development and validation of a cross-modality tensor fusion model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion in hepatocellular carcinoma

ObjectivesTo develop and validate a cross-modality tensor fusion (CMTF) model using multi-modality MRI radiomics features and clinical radiological characteristics for the prediction of microvascular invasion (MVI) in hepatocellular carcinoma (HCC). Materials and methodsThis study included 174 HCC patients (47 MVI-positive and 127 MVI-negative) confirmed by postoperative pathology. The synthetic minority over-sampling technique was used to augment MVI-positive samples. The amplified dataset of 254 samples (127 MVI-positive and 127 MVI-negative) was randomly divided into training and test cohorts in a 7:3 ratio. Radiomics features were respectively extracted from arterial phase, delayed phase, diffusion-weighted imaging, and fat-suppressed T2-weighted imaging. The least absolute shrinkage and selection operator was used for feature selection. Univariate and multivariate logistic regression analyses were employed to identify clinical and radiological independent predictors. The selected multi-modality MRI radiomics features, clinical and radiological characteristics were used to construct the CMTF model, single modality (SM) model, early fusion (EF) model. ResultsThe CMTF model demonstrated superior performance in predicting MVI compared to the SM and EF models. When integrating four MRI modalities, the CMTF model achieved a high area under the curve (AUC) with 95% confidence interval (95% CI) of 0.894 (0.820-0.968). Additionally, incorporating clinical and radiological characteristics further enhanced the predictive performance of CMTF model, the AUC (95% CI) value increased to 0.945 (0.892-0.998). ConclusionThe CMTF model showed promising performance in preoperative MVI prediction, providing a more effective non-invasive detection tool for HCC patients.

Predicting the productivity of fractured horizontal wells using few-shot learning

Predicting the productivity of multistage fractured horizontal wells plays an important role in exploiting unconventional resources. In recent years, machine learning (ML) models have emerged as a new approach for such studies. However, the scarcity of sufficient real data for model training often leads to imprecise predictions, even though the models trained with real data better characterize geological and engineering features. To tackle this issue, we propose an ML model that can obtain reliable results even with a small amount of data samples. Our model integrates the synthetic minority oversampling technique (SMOTE) to expand the data volume, the support vector machine (SVM) for model training, and the particle swarm optimization (PSO) algorithm for optimizing hyperparameters. To enhance the model performance, we conduct feature fusion and dimensionality reduction. Additionally, we examine the influences of different sample sizes and ML models for training. The proposed model demonstrates higher prediction accuracy and generalization ability, achieving a predicted R2 value of up to 0.9 for the test set, compared to the traditional ML techniques with an R2 of 0.13. This model accurately predicts the production of fractured horizontal wells even with limited samples, supplying an efficient tool for optimizing the production of unconventional resources. Importantly, the model holds the potential applicability to address similar challenges in other fields constrained by scarce data samples.

Regressive Machine Learning for Real-Time Monitoring of Bed-Based Patients

This study introduces an ensemble model designed for real-time monitoring of bedridden patients. The model was developed using a unique dataset, specifically acquired for this study, that captures six typical movements. The dataset was balanced using the Synthetic Minority Over-sampling Technique, resulting in a diverse distribution of movement types. Three models were evaluated: a Decision Tree Regressor, a Gradient Boosting Regressor, and a Bagging Regressor. The Decision Tree Regressor achieved an accuracy of 0.892 and an R2 score of 1.0 on the training dataset, and 0.939 on the test dataset. The Boosting Regressor achieved an accuracy of 0.908 and an R2 score of 0.99 on the training dataset, and 0.943 on the test dataset. The Bagging Regressor was selected due to its superior performance and trade-offs such as computational cost and scalability. It achieved an accuracy of 0.950, an R2 score of 0.996 for the training data, and an R2 score of 0.959 for the test data. This study also employs K-Fold cross-validation and learning curves to validate the robustness of the Bagging Regressor model. The proposed system addresses practical implementation challenges in real-time monitoring, such as data latency and false positives/negatives, and is designed for seamless integration with hospital IT infrastructure. This research demonstrates the potential of machine learning to enhance patient safety in healthcare settings.

Enhancing SMOTE for imbalanced data with abnormal minority instances

Imbalanced datasets are frequent in machine learning, where certain classes are markedly underrepresented compared to others. This imbalance often results in sub-optimal model performance, as classifiers tend to favour the majority class. A significant challenge arises when abnormal instances, such as outliers, exist within the minority class, diminishing the effectiveness of traditional re-sampling methods like the Synthetic Minority Over-sampling Technique (SMOTE). This manuscript addresses this critical issue by introducing four SMOTE extensions: Distance ExtSMOTE, Dirichlet ExtSMOTE, FCRP SMOTE, and BGMM SMOTE. These methods leverage a weighted average of neighbouring instances to enhance the quality of synthetic samples and mitigate the impact of outliers. Comprehensive experiments conducted on diverse simulated and real-world imbalanced datasets demonstrate that the proposed methods improve classification performance compared to the original SMOTE and its most competitive variants. Notably, we demonstrate that Dirichlet ExtSMOTE outperforms most other proposed and existing SMOTE variants in terms of achieving better F1 score, MCC, and PR-AUC. Our results underscore the effectiveness of these advanced SMOTE extensions in tackling class imbalance, particularly in the presence of abnormal instances, offering robust solutions for real-world applications.

Public Sentiment Analysis About Neuralink from Twitter Using Naïve Bayes: Multinomial, Gaussian and Complement

Elon Musk owns the business Neuralink, which attempts to build brain-machine interfaces. This study categorizes public opinion towards the use of Neuralink goods, including whether people agree (positive), disagree (negative), or feel neither way. Without accessing the Twitter API, the Twint Python Libraries were utilised to retrieve a dataset of 3000 using the keyword “neuralink”. What datasets are included in positive, neutral, or negative categories are designated using RoBERTa. Term Frequency Inverse Document Frequency (TF-IDF) is utilized for feature extraction, while Synthetic Minority Over-sampling Technique (SMOTE) is employed to handle class imbalance. Complement Naive Bayes, achieved accuracy of 81%, followed by Multinomial Naive Bayes, which achieved accuracy of 80%, and Gaussian Naive Bayes, which achieved accuracy of 75%. The model Complement Naïve Bayes was used in this study to attain the maximum accuracy, and accuracy increases when employing SMOTE compared to other Naïve bayes variants.

Predicting Online Gaming Behavior: A Comparative Analysis of Random Forest and Gaussian Naive Bayes Models

With the rising impact and economic benefits of the online gaming industry, online gaming companies need to understand players’ behavior to evaluate their products better and adjust their developing strategy. This paper uses machine learning models to predict players’ online gaming behaviors. The study utilizes the dataset from Kaggle, which contains 40,034 samples with 13 features related to player demographics, game preferences, and gameplay behaviors. The primary objective is to classify two target variables: ‘EngagementLevel’ and ‘InGamePurchases.’ Data preprocessing steps included handling missing values, encoding categorical features, normalizing numerical data, and addressing class imbalances using the Synthetic Minority Over-sampling Technique (SMOTE). The Random Forests (RF) and Gaussian Naïve Bayes (GNB) models were employed to predict the target variables. The RF model significantly outperformed the GNB model in both classification tasks, especially when predicting the in-game purchases. The RF model’s robustness is attributed to its ability to handle complex, non-linear relationships and interactions between features, while the GNB model’s performance was limited by its assumptions of feature independence and normally distributed data. The findings suggest that RF is a more effective tool for predicting online gaming behaviors, particularly in scenarios with complex feature interactions. Future research could incorporate additional machine learning models and more diverse datasets to further enhance predictive accuracy and offer a more comprehensive understanding of online gaming behaviors.

Leveraging Explainable Artificial Intelligence (XAI) for Expert Interpretability in Predicting Rapid Kidney Enlargement Risks in Autosomal Dominant Polycystic Kidney Disease (ADPKD)

Autosomal dominant polycystic kidney disease (ADPKD) is the predominant hereditary factor leading to end-stage renal disease (ESRD) worldwide, affecting individuals across all races with a prevalence of 1 in 400 to 1 in 1000. The disease presents significant challenges in management, particularly with limited options for slowing cyst progression, as well as the use of tolvaptan being restricted to high-risk patients due to potential liver injury. However, determining high-risk status typically requires magnetic resonance imaging (MRI) to calculate total kidney volume (TKV), a time-consuming process demanding specialized expertise. Motivated by these challenges, this study proposes alternative methods for high-risk categorization that do not rely on TKV data. Utilizing historical patient data, we aim to predict rapid kidney enlargement in ADPKD patients to support clinical decision-making. We applied seven machine learning algorithms—Random Forest, Logistic Regression, Support Vector Machine (SVM), Light Gradient Boosting Machine (LightGBM), Gradient Boosting Tree, XGBoost, and Deep Neural Network (DNN)—to data from the Polycystic Kidney Disease Outcomes Consortium (PKDOC) database. The XGBoost model, combined with the Synthetic Minority Oversampling Technique (SMOTE), yielded the best performance. We also leveraged explainable artificial intelligence (XAI) techniques, specifically Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP), to visualize and clarify the model’s predictions. Furthermore, we generated text summaries to enhance interpretability. To evaluate the effectiveness of our approach, we proposed new metrics to assess explainability and conducted a survey with 27 doctors to compare models with and without XAI techniques. The results indicated that incorporating XAI and textual summaries significantly improved expert explainability and increased confidence in the model’s ability to support treatment decisions for ADPKD patients.

Deep learning-based high-frequency jump test for detecting stock market manipulation: evidence from China’s securities market

PurposeThis study aims to tackle the critical issue of detecting stock market manipulation, which undermines the integrity and stability of financial markets globally. Even enhanced with machine learning, traditional statistical methods often struggle to analyze high-frequency trading data effectively due to inherent noise and the limited availability of publicly known manipulation cases. This leads to poor model generalization and a tendency toward over-fitting. Focusing on China's securities market, our study introduces an innovative approach that employs deep learning-based high-frequency jump tests to overcome these challenges and to develop a more effective method for identifying manipulative activities.Design/methodology/approachWe employed the “Jump Variation – Time-of-Day” (JV-TOD) non-parametric technique for jump tests on high-frequency data, coupled with the synthetic minority over-sampling technique (SMOTE) algorithm for re-balancing sample data. Our approach trains a deep neural network (DNN) on refined data to enhance its ability to identify manipulation patterns accurately.FindingsOur results show that the deep neural network model, calibrated with high-frequency price jump data, identifies manipulation behavior more specifically and accurately than traditional models. The model achieved an accuracy rate of 94.64%, an F1-score of 95.26% and a recall rate of 95.88%, significantly outperforming traditional models. These results demonstrate the effectiveness of our approach in mitigating over-fitting and improving the robustness of market manipulation detection.Practical implicationsThe proposed model provides regulatory entities and financial institutions with a more efficient tool to monitor and counteract market manipulation, thereby improving market fairness and investor protection.Originality/valueBy integrating the JV-TOD jump test with deep learning, this study proposed a new approach to market manipulation detection. The innovation is in its capacity to detect subtle manipulation signals that traditional methods typically overlook. Our model, which is trained on jump test data enhanced by the SMOTE algorithm, excels at learning complex manipulation patterns. This enhances both detection accuracy and robustness. In contrast to existing methods that are challenged by the noisy and intricate nature of high-frequency data, our approach shows enhanced performance in identifying nuanced market manipulations, offering a more effective and reliable method for detecting market manipulation.

Ppulsed field ablation and ultra-high-density mapping for PVI: use of machine learning and data augmentation to guide procedure and identify recurrent tachycardia mechanisms at one-year follow-up

Abstract Background In managing atrial fibrillation (AF), radiofrequency and cryoablation have been cornerstone techniques for achieving pulmonary vein isolation (PVI). Recently, pulsed-field ablation (PFA) has introduced a novel method for PVI. There remains a gap in knowledge regarding the permanent efficacy of ablation, related explicitly to acute lesion characteristics following PVI. Purpose Our study delves into an in-depth examination of acute lesion characteristics following PFA-PVI through ultra-high-density mapping (UHDM). We aim to identify specific clinical, anatomical, and periprocedural lesion features independently related to 1) intraoperative identification of UHDM non-isolated gaps with electrical conduction after first isolation and 2) three months follow-up recurrency of specific arrhythmias. Methods Results The present study includes 204 patients submitted to PFA-PVI for AF. UHDM guided all procedures to identify non-isolated gaps with electrical conduction. Perioperative and 3-month follow-up data were collected prospectively and analyzed. To build our prediction model, avoiding biases related to the unbalanced nature of the data, data augmentation was performed with SMOTE (Synthetic Minority Over-sampling Technique). Two machine learning (ML) models have been built, using logistic regression as learner, to predict the presence of isolation gaps identified by UHDM and follow-up recurrence of arrhythmias. A 20-fold cross-validation has been performed to train and test the models. The non-isolated gap was detected and immediately corrected in 14 (6.9%) patients and was present more often in patients with larger left atria (LA) (p<0.0001) and those with persistent AF (p=0.02). The ML model achieved an AUC of 0.88 in the prediction of the non-isolated gap after PFA (Precision: 0.65; Sens.: 0.90; F1: 0.76; Spec.: 0.83; NPV: 0.96). At three months follow-up, no patient experienced recurrent AF; recurrent roof-dependent atrial tachycardia was present in 10 (4.9%). Patients with recurrent atrial tachycardia had a significantly narrower remaining atrial-roof conduction bridge (p=0.01) identified intra-procedurally by UHDM, significantly larger LA (p=0.03), and non-significant trend for older age (p=0.07). The ML model achieved an AUC of 0.86, predicting recurrent tachycardia after PFA (Precision: 0.63; Sens.: 0.86; F1: 0.72; Spec.: 0.82; NPV: 0.94). Conclusions Consistent use of UHDM can help identify non-isolated gaps with electrical conduction that may occur even after PVI with updated technologies, such as PFA. Non-isolated gaps should be expected, particularly in patients with larger LA, where UHDM could be of particular use. Moreover, UHDM can help predict the eventual recurrence of arrhythmias. Again, LA size plays an essential role in such recurrencies, together with the size of the remaining conducting tissue "bridges" within the LA roof, measure by UHDM.