Synthetic Minority Oversampling Technique Research Articles

Smartphone-Based Pupillometry Using Machine Learning for the Diagnosis of Sports-Related Concussion

Background: Quantitative pupillometry has been proposed as an objective means to diagnose acute sports-related concussion (SRC). Objective: To assess the diagnostic accuracy of a smartphone-based quantitative pupillometer in the acute diagnosis of SRC. Methods: Division I college football players had baseline pupillometry including pupillary light reflex (PLR) parameters of maximum resting diameter, minimum diameter after light stimulus, percent change in pupil diameter, latency of pupil constriction onset, mean constriction velocity, maximum constriction velocity, and mean dilation velocity using a smartphone-based app. When an SRC occurred, athletes had the smartphone pupillometry repeated as part of their concussion testing. All combinations of the seven PLR parameters were tested in machine learning binary classification models to determine the optimal combination for differentiating between non-concussed and concussed athletes. Results: 93 football athletes underwent baseline pupillometry testing. Among these athletes, 11 suffered future SRC and had pupillometry recordings repeated at the time of diagnosis. In the machine learning pupillometry analysis that used the synthetic minority oversampling technique to account for the significant class imbalance in our dataset, the best-performing model was a random forest algorithm with the combination of latency, maximum diameter, minimum diameter, mean constriction velocity, and maximum constriction velocity PLR parameters as feature inputs. This model produced 91% overall accuracy, 98% sensitivity, 84.2% specificity, area under the curve (AUC) of 0.91, and an F1 score of 91.6% in differentiating between baseline and SRC recordings. In the machine learning analysis prior to oversampling of our imbalanced dataset, the best-performing model was k-nearest neighbors using latency, maximum diameter, maximum constriction velocity, and mean dilation velocity to produce 82% accuracy, 40% sensitivity, 87% specificity, AUC of 0.64, and F1 score of 24%. Conclusions: Smartphone pupillometry in combination with machine learning may provide fast and objective SRC diagnosis in football athletes.

Predicting Financial Distress in Indonesian Companies using Machine Learning

Predicting financial distress is essential in Indonesia's rapidly evolving economy, characterized by diverse business environments and regulatory challenges. This study evaluates four machine learning classifiers, XGBoost, Random Forest (RF), Support Vector Classification (SVC), and Long Short-Term Memory (LSTM), to predict financial distress among Indonesian companies. Two sampling methods, Random Under-Sampling (RUS) and Synthetic Minority Over-Sampling Technique (SMOTE), were used to address class imbalance. Empirical results indicate that the RF model trained with SMOTE sampling was the most effective, achieving an F1 score of 0.9632 and an accuracy of 0.96, while the XGBoost classifier with RUS sampling achieved a precision of 0.9716. These findings provide valuable insights into Indonesia's financial sector, guiding the selection of appropriate models for timely financial distress prediction and intervention.

Journal homepage: http://ijai.iaescore.com Detecting fraudulent financial statement under imbalanced data using neural network

In this paper a novel approach for detecting fraudulent financial statements by employing a combination of neural networks and synthetic minority over sampling technique (SMOTE) is introduced. This approach is designed to tackle the problem of imbalanced datasets prevalent in fraudulent cases, which if left unaddressed will hinder the model to accurately identify fraud. Three neural network models, each representing different fraud predictors as the input layer: 28 inputs raw financial data; 14 inputs financial ratios data; and 42 inputs combination both raw financial and financial ratios data are developed. Experimental validation using established research datasets is conducted to assess the performance of the proposed method. Performance metrics, namely area under the curve (AUC), precision, and sensitivity, are used for evaluation, comparing the proposed model against existing benchmark models found in literature. Results indicate that the proposed model achieves an AUC score of 70.6% and a precision score of 2.89%, in comparable to the existing models, with a sensitivity score of 83% outperforming all counterparts. The high sensitivity rate of the proposed model underscores its practical utility for auditors and regulators, as it minimizes the risk of false negatives, thereby enhancing confidence in fraud detection.

Comprehensive Performance Evaluation of Machine Learning Algorithms for detecting DDoS attacks in SDN

<div align="center">Software-Defined Networking (SDN) revolutionizes networking by separating control logic and data forwarding, enhancing security against threats like Distributed Denial of Service (DDoS) attacks. These attacks flood control plane bandwidth, causing SDN network failures. Recent studies emphasize the efficacy of machine learning and statistical approaches in identifying and mitigating these security risks. However, there has been a lack of focus on employing ensembling techniques, amalgamating diverse machine learning models, selecting pertinent features, and utilizing oversampling techniques to balance categorical data. Our study evaluates 20 machine-learning models, emphasizing feature engineering and addressing class imbalance using Synthetic Minority Oversampling TEchnique (SMOTE). The results indicate that Ensemble methods such as LGBM Classifier, Random Forest Classifier, XGB Classifier, Decision Tree Classifier attained near-perfect scores (almost 100%) across all metrics, suggesting potential overfitting. Conversely, models like AdaBoost Classifier, K-Neighbors Classifier, and SVC exhibited slightly lower (99%) but realistic performance, underscoring the intricacy of accurate prediction in cybersecurity. Simpler models, including Logistic Regression, Linear Discriminant Analysis, and Gaussian Naive Bayes, demonstrated moderate to low accuracy, approximately around 70%. These findings stress the imperative need for a nuanced approach in the selection and fine-tuning of machine learning models to ensure effective DDoS detection in SDN environments.</div>

Revolutionizing Fault Detection in Self-Healing Network via Multi-Serial Cascaded and Adaptive Network

Self-Healing Network (SHN) plays a crucial role in the realm of digital networking and the telecommunications industry. Fault detection in SHN is a critical aspect of network management and maintenance, which acts as a pivotal role in maintaining network health and minimizing disruptions. The SHN networks aim to manage faults and system failures by automating the detection process and pinpointing their origins. This proactive approach is essential to maintain network integrity and ensure a seamless user experience. In this paper, a novel multi-Serial cascaded and Adaptive Network based fault Detection in SHN (SAND-SHN) technique has been proposed for detecting faults in the SHN network. The proposed method uses the Eigen-Entropy Synthetic Minority Oversampling Technique (EE-SMOTE) to balance imbalanced data for classification and the Multi-Serial Cascaded and Adaptive Network (MSCAN), which integrates deep learning (DL) techniques to attain the final classified outcome. The proposed SAND-SHN method has been evaluated using a Python environment in terms of specific parameters such as accuracy, precision, recall, specificity, and F1-Score. The proposed technique has been evaluated using two datasets as EFCD dataset, and the SFDD dataset. The proposed SAND-SHN technique achieves a higher accuracy of 74% for RSO-MSCAN, 39.2% for DMO-MSCAN, 48.8% for BFGO-MSCAN, and 43.6% for FHO-MSCAN respectively.

User Interface Bug Classification Model Using ML and NLP Techniques: A Comparative Performance Analysis of ML Models

Analyzing user interface (UI) bugs is an important step taken by testers and developers to assess the usability of the software product. UI bug classification helps in understanding the nature and cause of software failures. Manually classifying thousands of bugs is an inefficient and tedious job for both testers and developers. Objective of this research is to develop a classification model for the User Interface (UI) related bugs using supervised Machine Learning (ML) algorithms and Natural Language Processing (NLP) techniques. Also, to assess the effect of different sampling and feature vectorization techniques on the performance of ML algorithms. Classification is based upon ‘Summary’ feature of the bug report and utilizes six classifiers i.e., Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), Logistic Regression (LR), Support Vector Machines (SVM), Random Forest (RF) and Gradient Boosting (GB). Dataset obtained is vectored using two vectorization techniques of NLP i.e., Bag of Words (BoW) and Term Frequency-Inverse Document Frequency (TF-IDF). ML models are trained after vectorization and data balancing. The models ' hyperparameter tuning (HT) has also been done using the grid search approach to improve their efficacy. This work provides a comparative performance analysis of ML techniques using Accuracy, Precision, Recall and F1 Score. Performance results showed that a UI bug classification model can be built by training a tuned SVM classifier using TF-IDF and SMOTE (Synthetic Minority Oversampling Techniques). SVM classifier provided the highest performance measure with Accuracy: 0.88, Precision: 0.86, Recall: 0.85 and F1: 0.85. Result also inferred that the performance of ML algorithms with TF-IDF is better than BoW in most cases. This work provides classification of bugs that are related to only the user interface. Also, the effect of two different feature extraction techniques and sampling techniques on algorithms were analyzed, adding novelty to the research work.

Prognostic prediction for HER2-low breast cancer patients using a novel machine learning model

BackgroundsTo develop a machine learning (ML) model for predicting the prognosis of breast cancer (BC) patients with low human epidermal growth factor receptor 2 (HER2) expression, and to investigate the association between clinicopathological characteristics and outcomes in HER2-low BC (HLBC) patients.MethodsA retrospective analysis was conducted on data from 998 female HLBC patients treated at the Breast Center of the Fourth Hospital of Hebei Medical University (Hebei, China) between January 1, 2017, and December 31, 2020. To address class imbalance, the synthetic minority over-sampling technique was applied. Feature selection was performed using the least absolute shrinkage and selection operator, followed by construction of the prediction model using the random forest algorithm. Model performance, including specificity and accuracy, was assessed using the receiver operating characteristic (ROC) curve and confusion matrix, comparing it against other ML models. Additionally, the log-rank test was employed to examine the relationship between selected features and patient outcomes in HLBC.ResultsThe random survival forest model demonstrated superior accuracy and specificity in predicting survival outcomes for HLBC patients. Compared with other ML models, it achieved more precise predictions of Disease-Free Survival (DFS) at 1, 2, and 3 years, with the area under the ROC curve (AUC) in the test and training cohorts measured at 0.726 and 0.819, 0.712 and 0.776, and 0.685 and 0.774, respectively. The analysis further identified a strong correlation between poor prognosis in HLBC patients and factors such as axillary lymph node dissection, family history, elevated topoisomerase (TOPO)-2 expression, advanced clinical stage, negative progesterone receptor status, P53 mutation, and increased Ki67 expression, observed across both cohorts.ConclusionsA novel ML model was developed for accurate prognosis prediction in HLBC patients, offering valuable insights into prognostic risk factors. This model equips clinicians with enhanced data to guide treatment decisions, ultimately contributing to improved patient outcomes.

Advanced Anemia Classification Using Comprehensive Hematological Profiles and Explainable Machine Learning Approaches

Anemia is a common health issue with serious clinical effects, making timely and accurate diagnosis essential to prevent complications. This study explores the use of machine learning (ML) methods to classify anemia and its subtypes using detailed hematological data. Six ML models were tested: Gradient Boosting, Random Forest, Naive Bayes, Logistic Regression, Support Vector Machine, and K-Nearest Neighbors. The dataset was preprocessed using feature standardization and the Synthetic Minority Oversampling Technique (SMOTE) to address class imbalance. Gradient Boosting delivered the highest accuracy, sensitivity, and F1-score, establishing itself as the top-performing model. SHapley Additive exPlanations (SHAP) analysis was applied to enhance model interpretability, identifying key predictive features. This study highlights the potential of explainable ML to develop efficient, accurate, and scalable tools for anemia diagnosis, fostering improved healthcare outcomes globally.

CL-SR: Boosting Imbalanced Image Classification with Contrastive Learning and Synthetic Minority Oversampling Technique Based on Rough Set Theory Integration

Image recognition models often struggle with class imbalance, which can impede their performance. To overcome this issue, researchers have extensively used resampling methods, traditionally focused on tabular datasets. In contrast to the original method, which generates data at the data level, this paper introduces a novel strategy that combines contrastive learning with the Synthetic Minority Oversampling Technique based on Rough Set Theory (SMOTE-RSB) specifically tailored for imbalanced image datasets. Our method leverages contrastive learning to refine representation learning and balance features, thus effectively mitigating the challenges of imbalanced image classification. We begin by extracting features using a pre-trained contrastive learning encoder. Subsequently, SMOTE-RSB is applied to these features to augment underrepresented classes and reduce irrelevant features. We evaluated our approach on several modified benchmark datasets, including CIFAR-10, SVHN, and ImageNet-LT, achieving notable improvements: an F1 score of 72.43% and a Gmean of 82.53% on the CIFAR-10 long-tailed dataset, F1 scores up to 79.57% and Gmean of 88.20% on various SVHN datasets, and a Top-1 accuracy of 68.67% on ImageNet-LT. Both qualitative and quantitative results confirm the effectiveness of our method in managing imbalances in image datasets. Additional ablation studies exploring various contrastive learning models and oversampling techniques highlight the flexibility and efficiency of our approach across different settings, underscoring its significant potential for enhancing imbalanced image classification.

Prediction of Vancomycin-Associated Nephrotoxicity Based on the Area under the Concentration-Time Curve of Vancomycin: A Machine Learning Analysis.

Several machine learning models have been proposed to predict vancomycin (VCM)-associated nephrotoxicity; however, they have notable limitations. Specifically, they do not use the area under the concentration-time curve (AUC) as recommended in the latest guidelines and do not address imbalanced data. Thus, we aimed to develop a novel model for predicting VCM-associated nephrotoxicity while overcoming these limitations. We retrospectively analyzed the medical records of patients who received VCM intravenously at our hospital from August 2017 to July 2021. We developed machine learning models for predicting VCM-associated nephrotoxicity based on the AUC of VCM and other patient background factors by using the following machine learning algorithms: lasso regression, support vector machine, complement naïve Bayes classifier, decision tree, random forest, and AdaBoost. We utilized the synthetic minority oversampling technique (SMOTE) and class weighting technique for dealing with imbalanced data and compared the performance of our developed machine learning models with that of a conventional model (AUC-guided therapeutic drug monitoring (TDM); AUC at steady state ≤600 µg·h/mL). Data from 270 patients were analyzed. The random forest with SMOTE was the best-performing model, achieving an F1 score of 0.353 and a sensitivity of 0.632 on the test data, compared with the conventional model, with an F1 score of 0.286 and a sensitivity of 0.316. We developed the first machine learning model for predicting VCM-associated nephrotoxicity based on the AUC of VCM, reducing the number of overlooked cases of nephrotoxicity compared with AUC-guided TDM, which may benefit patients overlooked by AUC-guided TDM.

Detecting Soil Tillage in Portugal: Challenges and Insights from Rules-Based and Machine Learning Approaches Using Sentinel-1 and Sentinel-2 Data

Monitoring soil tillage activities, such as plowing and cultivating, is essential for aligning agricultural practices with environmental standards for soil health. Detecting these activities presents significant challenges, especially when relying on remotely sensed data. This paper addresses these challenges within the framework of the Common Agricultural Policy (CAP), which requires EU countries to enhance their environmental monitoring and climate action efforts. We used remote sensing data from Sentinel-1 and Sentinel-2 missions to detect soil tillage practices in 73 test farms in Portugal. Three approaches were explored: a rule-based method and two machine learning techniques based on XGBoost (XGB). One machine learning approach utilized the original imbalanced dataset, while the other employed a SMOTE (Synthetic Minority Oversampling Technique) approach to balance underrepresented soil tillage operations within the training set. Our findings highlight the inherent difficulty in detecting soil tillage operations across all methods, though the XGB-SMOTE approach demonstrated the most promising results, achieving a recall of 67% and an AUC-ROC (area under the receiver operating characteristic curve) of 74%. These results underscore the need for further research to develop a fully automated detection model. This work has potential applications for monitoring compliance with CAP mandates and informing environmental policy to better support sustainable agricultural practices.

Construction of a risk prediction model for postoperative deep vein thrombosis in colorectal cancer patients based on machine learning algorithms

BackgroundColorectal cancer is a prevalent malignancy of the digestive system, with an increasing incidence. Lower extremity deep vein thrombosis (DVT) is a frequent postoperative complication, occurring in up to 40% of cases.ObjectiveThis research aims to develop and validate a machine learning model (ML) to predict the risk of lower limb deep vein thrombosis in patients with colorectal cancer, facilitating preventive and therapeutic measures to enhance recovery and ensure safety.MethodsIn this retrospective cohort study, we collected data from 429 colorectal cancer patients from January 2021 to January 2024. The medical records included age, blood test results, body mass index, underlying diseases, clinical staging, histological typing, surgical methods, and postoperative complications. We employed the Synthetic Minority Oversampling Technique to address imbalanced data and split the dataset into training and validation sets in a 7:3 ratio. Feature selection was performed using Random Forest (RF), XGBoost, and Least Absolute Shrinkage and Selection Operator algorithms (LASSO). We then trained six machine learning models: Logistic Regression (LR), Naive Bayes (NB), Gaussian Process (GP), Random Forest, XGBoost, and Multilayer Perceptron (MLP). The model’s performance was evaluated using metrics such as area under the Receiver Operating Characteristic curve, accuracy, sensitivity, specificity, F1 score, and confusion matrix. Additionally, SHAP and LIME were used to enhance the interpretability of the results.ResultsThe study combined Random Forest, XGBoost algorithms, and LASSO regression with univariate regression analysis to identify significant predictive factors, including age, preoperative prealbumin, preoperative albumin, preoperative hemoglobin, operation time, PIKVA2, CEA, and preoperative neutrophil count. The XGBoost model outperformed other ML algorithms, achieving an AUC of 0.996, an accuracy of 0.9636, a specificity of 0.9778, and an F1 score of 0.9576. Moreover, the SHAP method identified age and preoperative prealbumin as the primary determinants influencing ML model predictions. Finally, the study employed LIME for more precise prediction and interpretation of individual predictions.ConclusionThe machine learning algorithms effectively predicted postoperative lower limb deep vein thrombosis in colorectal cancer patients. The XGBoost model demonstrated strong potential for improving early detection and treatment in clinical settings.

Automatic Classification of Rotating Rectifier Faults in Brushless Synchronous Machines

This paper presents an advanced automatic fault classification method for detecting rotating rectifier faults in brushless synchronous machines (BSMs). The proposed approach employs a multilayer perceptron (MLP) neural network to classify the operational states of the rotating rectifier, including healthy conditions and common fault types: open-diode (OD), shorted-diode (SD), and open-phase (OP). Key machine measurements, available on an ordinary basis in the industry, such as active power (P), reactive power (Q), stator voltage (U), and excitation current (Ie), are used as inputs for this model, allowing for non-invasive, real-time fault detection. This model achieved an overall classification accuracy of 93.4%, with a precision of 94.9% for fault detection and strong recall performance across multiple fault types. The neural network’s robustness is enhanced by advanced data processing techniques, including Gaussian filtering and class balancing through the synthetic minority over-sampling technique (SMOTE). Experimental testing on a modified 5-kVA BSM setup, where rectifier faults were systematically induced, was used to train the network and validate the model’s performance. This method provides a promising tool for real-time condition monitoring of BSMs, improving machine reliability and minimizing downtime in industrial applications.

An eXplainable machine learning framework for predicting the impact of pesticide exposure in lung cancer prognosis

Lung cancer, the second most prevalent and lethal cancer, is caused by aberrant and uncontrolled cell division in the lungs. Once lung cancer spreads to surrounding tissues or organs, the likelihood of recovery declines; hence, early illness detection is vital. Machine learning has shown significant potential in several healthcare applications. Examining various factors and trends in the data, the machine learning model can predict lung cancer menace by pinpointing those more susceptible to the illness. Among the various causes of lung cancer, pesticide is a major contributor. ‘Pesticide’ refers to any chemical used in agriculture to manage pests like weeds and insects. Numerous health hazards, including the possibility of developing cancer, have been linked to exposure to specific pesticides. Our objective is to obtain the trust of medical professionals and patients depending on how interpretable machine learning models are in healthcare. This paper deals with implementing the proposed study by utilizing a public dataset from a Thai case study to predict the risk of lung cancer caused by pesticide exposure. Since the dataset was highly imbalanced, a hybrid normalization technique was utilized, combining the Synthetic Minority Oversampling Technique (SMOTE) and Edited Nearest Neighbor (ENN). We applied a two-stage feature selection technique combined with Extra Tree Classifier and Principal Component Analysis. An eXplainable XGBoost Classifier is developed to predict lung cancer risk based on pesticide exposure. The robustness of the model is reflected in the results, with accuracy, sensitivity, and F1-Score as 99.00%, 98.87%, and 98.57%, respectively. Two public datasets were utilized to generalize the model, and the model performed well on both datasets. The model achieved accuracy, sensitivity, and F1-Score of 99.00%, 99.00%, and 99.33% on the ‘Lung Cancer Prediction’ dataset. The model is trained and tested on the ‘survey lung cancer’ dataset and obtained an accuracy, sensitivity, and F1-Score of 99.00%, 99.00%, 99.00%, respectively. The proposed model outperformed existing state-of-the-art methodologies regarding quality metrics. An illustration is done on the XAI (eXplainable Artificial Intelligence) model by utilizing SHapley Additive exPlanations (SHAP), thereby identifying the most relevant features contributing to the lung cancer menace.

Etiology of Late-Onset Alzheimer’s Disease, Biomarker Efficacy, and the Role of Machine Learning in Stage Diagnosis

Late-onset Alzheimer’s disease (LOAD) is a subtype of dementia that manifests after the age of 65. It is characterized by progressive impairments in cognitive functions, behavioral changes, and learning difficulties. Given the progressive nature of the disease, early diagnosis is crucial. Early-onset Alzheimer’s disease (EOAD) is solely attributable to genetic factors, whereas LOAD has multiple contributing factors. A complex pathway mechanism involving multiple factors contributes to LOAD progression. Employing a systems biology approach, our analysis encompassed the genetic, epigenetic, metabolic, and environmental factors that modulate the molecular networks and pathways. These factors affect the brain’s structural integrity, functional capacity, and connectivity, ultimately leading to the manifestation of the disease. This study has aggregated diverse biomarkers associated with factors capable of altering the molecular networks and pathways that influence brain structure, functionality, and connectivity. These biomarkers serve as potential early indicators for AD diagnosis and are designated as early biomarkers. The other biomarker datasets associated with the brain structure, functionality, connectivity, and related parameters of an individual are broadly categorized as clinical-stage biomarkers. This study has compiled research papers on Alzheimer’s disease (AD) diagnosis utilizing machine learning (ML) methodologies from both categories of biomarker data, including the applications of ML techniques for AD diagnosis. The broad objectives of our study are research gap identification, assessment of biomarker efficacy, and the most effective or prevalent ML technology used in AD diagnosis. This paper examines the predominant use of deep learning (DL) and convolutional neural networks (CNNs) in Alzheimer’s disease (AD) diagnosis utilizing various types of biomarker data. Furthermore, this study has addressed the potential scope of using generative AI and the Synthetic Minority Oversampling Technique (SMOTE) for data augmentation.

Robust diabetic prediction using ensemble machine learning models with synthetic minority over-sampling technique

This paper addresses the pressing issue of diabetes, which is a widespread condition affecting a huge population worldwide. As cells become less responsive to insulin or fail to produce it adequately, blood sugar levels rise. This has the potential to cause severe health complications including kidney disease, vision impairment and heart conditions. Early diagnosis is paramount in mitigating the risk and severity of diabetes-related complications. To tackle this, we proposed a robust framework for diabetes prediction using Synthetic Minority Over-sampling Technique (SMOTE) with ensemble machine learning techniques. Our approach incorporates strategies such as imputation of missing values, outlier rejection, feature selection using correlation analysis and class distribution balancing using SMOTE. The extensive experimentation shows that the proposed combination of AdaBoost and XGBoost shows exceptional performance, with an impressive AUC of 0.968+/-0.015. This outperforms not only alternative methodologies presented in our study but also surpasses current state-of-the-art results. We anticipate that our model will significantly improve diabetes prediction, offering a promising avenue for improved healthcare outcomes in diabetes management.

Application of machine learning techniques to profile smoking behavior of adolescent girls in Ghana

Background Tobacco use trends among adolescents in low- and middle-income countries, and in particular narrowing gender gaps, highlight the need for interventions to prevent and/or reduce tobacco use among adolescent girls. We evaluated a social marketing program in Ghana discouraging tobacco use among adolescent girls and additionally investigated the pathways influencing smoking behaviors to identify programmatic opportunities for impact. Leveraging the data collected through the stepped wedge cluster randomized trial and panel survey of 9000 girls aged 13–19 , we sought to apply machine learning (ML) techniques to identify the most important variables for predicting initiation of smoking. Methods To identify predictors of smoking initiation we sought to develop a model which could accurately differentiate smokers from non-smokers and evaluated various ML approaches for training classifier algorithms to achieve this. We selected a Synthetic Minority Over-sampling Technique (SMOTE) because it optimized the recall and precision of the model. We then utilized the technique of feature importance for greater insight into how the model arrived at its decisions and to rank the most important variables for predicting smokers. To explore different dimensions of smoking behavior, including initiation and continuation, we trained our model by using several combinations of target outcomes and input variables from the panel survey. Results The resulting features of smokers highlight the importance of girls’ independence and connectivity, social environment, and peer influence on likelihood of smoking, and in particular subsequent initiation. These results were largely consistent with our formative research findings based on qualitative interviews informed by behavioral science. Conclusions This novel application of ML techniques demonstrates how data science approaches can generate new programmatic insights from rigorous evaluation data, especially when data collection is informed by behavioral theory. Such insights about the relative importance of different features can be valuable input for program planning and outreach.

ANALYSIS STUDENT EMOTIONS AND MENTAL HEALTH ON CUMULATIVE GPA USING MACHINE LEARNING AND SMOTE

This research investigates the impact of emotions and mental health on students' cumulative grade point average (CGPA) using machine learning classification algorithms while addressing data imbalances with the Synthetic Minority Oversampling Technique (SMOTE). Emotional well-being and mental health are acknowledged as vital determinants of academic achievement. Data imbalance, particularly in mental health metrics such as anxiety and depression, frequently compromises forecast accuracy. This study improves the accuracy of CGPA prediction based on emotional and mental health factors by utilizing SMOTE in machine learning models such as logistic regression and random forest. A dataset including 226 university students, including academic records and self-reported mental health evaluations, was evaluated. The random forest model attained an accuracy of 87.63%, exceeding the logistic regression model's accuracy of 86.56%. These findings emphasize the significant role of emotions and mental health in academic outcomes and validate SMOTE’s efficacy in addressing class imbalance. This work offers a fresh technique in educational data mining by revealing the possibility for improved academic achievement forecasts based on psychological characteristics, helping to the development of targeted therapies for students experiencing emotional issues. Implications for educational policy emphasize the significance of mental health support systems in promoting academic achievement. Subsequent research should investigate supplementary psychological variables and comprehensible models to improve predictive accuracy and facilitate evidence-based policymaking.

Advanced Predictive Modeling for Hepatitis C Diagnosis Using Machine Learning

The hepatitis C virus (HCV) virus, which has infected nearly fifty million individuals across the world, has recently been receiving significant attention. With the advent of artificial intelligence, there is an increasing effort to predict the HCV by utilizing machine learning models and training such models on relevant datasets. These data-driven models can aid doctors in the early detection of Hepatitis C infection. In this study, using datasets from the National Center for Health Statistics, we aim to develop a reliable model for predicting patients with positive hepatitis C tests. The most significant challenge in predicting such diseases using machine learning methods is finding an appropriate technique to address extremely imbalanced datasets, which arise from the smaller number of patients compared to healthy individuals in real-world datasets. We utilized real-world datasets and employed different machine learning algorithms, along with various methods for data balancing and feature selection. Unlike previous studies, which lacked this level of comprehensiveness, we utilized diverse feature selection and sampling methods such as Recursive Feature Elimination, Analysis of Variance (ANOVA) feature selection, Correlation matrix, synthetic minority over-sampling technique (SMOTE), BorderlineSMOTE, support vector machine synthetic minority over-sampling technique (SVMSMOTE), and Adaptive Synthetic Sampling (ADASYN) in conjunction with different machine learning algorithms including Random Forest, Decision Tree, XGBoost, AdaBoost, and logistic regression. We are the first to develop such a comprehensive study for the prediction of the HCV. Our findings suggest that we can predict patients infected by the HCV with a reasonable recall score of 0.86. This recall is achieved through the application of a model using the AdaBoost algorithm and the ADASYN method for balancing the dataset. The model's performance, especially on the validation dataset, was slightly better when we used ANOVA feature selection. Feature importance analysis conducted with ANOVA feature selection and Recursive Feature Elimination indicates that four to five features are the most prominent in our research analysis to predict patients with positive Hepatitis C tests.

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.