Machine Learning Classifiers Research Articles

Multi-class boosting for the analysis of multiple incomplete views on microbiome data

BackgroundMicrobiome dysbiosis has recently been associated with different diseases and disorders. In this context, machine learning (ML) approaches can be useful either to identify new patterns or learn predictive models. However, data to be fed to ML methods can be subject to different sampling, sequencing and preprocessing techniques. Each different choice in the pipeline can lead to a different view (i.e., feature set) of the same individuals, that classical (single-view) ML approaches may fail to simultaneously consider. Moreover, some views may be incomplete, i.e., some individuals may be missing in some views, possibly due to the absence of some measurements or to the fact that some features are not available/applicable for all the individuals. Multi-view learning methods can represent a possible solution to consider multiple feature sets for the same individuals, but most existing multi-view learning methods are limited to binary classification tasks or cannot work with incomplete views.ResultsWe propose irBoost.SH, an extension of the multi-view boosting algorithm rBoost.SH, based on multi-armed bandits. irBoost.SH solves multi-class classification tasks and can analyze incomplete views. At each iteration, it identifies one winning view using adversarial multi-armed bandits and uses its predictions to update a shared instance weight distribution in a learning process based on boosting. In our experiments, performed on 5 multi-view microbiome datasets, the model learned by irBoost.SH always outperforms the best model learned from a single view, its closest competitor rBoost.SH, and the model learned by a multi-view approach based on feature concatenation, reaching an improvement of 11.8% of the F1-score in the prediction of the Autism Spectrum disorder and of 114% in the prediction of the Colorectal Cancer disease.ConclusionsThe proposed method irBoost.SH exhibited outstanding performances in our experiments, also compared to competitor approaches. The obtained results confirm that irBoost.SH can fruitfully be adopted for the analysis of microbiome data, due to its capability to simultaneously exploit multiple feature sets obtained through different sequencing and preprocessing pipelines.

Emergency Department Risk Model: Timely Identification of Patients for Outpatient Care Coordination

Emergency Department Risk Model: Timely Identification of Patients for Outpatient Care Coordination

Machine-learning classifier models for predicting sarcopenia in the elderly based on physical factors.

As the size of the elderly population gradually increases, musculoskeletal disorders, such as sarcopenia, are increasing. Diagnostic techniques such as X-rays, computed tomography, and magnetic resonance imaging are used to predict and diagnose sarcopenia, and methods using machine learning are gradually increasing. This study aimed to create a model that can predict sarcopenia using physical characteristics and activity-related variables without medical diagnostic equipment, such as imaging equipment, for the elderly aged 60 years or older. A sarcopenia prediction model was constructed using public data obtained from the Korea National Health and Nutrition Examination Survey. Models were built using Logistic Regression, Support Vector Machine (SVM), XGBoost, LightGBM, RandomForest, and Multi-layer Perceptron Neural Network (MLP) algorithms, and the feature importance of the models trained with the algorithms, except for SVM and MLP, was analyzed. The sarcopenia prediction model built with the LightGBM algorithm achieved the highest test accuracy, of 0.848. In constructing the LightGBM model, physical characteristic variables such as body mass index, weight, and waist circumference showed high importance, and activity-related variables were also used in constructing the model. The sarcopenia prediction model, which consisted of only physical characteristics and activity-related factors, showed excellent performance. This model has the potential to assist in the early detection of sarcopenia in the elderly, especially in communities with limited access to medical resources or facilities. Geriatr Gerontol Int 2024; ••: ••-••.

Efficient identification of broad absorption line quasars using dimensionality reduction and machine learning

Efficient identification of broad absorption line quasars using dimensionality reduction and machine learning

Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning.

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Faulty cell prediction accuracy comparison of machine learning algorithms using temperature sensor placement optimization approach in immersion cooled Li-ion battery modules

Immersion cooling is a promising thermal management system for LiBs where the cells are submerged in a thermally conductive coolant, thus improving heat dissipation and prolonging battery life. The present study investigates an aligned arranged 4S4P immersion-cooled LiB module to develop a best-fit machine learning (ML) model that could predict the fault position in the module depending on the inputs from the temperature sensors that are optimized under different operating and fault conditions. The Pearson Correlation Coefficient (PCC) feature selection approach is used to optimize the sensors, while the data is generated from numerical simulations on a 4S4P immersion-cooled LiB module. The model validation through internal experimental trials is performed on a 2S2P battery module. The four ML classification algorithms, which include the K Nearest Neighbors, Random Forest (RF), Extreme Gradient, and Long Short Term Memory (LSTM), are trained on the optimized sensors data and are further tested internally and externally to assess their performance on unseen data within and outside the training range. A 5-fold cross-validation process is also implemented, and following a comprehensive comparison of the predictions based on the accuracies and model elapsed time, the best-fit model is identified. The results conclude that while the LSTM model slightly outweighs the other models with an accuracy of 98.18% for the specific external test cases, the RF model is chosen as the best-fit model with a prediction accuracy of 99.7% based on the error metrics and low training time for the internal testing. The outcomes of this present work contribute to the early identification of battery module failures, enhancing safety and reducing costs.

Exploring the Learning Analytics of Skill-based Course using Machine Learning Classification Models

This study explores learning analytics of a skill-based course using various machine learning classification models, including Random Forest, Logistic Regression, CatBoost, Support Vector Classification (SVC), and Naïve Bayes. The objective is to categorize student outcomes into four classes: Pass, Distinction, Withdrawn, and Fail. The research contributes to the growing body of knowledge in learning analytics and machine learning applications in education. The findings from this investigation offer educators and academic institutions a robust framework for early identification of students at risk of underperformance or withdrawal, thereby enabling timely intervention to enhance student success in skill-based courses

HSLE: A Hybrid Ensemble Classifier for Prediction of Heart Disease

Background: Detecting heart disease in a timely manner is vital for preventing its progression, as it is the primary cause of death across the globe. Machine learning has the potential to enhance diagnostic accuracy and enable better clinical decision-making. A machine learningpowered hybrid system for diagnosing heart disease may provide a better optimal solution for heart disease prediction. Objective: The overarching objectives include accuracy improvement, enhanced classification reliability, and the development of high-performance prediction models for heart disease. These objectives indicate a commitment to advancing methodologies and models in the field of machine learning and data science, particularly within the domain of healthcare and disease prediction. Method: The proposed system was developed using the Cleveland dataset that was preprocessed and analyzed using Recursive Feature Elimination with Cross-Validation (RFECV) and Least Absolute Shrinkage and Selection Operator (LASSO) feature extraction techniques. Further, a hybrid feature selection approach using RFECV and K-Best has been proposed for feature selection. Eight machine learning classifiers such as Multilayer Perceptron (MLP), Random Forest (RF), Extreme Gradient Boosting (XGB), K-Nearest Neighbours (KNN), Extra Tree (ET), Support Vector Machine (SVC), Adaboost, Decision Tree (DT) were utilized, and the performance of the system was measured in terms of various metrics. Result: The results showed that the proposed HSLE algorithm with hybrid feature selection led to the highest overall accuracy of 98.76%. Conclusion: As mentioned, the main cause of adult death worldwide is chronic disease. Early detection can stop the condition from getting worse. Our research presents an innovative hybrid machine-learning approach designed to forecast heart disease.

SPOTTING OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING

Cyberbullying occurs when someone harasses, threatens, or mistreats someone else online or on social media. Cyberbullying leads to threats, public embarrassment, and reprimands. Cyberbullying has caused a rise in youth suicide and mental health issues. It has lowered my self-esteem and escalated my suicidal thoughts. If cyberbullying continues, an entire generation of young adults will suffer from low self-esteem and mental health issues. Many machine learning algorithms are used to automatically identify social media cyberbullying. Social media monitoring allows this. These models don't account for all the factors that could make a comment or post bullying. Bullying is still ambiguous. This study presents a cyberbullying diagnosis model based on several factors. Cyberbully is a misuse of technology advantage to bully a person. This project is used Dataset namely,’ Cyberbullying-tweets’. This project used Machine Learning Classifiers such as Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and Neural Networks (NN), Logistic Regression(LR) Algorithms and calculated performance results for comparing the performance for dataset. Keywords: Cyberbullying Detection, Social Media Analysis, Machine Learning Models, Natural Language Processing (NLP), Text Classification , Feature Extraction, Sentiment Analysis, Textual Data Mining, Online Harassment, User Profiling, Toxic Language Detection, Hate Speech Detection, Content Moderation, Multi-Layer Perceptron (MLP), Support Vector Machine (SVM), Neural Network Algorithms, Lexicon-based Features, Syntactic Features, N-gram Analysis, Arabic Social Media (if focusing on Arabic language),User Behavior Analysis, Feature Engineering, Cross- Platform Analysis, Real-time Monitoring, Social Network Analysis

A machine learning prediction model for cancer risk in patients with type 2 diabetes based on clinical tests.

The incidence of type 2 diabetes is rapidly increasing worldwide. Studies have shown that it is also associated with cancer-related morbidities. Early detection of cancer in patients with type 2 diabetes is crucial. This study aimed to construct a model to predict cancer risk in patients with type 2 diabetes. This study collected clinical data from a total of 5198 patients. A cancer risk prediction model was established by analyzing 261 items from routine laboratory tests. We screened 107 risk factors from 261 clinical tests based on the importance of the characteristic variables, significance of differences between groups (P< 0.05), and minimum description length algorithm. Compared with 16 machine learning classifiers, five classifiers based on the decision tree algorithm (CatBoost, light gradient boosting, random forest, XGBoost, and gradient boosting) had an area under the receiver operating characteristic curve (AUC) of > 0.80. The AUC for CatBoost was 0.852 (sensitivity: 79.6%; specificity: 83.2%). The constructed model can predict the risk of cancer in patients with type 2 diabetes based on tumor biomarkers and routine tests using machine learning algorithms. This is helpful for early cancer risk screening and prevention to improve patient outcomes.

Unlocking the adaptive advantage: correlation and machine learning classification to identify optimal online adaptive stereotactic partial breast candidates.

Online adaptive radiotherapy (OART) is a promising technique for delivering stereotactic accelerated partial breast irradiation (APBI), as lumpectomy cavities vary in location and size between simulation and treatment. However, OART is resource-intensive, increasing planning and treatment times and decreasing machine throughput compared to the standard of care (SOC). Thus, it is pertinent to identify high-yield OART candidates to best allocate resources. &#xD;Approach. Reference plans (plans based on simulation anatomy), SOC plans (reference plans recalculated onto daily anatomy), and daily adaptive plans were analyzed for 31 sequential APBI targets, resulting in the analysis of 333 treatment plans. Spearman correlations between 22 reference plan metrics and 10 adaptive benefits, defined as the difference between mean SOC and delivered metrics, were analyzed to select a univariate predictor of OART benefit. A multivariate logistic regression model was then trained to stratify high- and low-benefit candidates.&#xD;Main Results. Adaptively delivered plans showed dosimetric benefit as compared to SOC plans for most plan metrics, although the degree of adaptive benefit varied per patient. The univariate model showed high likelihood for dosimetric adaptive benefit when the reference plan ipsilateral breast V15Gy exceeds 23.5%. Recursive feature elimination identified 5 metrics that predict high-dosimetric-benefit adaptive patients. Using leave-one-out cross validation, the univariate and multivariate models classified targets with 74.2% and 83.9% accuracy, resulting in improvement in per-fraction adaptive benefit between targets identified as high- and low-yield for 7/10 and 8/10 plan metrics, respectively. &#xD;Significance. This retrospective, exploratory study demonstrated that dosimetric benefit can be predicted using only ipsilateral breast V15 Gy on the reference treatment plan, allowing for a simple, interpretable model. Using multivariate logistic regression for adaptive benefit prediction led to increased accuracy at the cost of a more complicated model. This work presents a methodology for clinics wishing to triage OART resource allocation.&#xD.

Lumbar spine MRI annotation with intervertebral disc height and Pfirrmann grade predictions.

Many lumbar spine diseases are caused by defects or degeneration of lumbar intervertebral discs (IVD) and are usually diagnosed through inspection of the patient's lumbar spine MRI. Efficient and accurate assessments of the lumbar spine are essential but a challenge due to the size of the clinical radiologist workforce not keeping pace with the demand for radiology services. In this paper, we present a methodology to automatically annotate lumbar spine IVDs with their height and degenerative state which is quantified using the Pfirrmann grading system. The method starts with semantic segmentation of a mid-sagittal MRI image into six distinct non-overlapping regions, including the IVD and vertebrae regions. Each IVD region is then located and assigned with its label. Using geometry, a line segment bisecting the IVD is determined and its Euclidean distance is used as the IVD height. We then extract an image feature, called self-similar color correlogram, from the nucleus of the IVD region as a representation of the region's spatial pixel intensity distribution. We then use the IVD height data and machine learning classification process to predict the Pfirrmann grade of the IVD. We considered five different deep learning networks and six different machine learning algorithms in our experiment and found the ResNet-50 model and Ensemble of Decision Trees classifier to be the combination that gives the best results. When tested using a dataset containing 515 MRI studies, we achieved a mean accuracy of 88.1%.

Classification of e-waste using machine learning-assisted laser-induced breakdown spectroscopy.

Waste management and the economy are intertwined in various ways. Adopting sustainable waste management techniques can contribute to economic growth and resource conservation. Artificial intelligence (AI)-based classification is very crucial for rapid and contactless classification of metals in electronic waste (e-waste) management. In the present research work, five types of aluminium alloys, because of their extensive use in structural, electrical and thermotechnical functions in the electronics industry, were taken. Laser-induced breakdown spectroscopy (LIBS), a spectral identifier technique, was employed in conjunction with machine learning (ML) classification models of AI. Principal component analysis (PCA), an unsupervised ML classifier, was found incapable to differentiate LIBS data of alloys. Supervised ML classifier was then trained (for 10-fold cross-validation) on randomly selected 80% and tested on 20% spectral data of each alloy to assess classification capacity of each. In most of the tested variants of K nearest neighbour (kNN) the resulting accuracy was lower than 30% but kNN ensembled with random subspace method showed improved accuracy up to 98%. This study revealed that an AI-based LIBS system can classify e-waste alloys rather effectively in a non-contactless mode and could potentially be connected with robotic systems, hence, minimizing manual labour.

A novel multi-task machine learning classifier for rare disease patterning using cardiac strain imaging data

To provide accurate predictions, current machine learning-based solutions require large, manually labeled training datasets. We implement persistent homology (PH), a topological tool for studying the pattern of data, to analyze echocardiography-based strain data and differentiate between rare diseases like constrictive pericarditis (CP) and restrictive cardiomyopathy (RCM). Patient population (retrospectively registered) included those presenting with heart failure due to CP (n = 51), RCM (n = 47), and patients without heart failure symptoms (n = 53). Longitudinal, radial, and circumferential strains/strain rates for left ventricular segments were processed into topological feature vectors using Machine learning PH workflow. In differentiating CP and RCM, the PH workflow model had a ROC AUC of 0.94 (Sensitivity = 92%, Specificity = 81%), compared with the GLS model AUC of 0.69 (Sensitivity = 65%, Specificity = 66%). In differentiating between all three conditions, the PH workflow model had an AUC of 0.83 (Sensitivity = 68%, Specificity = 84%), compared with the GLS model AUC of 0.68 (Sensitivity = 52% and Specificity = 76%). By employing persistent homology to differentiate the “pattern” of cardiac deformations, our machine-learning approach provides reasonable accuracy when evaluating small datasets and aids in understanding and visualizing patterns of cardiac imaging data in clinically challenging disease states.

-wave-based exploration of sensitive EEG features and classification of situation awareness

Abstract The purpose of this study was to explore the electroencephalogram (EEG) features sensitive to situation awareness (SA) and then classify SA levels. Forty-eight participants were recruited to complete an SA standard test based on the multi-attribute task battery (MATB) II, and the corresponding EEG data and situation awareness global assessment technology (SAGAT) scores were recorded. The population with the top 25% of SAGAT scores was selected as the high-SA level (HSL) group, and the bottom 25% was the low-SA level (LSL) group. The results showed that (1) for the relative power of $\beta$ 1 (16–20Hz), $\beta$ 2 (20–24Hz) and $\beta$ 3 (24–30Hz), repeated measures analysis of variance (ANOVA) in three brain regions (Central Central-Parietal, and Parietal) × three brain lateralities (left, midline, and right) × two SA groups (HSL and LSL) showed a significant main effect for SA groups; post hoc comparisons revealed that compared with LSL, the above features of HSL were higher. (2) for most ratio features associated with $\beta$ 1 ∼ $\beta$ 3, ANOVA also revealed a main effect for SA groups. (3) EEG features sensitive to SA were selected to classify SA levels with small-sample data based on the general supervised machine learning classifiers. Five-fold cross-validation results showed that among the models with easy interpretability, logistic regression (LR) and decision tree (DT) presented the highest accuracy (both 92%), while among the models with hard interpretability, the accuracy of random forest (RF) was 88.8%, followed by an artificial neural network (ANN) of 84%. The above results suggested that (1) the relative power of $\beta$ 1 ∼ $\beta$ 3 and their associated ratios were sensitive to changes in SA levels; (2) the general supervised machine learning models all exhibited good accuracy (greater than 75%); and (3) furthermore, LR and DT are recommended by combining the interpretability and accuracy of the models.

Predicting suicidality with small sets of interpretable reward behavior and survey variables

AbstractThe prediction of suicidal thought and behavior has met with mixed results. This study of 3,476 de-identified participants (4,019 before data exclusion) quantified the prediction of four suicidal thought and behavior (STB) variables using a short reward/aversion judgment task and a limited set of demographic and mental health surveys. The focus was to produce a simple, quick and objective framework for assessing STB that might be automatable, without the use of big data. A balanced random forest classifier performed better than a Gaussian mixture model and four standard machine learning classifiers for predicting passive suicide ideation, active suicide ideation, suicide planning and planning for safety. Accuracies ranged from 78% to 92% (optimal area under the curve between 0.80 and 0.95) without overfitting, and peak performance was observed for predicting suicide planning. The relative importance of features for prediction showed distinct weighting across judgment variables, contributing between 40% and 64% to prediction per Gini scores. Mediation/moderation analyses showed that depression, anxiety, loneliness and age variables moderated the judgment variables, indicating that the interaction of judgment with mental health and demographic indices is fundamental for the high-accuracy prediction of STB. These findings suggest the feasibility of an efficient and highly scalable system for suicide assessment, without requiring psychiatric records or neural measures. The findings suggest that STB might be understood within a cognitive framework for judgment with quantitative variables whose unique constellation separates passive and active suicidal thought (ideation) from suicide planning and planning for safety.

Enhancing ECG signal classification through pre-trained stacked-CNN embeddings: a transfer learning approach

Rapid and accurate electrocardiogram (ECG) signal classification is crucial in high-stakes healthcare settings. However, existing computational models often struggle to balance high performance with computational efficiency. This study introduces an innovative computational framework that combines transfer learning with traditional machine learning to optimize ECG classification. We use a pre-trained Stacked Convolutional Neural Network (SCNN) to generate high-dimensional feature embeddings, which are then evaluated by an array of machine learning classifiers. Our models demonstrate exceptional performance, particularly when utilizing embeddings from SCNNs trained on diverse datasets. This underscores the importance of data diversity in improving classifier discrimination. Notably, Multilayer Perceptrons (MLPs) stand out for their ability to balance computational efficiency with strong performance, achieving test F1-scores of 0.94 and 1.00 in multi-class and binary tasks on the CinC2017 dataset, and 0.85 and 0.99 on the CPSC2018 dataset. Our approach consistently outperforms existing methods, setting new benchmarks in ECG classification. The synergy between deep learning-based feature extraction and traditional machine learning through transfer learning offers a robust, efficient, and adaptable strategy for ECG classification, addressing a critical research gap and laying the groundwork for future advancements in this crucial healthcare field.

Quantum Support Vector Machine for Multi Classification

Abstract Classical machine learning algorithms seem to be totally incapable of processing tremendous data, while quantum machine learning algorithms could deal with big data unhurriedly and provide exponential acceleration over classical counterpart. In this paper, we propose two quantum support vector machine algorithms for multi classification. One is the quantum version of directed acyclic graph support vector machine. The other one is to use the Grover search algorithm before measurement, which amplifies the amplitude of the phase stored in the classification result. For $k$ classification, the former provides quadratic reduction in computational complexity when classifying. The latter accelerates the training speed significantly and more importantly, the classification result can be read out with a probability of at least 50\% using only one measurement. We conduct numerical simulations on two algorithms, and their classification success rates are 96\% and 88.7\%, respectively.

Fall-risk assessment of aged workers using wearable inertial measurement units based on machine learning

Falls are the major cause of fatal and nonfatal incidents among aged workers. Estimating individual fall risk is crucial for occupational protection and public health. This study aimed to develop a fall-risk assessment method based on Machine Learning (ML) and Inertial Measurement Units (IMUs). A total of 28 aged workers (60 to 80 years old) participated in this study, recruited from community sanitation workers and janitors. They were categorized into high and low fall-risk groups based on functional gait assessment. Each participant performed 5 sets of motion experiments in the lab, covering 6 daily motions. We gathered their kinematic data with IMUs for training ML-based fall-risk assessment models. Five classic ML classifiers were optimized using grid search, and a Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) hybrid deep neural network was built to recognize walking motion from kinematic data for input into the fall-risk assessment model. The results demonstrated that ML classifiers trained with walking motion data exhibited superior performance. Cross-validation revealed that the optimized Random Forest classifier, with IMU on the right upper leg, reached 91.3 % accuracy. Additionally, the CNN-LSTM models were evaluated using F1-score, which can balance accuracy and coverage of model performance evaluation. The CNN-LSTM achieved a maximum F1-score of 95.18 %, proving their effectiveness in extracting walking motion data. These findings indicate that the developed IMU-based ML method exhibits excellent performance in assessing fall risk, potentially allowing aged workers to assess their fall risk before clinical diagnosis by embedding it in wearable IMUs.

Comparison of Different Fusion Radiomics for Predicting Benign and Malignant Sacral Tumors: A Pilot Study.

Differentiating between benign and malignant sacral tumors is crucial for determining appropriate treatment options. This study aims to develop two benchmark fusion models and a deep learning radiomic nomogram (DLRN) capable of distinguishing between benign and malignant sacral tumors using multiple imaging modalities. We reviewed axial T2-weighted imaging (T2WI) and non-contrast computed tomography (NCCT) of 134 patients pathologically confirmed as sacral tumors. The two benchmark fusion models were developed using fusion deep learning (DL) features and fusion classical machine learning (CML) features from multiple imaging modalities, employing logistic regression, K-nearest neighbor classification, and extremely randomized trees. The two benchmark models exhibiting the most robust predictive performance were merged with clinical data to formulate the DLRN. Performance assessment involved computing the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, negative predictive value (NPV), and positive predictive value (PPV). The DL benchmark fusion model demonstrated superior performance compared to the CML fusion model. The DLRN, identified as the optimal model, exhibited the highest predictive performance, achieving an accuracy of 0.889 and an AUC of 0.961 in the test sets. Calibration curves were utilized to evaluate the predictive capability of the models, and decision curve analysis (DCA) was conducted to assess the clinical net benefit of the DLR model. The DLRN could serve as a practical predictive tool, capable of distinguishing between benign and malignant sacral tumors, offering valuable information for risk counseling, and aiding in clinical treatment decisions.