Univariate Feature Research Articles

Ensemble-based customer churn prediction in banking: a voting classifier approach for improved client retention using demographic and behavioral data

Customer turnover is a crucial issue in banking since maintained profitability depends on keeping clients. This work aims to categorize consumer turnover in banks by using a new ensemble approach combining many machine learning methods, hence enhancing churn prediction models. Using a comprehensive dataset including demographic, financial, and behavioral data—such as credit score, account balance, tenure, and activity levels—the study employs the goal variable revealing if a customer has left the bank. The study starts with univariate, bivariate, and multivariate feature exploration and subsequently uses the Interquartile Range (IQR) approach to identify outliers thereby improving the data quality. Five models—K-Nearest Neighbors, Support Vector Classifier, Random Forest, Decision Tree, and XGBoost—a Voting Classifier ensemble—are used to estimate project churn. Building upon all the strengths of each model, this approach improves the prediction of classification and provides a balanced and highly robust classification system. The applied approaches are K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Random Forest, Decision Tree, and XGBoost within a Voting Classifier configuration. The performance of the Voting Classifier without SMOTE yields the following results: Accuracy: 0.87, precision: 0.87, recall: 0.80, and F1-Score: 0.87. The proposed model that extend the base model using SMOTE (Synthetic Minority Over-sampling Technique), yields a higher prediction accuracy of 0.90, precision of 0.90, recall of 0.90 and F1-Score of 0.90. This enhancement is proving the efficiency of SMOTE to handle the class imbalance problem in order to render the churn prediction more balanced and reliable system. The proposed approach assures a reliable solution to the strategies to retain the customers in the banking organisations.

Machine learning-based prognostic modeling in gallbladder cancer using clinical data and pre-treatment [18F]-FDG-PET-radiomic features.

This study evaluates the effectiveness of machine learning (ML) models that incorporate clinical and 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-radiomic features for predicting outcomes in gallbladder cancer patients. The study analyzed 52 gallbladder cancer patients who underwent pre-treatment [18F]-FDG-PET/CT scans between January 2011 and December 2021. Twenty-seven patients were assigned to the training cohort between January 2011 and January 2018, and the data randomly split into training (70%) and validation (30%) sets. The independent test cohort consisted of 25 patients between February 2018 and December 2021. Eight clinical features (T stage, N stage, M stage, Union for International Cancer Control [UICC] stage, histology, tumor size, carcinoembryonic antigen level, and carbohydrate antigen 19-9 level) and 49 radiomic features were used to forecast progression-free survival (PFS). Three feature selection methods were applied including the univariate statistical feature selection test method, least absolute shrinkage and selection operator Cox regression method and recursive feature elimination method, and two ML algorithms (Cox proportional hazard and random survival forest [RSF]) were employed. Predictive performance was assessed using the concordance index (C-index). Two clinical variables (UICC stage, N stage) and three radiomic features (total lesion glycolysis, grey-level size-zone matrix_grey level non-uniformity and grey-level run-length matrix_run-length non-uniformity) were identified by the statistical feature selection method as significant for PFS prediction. The RSF model incorporating these features demonstrated strong predictive performance, with C-indices above 0.80 in both training and testing sets (training 0.81, testing 0.89). This model almost closely matched the actual and predicted progression timelines with a low mean absolute error of 1.435, a median absolute error of 0.082, and a root mean square error of 2.359. This study highlights the potential of using ML approaches with clinical and pre-treatment [18F]-FDG-PET radiomic data for predicting the prognosis of gallbladder cancer.

Dynamic Prediction of Physical Exertion: Leveraging AI Models and Wearable Sensor Data During Cycling Exercise.

Background/Objectives: This study aimed to explore machine learning approaches for predicting physical exertion using physiological signals collected from wearable devices. Methods: Both traditional machine learning and deep learning methods for classification and regression were assessed. The research involved 27 healthy participants engaged in controlled cycling exercises. Physiological data, including ECG, heart rate, oxygen saturation, and pedal speed (RPM), were collected during these sessions, which were divided into eight two-minute segments. Heart rate variability (HRV) was also calculated to serve as a predictive indicator. We employed two feature selection algorithms to identify the most relevant features for model training: Minimum Redundancy Maximum Relevance (MRMR) for both classification and regression, and Univariate Feature Ranking for Classification. A total of 34 traditional models were developed using MATLAB's Classification Learner App, utilizing 20% of the data for testing. In addition, Long Short-Term Memory (LSTM) networks were trained on the top features selected by the MRMR and Univariate Feature Ranking algorithms to enhance model performance. Finally, the MRMR-selected features were used for regression to train the LSTM model for predicting continuous outcomes. Results: The LSTM model for regression demonstrated robust predictive capabilities, achieving a mean squared error (MSE) of 0.8493 and an R-squared value of 0.7757. The classification models also showed promising results, with the highest testing accuracy reaching 89.2% and an F1 score of 91.7%. Conclusions: These results underscore the effectiveness of combining feature selection algorithms with advanced machine learning (ML) and deep learning techniques for predicting physical exertion levels using wearable sensor data.

Predicting Tumor Progression in Patients with Cervical Cancer Using Computer Tomography Radiomic Features

The objective of this study was to evaluate the effectiveness of utilizing radiomic features from radiation planning computed tomography (CT) scans in predicting tumor progression among patients with cervical cancers. A retrospective analysis was conducted on individuals who underwent radiotherapy for cervical cancer between 2015 and 2020, utilizing an institutional database. Radiomic features, encompassing first-order statistical, morphological, Gray-Level Co-Occurrence Matrix (GLCM), Gray-Level Run Length Matrix (GLRLM), and Gray-Level Dependence Matrix (GLDM) features, were extracted from the primary cervical tumor on the CT scans. The study encompassed 112 CT scans from patients with varying stages of cervical cancer ((FIGO Staging of Cervical Cancer 2018): 24% at stage I, 47% at stage II, 21% at stage III, and 10% at stage IV). Of these, 31% (n = 35/112) exhibited tumor progression. Univariate feature analysis identified three morphological features that displayed statistically significant differences (p < 0.05) between patients with and without progression. Combining these features enabled a classification model to be developed with a mean sensitivity, specificity, accuracy, and AUC of 76.1% (CI 1.5%), 70.4% (CI 4.1%), 73.6% (CI 2.1%), and 0.794 (CI 0.029), respectively, employing nested ten-fold cross-validation. This research highlights the potential of CT radiomic models in predicting post-radiotherapy tumor progression, offering a promising approach for tailoring personalized treatment decisions in cervical cancer.

An Automated Histopathological Colorectal Cancer Multi‐Class Classification System Based on Optimal Image Processing and Prominent Features

ABSTRACTColorectal cancer (CRC) is characterized by the uncontrollable growth of cancerous cells within the rectal mucosa. In contrast, colon polyps, precancerous growths, can develop into colon cancer, causing symptoms like rectal bleeding, abdominal pain, diarrhea, weight loss, and constipation. It is the leading cause of death worldwide, and this potentially fatal cancer severely afflicts the elderly. Furthermore, early diagnosis is crucial for effective treatment, as it is often more time‐consuming and laborious for experts. This study improved the accuracy of CRC multi‐class classification compared to previous research utilizing diverse datasets, such as NCT‐CRC‐HE‐100 K (100,000 images) and CRC‐VAL‐HE‐7 K (7,180 images). Initially, we utilized various image processing techniques on the NCT‐CRC‐HE‐100 K dataset to improve image quality and noise‐freeness, followed by multiple feature extraction and selection methods to identify prominent features from a large data hub and experimenting with different approaches to select the best classifiers for these critical features. The third ensemble model (XGB‐LightGBM‐RF) achieved an optimum accuracy of 99.63% with 40 prominent features using univariate feature selection methods. Moreover, the third ensemble model also achieved 99.73% accuracy from the CRC‐VAL‐HE‐7 K dataset. After combining two datasets, the third ensemble model achieved 99.27% accuracy. In addition, we trained and tested our model with two different datasets. We used 80% data from NCT‐CRC‐HE‐100 K and 20% data from CRC‐VAL‐HE‐7 K, respectively, for training and testing purposes, while the third ensemble model obtained 98.43% accuracy in multi‐class classification. The results show that this new framework, which was created using the third ensemble model, can help experts figure out what kinds of CRC diseases people are dealing with at the very beginning of an investigation.

Applying a transformer architecture to intraoperative temporal dynamics improves the prediction of postoperative delirium

BackgroundPatients who experienced postoperative delirium (POD) are at higher risk of poor outcomes like dementia or death. Previous machine learning models predicting POD mostly relied on time-aggregated features. We aimed to assess the potential of temporal patterns in clinical parameters during surgeries to predict POD.MethodsLong short-term memory (LSTM) and transformer models, directly consuming time series, were compared to multi-layer perceptrons (MLPs) trained on time-aggregated features. We also fitted hybrid models, fusing either LSTM or transformer models with MLPs. Univariate Spearman’s rank correlations and linear mixed-effect models establish the importance of individual features that we compared to transformers’ attention weights.ResultsBest performance is achieved by a transformer architecture ingesting 30 min of intraoperative parameter sequences. Systolic invasive blood pressure and given opioids mark the most important input variables, in line with univariate feature importances.ConclusionsIntraoperative temporal dynamics of clinical parameters, exploited by a transformer architecture named TRAPOD, are critical for the accurate prediction of POD.

Predicting wood moisture classes by sound frequency spectra and Explainable Machine Learning during milling

ABSTRACT Varying moisture content in wood lead to problems in the automatic selection of optimised machining parameters. Therefore, production in the wood sector can be improved by the automatic identification of moisture classes during machining. In this work, wood milling was monitored by a novel optical microphone to detect differences in wood moisture classes. A full factorial randomised design was executed along with four moisture classes (dried, conditioned, wet and frozen) and two cutting speeds as independent variables. The measured signals were segmented by extracting information from each cut and were transformed to the frequency domain. A supervised univariate feature ranking based on χ ²-tests was applied to select the most important frequencies. Machine Learning was applied to the selected spectral data to classify the cutting speeds and moisture classes. After testing several classification models, ensemble models with regression-tree learners were the best-performing model type achieved an average validation accuracy of 97.2%. The model explanation was done by Local Interpretable Model-Agnostic Explanation based on regression trees as a simple model, where the frequencies that are responsible for the separation of the data could be identified and were used for retraining the model, achieving a validation accuracy of 90.5%.

A novel hybrid model for multi-step-ahead forecasting of wind speed based on univariate data feature enhancement

Reliable multistep ahead wind speed forecasting (MAWSF) is critical for the energy management of wind farms and the long-term maintenance of wind power systems. However, relying on inherent meteorological features such as temperature and atmospheric pressure often fails to meet the deep learning model’s feature requirements for accurate wind speed forecasting (WSF). This paper introduces a hybrid multistep forecasting model that constructs a univariate wind speed feature enhancement framework, combining random forest (RF) and Transformer models for WSF. Initially, the hybrid enhancement framework decomposes the univariate wind speed data and extracts time-series features, effectively mining the latent feature information. Subsequently, the RF feature selector filters out significant features contributing to WSF and eliminates redundant features to provide stable features. Finally, the Transformer model is utilized for both short-term and long-term MAWSF. This study conducted MAWSF on data with sampling intervals of 20 min, 30 min and 1 h. The results indicate that, compared to existing state-of-the-art models, the hybrid model in MAWSF tasks reduces the dependency of models on inherent meteorological features, achieving more accurate forecasting and faster computation speeds. Ultimately, the proposed model can provide reliable technical support for energy management and maintenance guidance in real-world wind farms.

Differentiating MYCN-amplified RB1 wild-type retinoblastoma from biallelic RB1 mutant retinoblastoma using MR-based radiomics: a retrospective multicenter case–control study

MYCN-amplified RB1 wild-type (MYCNampRB1+/+) retinoblastoma is a rare and aggressive subtype, often resistant to standard therapies. Identifying unique MRI features is crucial for diagnosing this subtype, as biopsy is not recommended. This study aimed to differentiate MYCNampRB1+/+ from the most prevalent RB1-/- retinoblastoma using pretreatment MRI and radiomics. Ninety-eight unilateral retinoblastoma patients (19 MYCN cases and 79 matched controls) were included. Tumors on T2-weighted MR images were manually delineated and validated by experienced radiologists. Radiomics analysis extracted 120 features per tumor. Several combinations of feature selection methods, oversampling techniques and machine learning (ML) classifiers were evaluated in a repeated fivefold cross-validation machine learning pipeline to yield the best-performing prediction model for MYCN. The best model used univariate feature selection, data oversampling (duplicating MYCN cases), and logistic regression classifier, achieving a mean AUC of 0.78 (SD 0.12). SHAP analysis highlighted lower sphericity, higher flatness, and greater gray-level heterogeneity as predictive for MYCNampRB1+/+ status, yielding an AUC of 0.81 (SD 0.11). This study shows the potential of MRI-based radiomics to distinguish MYCNampRB1+/+ and RB1-/- retinoblastoma subtypes.

High-order brain network feature extraction and classification method of first-episode schizophrenia: an EEG study.

A multimodal persistent topological feature extraction and classification method is proposed to enhance the recognition accuracy of first-episode schizophrenia patients. This approach addresses the limitations of traditional higher-order brain network analyses that rely on single persistent features (e.g., persistent images). The study utilized resting-state EEG data from 198 subjects recruited at Huilongguan Hospital in Beijing, comprising 102 males and 96 females, with a mean age of 30 years and mean education of 14 years. Persistent topological features were extracted using adaptive thresholding during persistent homology (PH) filtrations. The distribution of these features was visualized through heatmaps and persistence entropies, while the generation process was elucidated using Betti curves and persistence landscapes. The classification performance of the multimodal persistent topological features was assessed using various machine learning classifiers. The classifier yielding the highest performance was selected for comparison with traditional brain network features derived from graph theory and single persistent topological features. The results revealed significant topological changes in first-episode schizophrenia patients throughout the persistent homology filtering compared to healthy subjects. The univariate feature selection algorithm achieved a classification accuracy of 94.6% with a combination of attributes meeting the criterion of AC ≥ 0.6. The proposed method demonstrates clinical significance for the early identification and diagnosis of first-episode schizophrenia patients, offering a new research perspective for constructing higher-order functional connectivity networks and extracting topological structure features.

Study on medical dispute prediction model and its clinical-application effectiveness based on machine learning

BackgroundMedical dispute is a global public health issue, which has been garnering increasing attention. In this study, we used machine learning (ML) method to establish a dispute prediction model and explored the clinical-application efficiency of this model in effectively reducing the occurrence of medical disputes.MethodsRetrospective study of All disputes filed by Gansu Medical Mediation Committee from 2019 to 2021 and patients with the same hospital level as that of the dispute group and hospitalization year were randomly selected as the control group in 1:1 ratio. SPSS software was used for univariate feature selection of the 14 factors that may cause disputes, and factors with statistical differences were selected. The data were divided into training and test sets in a 7:3 ratio. Six ML models were selected, and Python was used to establish a dispute prediction model. The area under the curve (AUC) of the receiver operating characteristic curve (ROC), sensitivity, specificity, accuracy, precision, average precision (AP), and F1 score were used to characterize the fitting and accuracy of the models, while decision curve analysis (DCA) was used to evaluate their clinical utility.ResultsA total of 1189 patients in the dispute and control groups were extracted. Following 11 influencing factors were selected: the inpatient department, doctor title, patient age, patient gender, patient occupation, payment method, hospitalization days, hospitalization times, discharge method, blood transfusion volume, and hospitalization espenses. Compared to other models, the AUC (0.945, 95% CI 0.913–0.981), Sensitivity (0.887), Accuracy (0.887), AP (0.834), and F1 score (0.880) of the random forest model were higher than those of other models, while the DCA curve indicated its high clinical benefits.ConclusionsInpatient department, hospitalization expenses, and discharge type are the primary influencing factors of dispute. Random forest exhibited high dispute prediction and clinical-application value and is expected to be promoted for offline dispute prediction.

Developing a real-time hand exoskeleton system that controlled by a hand gesture recognition system via wireless sensors

Numerous studies have been conducted using wearable sensors on gesture recognition and classification methods for the control of robotic arms, prostheses, and exoskeleton systems. The primary goal of this study is to classify 32 different hand gestures in real-time using electromyography (EMG) signals. EMG signals obtained by measuring the electrical activity of the muscles were simulated wirelessly on a hand exoskeleton. A Myo Armband placed on the upper arm was used to generate these signals for evaluating and validating the system. The signals were normalized according to maximum voluntary contraction (MVC), and relevant features such as MAV, STD, VAR, RMS, IEMG, ZC, and WL were selected using the univariate feature selection. A support vector machine (SVM) was then used for classification. The 32 different hand gestures were classified to an accuracy level of 99.9%. In short, this proposed approach can be effectively used in real-time hand gesture recognition and generating real-time actions for the hand exoskeleton system.

Advancing thyroid care: An accurate trustworthy diagnostics system with interpretable AI and hybrid machine learning techniques

The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated potential superiority in mitigating the occurrence of this disease by facilitating early detection and treatment. However, there is a growing demand among stakeholders and patients for reliable and credible explanations of the generated predictions in sensitive medical domains. Hence, we propose an interpretable thyroid classification model to illustrate outcome explanations and investigate the contribution of predictive features by utilizing explainable AI. Two real-time thyroid datasets underwent various preprocessing approaches, addressing data imbalance issues using the Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Subsequently, two hybrid classifiers, namely RDKVT and RDKST, were introduced to train the processed and selected features from Univariate and Information Gain feature selection techniques. Following the training phase, the Shapley Additive Explanation (SHAP) was applied to identify the influential characteristics and corresponding values contributing to the outcomes. The conducted experiments ultimately concluded that the presented RDKST classifier achieved the highest performance, demonstrating an accuracy of 98.98 % when trained on Information Gain selected features. Notably, the features T3 (triiodothyronine), TT4 (total thyroxine), TSH (thyroid-stimulating hormone), FTI (free thyroxine index), and T3_measured significantly influenced the generated outcomes. By balancing classification accuracy and outcome explanation ability, this study aims to enhance the clinical decision-making process and improve patient care.

Machine learning-enabled detection of attention-deficit/hyperactivity disorder with multimodal physiological data: a case-control study

BackgroundAttention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals’ functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored.MethodsThe main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection.ResultsResults indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD.ConclusionsThis study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.

Sustainable IoT Security in Entrepreneurship: Leveraging Univariate Feature Selection and Deep CNN Model for Innovation and Knowledge

Due to the rapid increase in Internet of Things (IoT) devices in entrepreneurial environments, innovative cybersecurity advancements are needed to defend against escalating cyber threats. The present paper proposes an approach involving univariate feature selection leading to Sustainable IoT security. This method aims at increasing the efficiency and accuracy of the deep Convolutional Neural Network (CNN) model concerning botnet attack detection and mitigation. The approach to obtaining Sustainable IoT Security goes beyond the focus on technical aspects by proving that increased cybersecurity in IoT environments also fosters entrepreneurship in terms of stimulation, knowledge increase, and innovation. This approach is a major step towards providing entrepreneurs with the necessary tools to protect them in this digital era, which will enable and support the defense against cyber threats. A secure, innovative, and knowledgeable entrepreneurial environment is the result of Sustainable IoT security.

Effective Cancer Diagnosis through High-Dimensional Microarray Data Analysis by Integrating DCT and UFS

Cancer remains a global health challenge, with various types such as lung, breast, and colon cancer posing significant threats. Timely and accurate diagnosis is crucial for effective treatment and improved survival rates. Genetic research offers promising avenues in the fight against cancer, as identifying gene mutations and expression levels enables the development of targeted therapies and a deeper understanding of disease subtypes and progression. This study explores an innovative hybrid approach to enhance cancer diagnosis and classification. By combining Discrete Cosine Transformation (DCT) and Univariate Feature Selection (UFS) methods, the feature selection process is optimized for the dataset. The extracted features are then rigorously tested using established classifiers to assess their effectiveness in cancer classification. The proposed method's performance was evaluated using eight distinct datasets, and metrics such as MF1, K-score, and sensitivity were calculated and compared with various methods in the literature. Empirical evidence demonstrates that the proposed method outperforms others on 5 out of 8 datasets in terms of both accuracy and computational efficiency. The introduced method represents a reliable tool for cancer diagnosis and classification.

A New Approach of Botnet Activity Detection Models Using Combination of Univariate and ANOVA Feature Selection Techniques

A New Approach of Botnet Activity Detection Models Using Combination of Univariate and ANOVA Feature Selection Techniques

Biomarker identification by interpretable maximum mean discrepancy.

In many biomedical applications, we are confronted with paired groups of samples, such as treated versus control. The aim is to detect discriminating features, i.e. biomarkers, based on high-dimensional (omics-) data. This problem can be phrased more generally as a two-sample problem requiring statistical significance testing to establish differences, and interpretations to identify distinguishing features. The multivariate maximum mean discrepancy (MMD) test quantifies group-level differences, whereas statistically significantly associated features are usually found by univariate feature selection. Currently, few general-purpose methods simultaneously perform multivariate feature selection and two-sample testing. We introduce a sparse, interpretable, and optimized MMD test (SpInOpt-MMD) that enables two-sample testing and feature selection in the same experiment. SpInOpt-MMD is a versatile method and we demonstrate its application to a variety of synthetic and real-world data types including images, gene expression measurements, and text data. SpInOpt-MMD is effective in identifying relevant features in small sample sizes and outperforms other feature selection methods such as SHapley Additive exPlanations and univariate association analysis in several experiments. The code and links to our public data are available at https://github.com/BorgwardtLab/spinoptmmd.

Prediction of ovarian cancer prognosis using statistical radiomic features of ultrasound images

Objective. Ovarian cancer is the deadliest gynecologic malignancy worldwide. Ultrasound is the most useful non-invasive test for preoperative diagnosis of ovarian cancer. In this study, by leveraging multiple ultrasound images from the same patient to generate personalized, informative statistical radiomic features, we aimed to develop improved ultrasound image-based prognostic models for ovarian cancer. Approach. A total of 2057 ultrasound images from 514 ovarian cancer patients, including 355 patients with epithelial ovarian cancer, from two hospitals in China were collected for this study. The models were constructed using our recently developed Frequency Appearance in Multiple Univariate pre-Screening feature selection algorithm and Cox proportional hazards model. Main results. The models showed high predictive performance for overall survival (OS) and recurrence-free survival (RFS) in both epithelial and nonepithelial ovarian cancer, with concordance indices ranging from 0.773 to 0.794. Radiomic scores predicted 2 year OS and RFS risk groups with significant survival differences (log-rank test, P < 1.0 × 10−4 for both validation cohorts). OS and RFS hazard ratios between low- and high-risk groups were 15.994 and 30.692 (internal cohort) and 19.339 and 19.760 (external cohort), respectively. The improved performance of these newly developed prognostic models was mainly attributed to the use of multiple preoperative ultrasound images from the same patient to generate statistical radiomic features, rather than simply using the largest tumor region of interest among them. The models also revealed that the roundness of tumor lesion shape was positively correlated with prognosis for ovarian cancer. Significance. The newly developed prognostic models based on statistical radiomic features from ultrasound images were highly predictive of the risk of cancer-related death and possible recurrence not only for patients with epithelial ovarian cancer but also for those with nonepithelial ovarian cancer. They thereby provide reliable, non-invasive markers for individualized prognosis evaluation and clinical decision-making for patients with ovarian cancer.

Toward Enhanced Prediction of High‐Impact Solar Energetic Particle Events Using Multimodal Time Series Data Fusion Models

AbstractSolar energetic particle (SEP) events, originating from solar flares and Coronal Mass Ejections, present significant hazards to space exploration and technology on Earth. Accurate prediction of these high‐energy events is essential for safeguarding astronauts, spacecraft, and electronic systems. In this study, we conduct an in‐depth investigation into the application of multimodal data fusion techniques for the prediction of high‐energy SEP events, particularly ∼100 MeV events. Our research utilizes six machine learning (ML) models, each finely tuned for time series analysis, including Univariate Time Series (UTS), Image‐based model (Image), Univariate Feature Concatenation (UFC), Univariate Deep Concatenation (UDC), Univariate Deep Merge (UDM), and Univariate Score Concatenation (USC). By combining time series proton flux data with solar X‐ray images, we exploit complementary insights into the underlying solar phenomena responsible for SEP events. Rigorous evaluation metrics, including accuracy, F1‐score, and other established measures, are applied, along with K‐fold cross‐validation, to ensure the robustness and generalization of our models. Additionally, we explore the influence of observation window sizes on classification accuracy.