Recursive Elimination Research Articles

Forecasting the trend of tuberculosis incidence in Anhui Province based on machine learning optimization algorithm, 2013–2023

Tuberculosis has been one of the most common communicable diseases raising global concerns. Accurately predicting the incidence of Tuberculosis remains challenging. Here we constructed a time-series analysis and fusion tool using multi-source data, and aimed to more accurately predict the incidence trend of tuberculosis of Anhui Province from 2013 to 2023. Random forest algorithm (RF), Feature Recursive Elimination (RFE) and Least absolute shrinkage and selection operator (LASSO) were implemented to improve the derivation of features related to infectious diseases and feature work. Based on the characteristics of infectious disease data, a model of RF-RFE-LASSO integrated particle swarm optimization multiple inputs long short term memory recurrent neural network (RRL-PSO-MiLSTM) was created to perform more accurate prediction. Results showed that the PSO-MiLSTM achieved excellent prediction results compared with common single-input and multi-input time-series models (test set MSE:42.3555, MAE: 59.3333, RMSE: 146.7237, MAPE: 2.1133, R2: 0.8634). PSO-MiLSTM enriches and complements the methodological research content of calibrating the time-series predictive analysis of infectious diseases using multi-source data, and can be used as a brand-new benchmark for the analysis of influencing factors and trend prediction of infectious diseases at the public health level in the future, as well as providing a reference for incidence rate prediction of infectious diseases.

MResGat: Multi-head Residual Dilated Convolution Assisted Gated Unit Framework for Crop Yield Prediction

The importance of predicting crop yields has increased due to growing concerns of surrounding food security. Early forecasting of crop yields holds a pivotal role in avoiding starvations by estimating the food supply available for the expanding global population. Several Deep Learning (DL) and Machine Learning (ML) techniques are involved to develop effective and accurate crop yield prediction model. Nevertheless, existing models faces some limitations such as less accuracy, high error rate because of noisy data, high training time and extracted less effective features for prediction. To overcome these issues, the novel DL methodology is introduced for attaining high accurate crop yield prediction. Initially, the soil, weather and other resources big data are collected from the various agriculture field. In data collection phase, the input data of larger size are stored in the Hadoop platform for the purpose of storing as well as processing the entire data in a distributed manner. The data are pre-processed through the utilization of Missing value imputation and z-score based data normalization. From the pre-processed data, the optimal features are considered using Integrated Correlation Random recursive elimination (InCorRe) approach. Based on the previous soil and weather information, the suitable yield of crops can be predicted using Multi head Residual dilated convolution assisted gated unit (MResGat) model. Finally, the losses of the network model can be optimized using African vulture optimization algorithm (AVO). The proposed method is evaluated using the several performance metrics, which achieved 0.023% of MSE value and 0.036% of MAE values.

Deep learning Radiomics Based on Two-Dimensional Ultrasound for Predicting the Efficacy of Neoadjuvant Chemotherapy in Breast Cancer.

We investigate the predictive value of a comprehensive model based on preoperative ultrasound radiomics, deep learning, and clinical features for pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) for the breast cancer. We enrolled 155 patients with pathologically confirmed breast cancer who underwent NAC. The patients were randomly divided into the training set and the validation set in the ratio of 7:3. The deep learning and radiomics features of pre-treatment ultrasound images were extracted, and the random forest recursive elimination algorithm and the least absolute shrinkage and selection operator were used for feature screening and DL-Score and Rad-Score construction. According to multifactorial logistic regression, independent clinical predictors, DL-Score, and Rad-Score were selected to construct the comprehensive prediction model DLRC. The performance of the model was evaluated in terms of its predictive effect, and clinical practicability. Compared to the clinical, radiomics (Rad-Score), and deep learning (DL-Score) models, the DLRC accurately predicted the pCR status, with an area under the curve (AUC) of 0.937 (95%CI: 0.895-0.970) in the training set and 0.914 (95%CI: 0.838-0.973) in the validation set. Moreover, decision curve analysis confirmed that the DLRC had the highest clinical value among all models. The comprehensive model DLRC based on ultrasound radiomics, deep learning, and clinical features can effectively and accurately predict the pCR status of breast cancer after NAC, which is conducive to assisting clinical personalized diagnosis and treatment plan.

Regression prediction model for shear strength of cold joint in concrete

The shear resistance of cold joint in concrete is influenced by various design parameters. Traditional mechanical models typically consider only a limited number of parameters to predict the shear strength of cold joints. This research aims to explore the complex nonlinear relationship between design parameters and cold joint shear strength using statistical method and machine learning technology. The goal is to develop a more accurate, reliable, and engineering applicable regression model for predicting shear strength. A dataset of 546 Z-shaped shear specimens characterizing cold joint in concrete was constructed, involving a total of 16 variables that may affect shear performance. Correlation analysis and recursive elimination were adopted to eliminate correlated and insignificant variables based on their importance. Multiple linear regression (MLR), random forest regression (RFR), and support vector machine regression (SVR) prediction models for cold joint shear strength were established based on rigorously screened variables and comprehensively evaluated using multiple methods. It was found that the most significant factors influencing the shear strength of cold joints are concrete strength, interface shear key, product of interface reinforcement strength and its reinforcement ratio, normal stress, fiber length of new concrete, casting method of the new concrete, and product of the fiber length and its tensile strength of old concrete. The MLR, SVR, and RFR models all exhibited superior performance relative to traditional mechanics-based models with regard to shear strength prediction of cold joints. The RFR model is recommended for predicting the shear strength of cold joints due to its superior evaluation indexes in comparison to the MLR and SVR models, and variable sensitivity analysis shows that it does not yield common-sense errors.

A dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020

Being a major tea producing province in China, Fujian Province is badly in need of quick and accurate spatial distribution of tea plantation for decision-making in both the agricultural economic development and the ecological environment construction for the province. This study retrieved and processed Sentinel-1 (S1) radar data and Sentinel-2 (S2) multispectral data on the GEE cloud platform; and it extracted 98 features, such as spectral features, texture features, and terrain features from the terrain data. The recursive elimination support vector machine algorithm (SVM RFE) is used to screen the characteristic variables, resulting in the creation of 4 feature combination schemes. Using a support vector machine (SVM) classifier to extract the distribution data of tea plantations and assessing the accuracy of the 4 feature combination schemes, we obtained the spatial distribution data of tea plantations at 10 m resolution in Fujian Province in 2020. On this basis, we used the GEE cloud platform to access the vegetation disturbance information in Fujian Province from 2000 to 2020. We finally obtained a dataset of spatial distribution of tea plantations at 10 m resolution in Fujian Province from 2000 to 2020 by excluding the non-tea plantation areas from the images between 2000 and 2015 with the mask generated from the 2020 tea garden extraction results. This dataset has been manually validated using sample points from key tea-producing counties and townships. The results indicate an extraction accuracy of over 92% for tea plantations in 2020. The extraction accuracy of tea plantations obtained using interference data removal method in 2000, 2005, 2010, and 2015 was all above 80%. The dataset with a high accuracy in tea plantation extraction can provide support for relevant departments in tea plantation management.

Prediction and Rational Design of Stacking Fault Energy of Austenitic Alloys Based on Interpretable Machine Learning and Chemical Composition

Accurately predicting the stacking fault energy (SFE), as one of the crucial factors influencing the material deformation mechanism, is a focal point in research. This study utilizes measured SFE values from the literature on austenitic alloys to establish a predictive model for the relationship between chemical composition and SFE using machine learning techniques. Among five compared machine learning algorithms, the extremely randomized trees algorithm demonstrates the highest prediction accuracy. Incorporating atomic features further enhances the model's performance. Subsequently, feature selection is conducted using correlation analysis, recursive elimination, and exhaustive search to obtain the optimal subset of features. The interpretability of the model is analyzed using Shapley additive explanations values, providing rankings of feature importance and critical thresholds for feature influence. Finally, rational design of SFE is demonstrated by adjusting alloy composition, exemplified by Fe–17.5Cr–15.6Ni–2.5Mo–0.02Si–0Co steel.

Hybrid optimal feature selection approach for internet of things based medical data analysis for prognosis

<p>Healthcare is very important application domain in internet of things (IoT). The aim is to provide a novel combined feature selection (FS) methods like univariate (UV) with tree-based methods (TB), recursive feature elimination (RFE) with least absolute shrinkage selection operator (LASSO), mutual information (MI) with genetic algorithm (GA) and embedded methods (EM) with univariate has been applied to internet of medical things (IoMT)based heart disease dataset. The well-suited machine learning algorithms for IoT medical data are logistic regression (LR) and support vector machine (SVM). Each combined method has been applied to the machine learning algorithms to find the best classifier for prognosis. The various performance metrices has been calculated for all the combined feature selection methods for logistic regression and support vector machine and found that for precise classification could be done using recursive elimination feature selection method with LASSO applied to logistic regression achieved a better performance than all other combined methods with high accuracy, sensitivity and high area under curve. Decision has been taken by data analytics that RFE+LASSO using LR feature selection method will provide an overall better performance for IoT based medical heart disease dataset after comparing all other combined methods with LR and SVM classifiers<em>. </em></p>

Optimization Study of Soil Organic Matter Mapping Model in Complex Terrain Areas: A Case Study of Mingguang City, China

Traditional soil organic matter mapping is mostly polygonal drawing, which is even more difficult to accurately depict in complex terrain areas. The spatial distribution of soil organic matter is closely related to agricultural production, natural resources, environmental governance, and socio-economic development. Efficiently, economically, and accurately obtaining information on changes in soil organic matter in areas with diverse topography is an urgent problem to be solved. Mingguang City has a high research value because of its unique topography and natural landscape. To solve the problem of soil organic matter mapping in this area, this study will construct an excellent organic matter prediction model. Using 173 soil survey samples (123 for training and 50 for testing), the optimal feature variable subsets selected from 31 environmental variables through Pearson correlation, stepwise regression-variance inflation factor, and recursive feature elimination models based on different algorithms were employed. Each selected feature subset was then used to construct organic matter prediction models using multiple advanced machine learning algorithms. By comparing accuracy validation and model performance, the organic matter prediction model suitable for Mingguang City (RFE-RF_SVM) was obtained, that is, the prediction model of organic matter based on support vector machines with the feature variables screened by the feature recursive elimination algorithm of random forest with RMSE = 3.504, VSI = 0.036, and R-squared = 0.730. Furthermore, the analysis focused on assessing the significance of the predictive factors. The mapping results of this study show that the soil organic matter content in the central and northwestern parts of the study area is low, and the reasons for this situation are different. The central part is mainly caused by the change of land use and topography, while the northwestern part is caused by the loose soil structure caused by the parent material. The government can take targeted measures to improve the soil in the areas with poor organic matter.

Advancing post-traumatic seizure classification and biomarker identification: Information decomposition based multimodal fusion and explainable machine learning with missing neuroimaging data

A late post-traumatic seizure (LPTS), a consequence of traumatic brain injury (TBI), can potentially evolve into a lifelong condition known as post-traumatic epilepsy (PTE). Presently, the mechanism that triggers epileptogenesis in TBI patients remains elusive, inspiring the epilepsy community to devise ways to predict which TBI patients will develop PTE and to identify potential biomarkers. In response to this need, our study collected comprehensive, longitudinal multimodal data from 48 TBI patients across multiple participating institutions. A supervised binary classification task was created, contrasting data from LPTS patients with those without LPTS. To accommodate missing modalities in some subjects, we took a two-pronged approach. Firstly, we extended a graphical model-based Bayesian estimator to directly classify subjects with incomplete modality. Secondly, we explored conventional imputation techniques. The imputed multimodal information was then combined, following several fusion and dimensionality reduction techniques found in the literature, and subsequently fitted to a kernel- or a tree-based classifier. For this fusion, we proposed two new algorithms: recursive elimination of correlated components (RECC) that filters information based on the correlation between the already selected features, and information decomposition and selective fusion (IDSF), which effectively recombines information from decomposed multimodal features. Our cross-validation findings showed that the proposed IDSF algorithm delivers superior performance based on the area under the curve (AUC) score. Ultimately, after rigorous statistical comparisons and interpretable machine learning examination using Shapley values of the most frequently selected features, we recommend the two following magnetic resonance imaging (MRI) abnormalities as potential biomarkers: the left anterior limb of internal capsule in diffusion MRI (dMRI), and the right middle temporal gyrus in functional MRI (fMRI).

Prediction of digital transformation of manufacturing industry based on interpretable machine learning.

The enhancement of digital transformation is of paramount importance for business development. This study employs machine learning to establish a predictive model for digital transformation, investigates crucial factors that influence digital transformation, and proposes corresponding improvement strategies. Initially, four commonly used machine learning algorithms are compared, revealing that the Extreme tree classification (ETC) algorithm exhibits the most accurate prediction. Subsequently, through correlation analysis and recursive elimination, key features that impact digital transformation are selected resulting in the corresponding feature subset. Shapley Additive Explanation (SHAP) values are then employed to perform an interpretable analysis on the predictive model, elucidating the effects of each key feature on digital transformation and obtaining critical feature values. Lastly, informed by practical considerations, we propose a quantitative adjustment strategy to enhance the degree of digital transformation in enterprises, which provides guidance for digital development.

MRI- and DWI-Based Radiomics Features for Preoperatively Predicting Meningioma Sinus Invasion.

The aim of this study was to use multimodal imaging (contrast-enhanced T1-weighted (T1C), T2-weighted (T2), and diffusion-weighted imaging (DWI)) to develop a radiomics model for preoperatively predicting venous sinus invasion in meningiomas. This prediction would assist in selecting the appropriate surgical approach and forecasting the prognosis of meningiomas. A retrospective analysis was conducted on 331 participants who had been pathologically diagnosed with meningiomas. For each participant, 3948 radiomics features were acquired from the T1C, T2, and DWI images. Minimum redundancy maximum correlation, rank sum test, and multi-factor recursive elimination were used to extract the most significant features of different models. Then, multivariate logistic regression was used to build classification models to predict meningioma venous sinus invasion. The diagnostic capabilities were assessed using receiver operating characteristic (ROC) analysis. In addition, a nomogram was constructed by incorporating clinical and radiological characteristics and a radiomics signature. To assess the clinical usefulness of the nomogram, a decision curve analysis (DCA) was performed.Tumor shape, boundary, and enhancement features were independent predictors of meningioma venous sinus invasion (p = 0.013, p = 0.013, p = 0.005, respectively). Eleven (T2:1, T1C:4, DWI:6) of the 3948 radiomics features were screened for strong association with meningioma sinus invasion. The areas under the ROC curves for the training and external test sets were 0.946 and 0.874, respectively. The clinicoradiomic model showed excellent predictive performance for invasive meningioma, which may help to guide surgical approaches and predict prognosis.

Radiomic nomogram for discriminating parotid pleomorphic adenoma from parotid adenolymphoma based on grayscale ultrasonography.

To differentiate parotid pleomorphic adenoma (PA) from adenolymphoma (AL) using radiomics of grayscale ultrasonography in combination with clinical features. This retrospective study aimed to analyze the clinical and radiographic characteristics of 162 cases from December 2019 to March 2023. The study population consisted of a training cohort of 113 patients and a validation cohort of 49 patients. Grayscale ultrasonography was processed using ITP-Snap software and Python to delineate regions of interest (ROIs) and extract radiomic features. Univariate analysis, Spearman's correlation, greedy recursive elimination strategy, and least absolute shrinkage and selection operator (LASSO) correlation were employed to select relevant radiographic features. Subsequently, eight machine learning methods (LR, SVM, KNN, RandomForest, ExtraTrees, XGBoost, LightGBM, and MLP) were employed to build a quantitative radiomic model using the selected features. A radiomic nomogram was developed through the utilization of multivariate logistic regression analysis, integrating both clinical and radiomic data. The accuracy of the nomogram was assessed using receiver operating characteristic (ROC) curve analysis, calibration, decision curve analysis (DCA), and the Hosmer-Lemeshow test. To differentiate PA from AL, the radiomic model using SVM showed optimal discriminatory ability (accuracy = 0.929 and 0.857, sensitivity = 0.946 and 0.800, specificity = 0.921 and 0.897, positive predictive value = 0.854 and 0.842, and negative predictive value = 0.972 and 0.867 in the training and validation cohorts, respectively). A nomogram incorporating rad-Signature and clinical features achieved an area under the ROC curve (AUC) of 0.983 (95% confidence interval [CI]: 0.965-1) and 0.910 (95% CI: 0.830-0.990) in the training and validation cohorts, respectively. Decision curve analysis showed that the nomogram and radiomic model outperformed the clinical-factor model in terms of clinical usefulness. A nomogram based on grayscale ultrasonic radiomics and clinical features served as a non-invasive tool capable of differentiating PA and AL.

Recursive Elimination of “Outliers” to Get Benchmark Dataset

Recursive Elimination of “Outliers” to Get Benchmark Dataset

MRET: Modified Recursive Elimination Technique for ranking author assessment parameters.

In scientific research, assessing the impact and influence of authors is crucial for evaluating their scholarly contributions. Whereas in literature, multitudinous parameters have been developed to quantify the productivity and significance of researchers, including the publication count, citation count, well-known h index and its extensions and variations. However, with a plethora of available assessment metrics, it is vital to identify and prioritize the most effective metrics. To address the complexity of this task, we employ a powerful deep learning technique known as the Multi-Layer Perceptron (MLP) classifier for the classification and the ranking purposes. By leveraging the MLP's capacity to discern patterns within datasets, we assign importance scores to each parameter using the proposed modified recursive elimination technique. Based on the importance scores, we ranked these parameters. Furthermore, in this study, we put forth a comprehensive statistical analysis of the top-ranked author assessment parameters, encompassing a vast array of 64 distinct metrics. This analysis gives us treasured insights in between these parameters, shedding light on the potential correlations and dependencies that may affect assessment outcomes. In the statistical analysis, we combined these parameters by using seven well-known statistical methods, such as arithmetic means, harmonic means, geometric means etc. After combining the parameters, we sorted the list of each pair of parameters and analyzed the top 10, 50, and 100 records. During this analysis, we counted the occurrence of the award winners. For experimental proposes, data collection was done from the field of Mathematics. This dataset consists of 525 individuals who are yet to receive their awards along with 525 individuals who have been recognized as potential award winners by certain well known and prestigious scientific societies belonging to the fields' of mathematics in the last three decades. The results of this study revealed that, in ranking of the author assessment parameters, the normalized h index achieved the highest importance score as compared to the remaining sixty-three parameters. Furthermore, the statistical analysis results revealed that the Trigonometric Mean (TM) outperformed the other six statistical models. Moreover, based on the analysis of the parameters, specifically the M Quotient and FG index, it is evident that combining these parameters with any other parameter using various statistical models consistently produces excellent results in terms of the percentage score for returning awardees.

Relief (Recursive Elimination of Feature) method for Solar Home System (SHS) analysis in Delta Mahakam

The area of Delta Mahakam has not been accessible by an electricity network for a long time and has been relying on gasoline as a source of electric power generation for daily and economic activity. The community uses the Solar Home System (SHS) unit for their home and public facility. The provision of these SHSs units was an activity of a community development program from a company having industrial activity in the area. This research aims to identify the SHS unit’s condition and the attributes relevant to the condition of the SHS unit. An SHS condition was determined by gathering data on the technical specification such as unit power size and battery capacity, electricity utilization, and its financing model. Data is collected using field survey, data collection, and interviews with respondents. The data was then analysed by the Recursive Elimination of Feature (Relief) method to select features sensitive to the condition of the SHS unit. The result of this study showed that the majority of SHS units are still functional to satisfy the electricity need. The set of attributes used in this research were accurate for the intended classes of SHS condition. This result provides information beneficial to improve the existing program and impact the community.

Prediction and customized design of Curie temperature of Fe-based amorphous alloys based on interpretable machine learning

Predicting the Curie temperature (Tc) is a crucial problem in the field of amorphous alloys. In this study, Fe-based amorphous alloys are taken as an example, and the composition and corresponding Tc are collected through a literature review. Three feature construction strategies are employed to establish the relationship between the composition and Tc using machine learning. The research findings demonstrate that the combination of the Meredig rule and the GBT algorithm yields the highest prediction accuracy. The features are constructed using recursive elimination and enumeration methods, ultimately resulting in an optimal 8-dimensional feature subset. Furthermore, the Shapley Additive exPlanations (SHAP) values are introduced to analyze the interpretability of the prediction model, providing a feature importance ranking and their critical values. Finally, by replacing the Fe and P atoms with Mn and Si atoms, respectively, in the Fe80P13C7 alloy, Fe62Mn18P(13-x)C7Six (x = 4,5,6) alloys are successfully designed to exhibit a Tc close to room temperature (335 K), enabling customized Tc design for Fe-based amorphous alloys.

Developing System-Based Artificial Intelligence Models for Detecting the Attention Deficit Hyperactivity Disorder

This study presents a novel methodology for automating the classification of pediatric ADHD using electroencephalogram (EEG) biomarkers through machine learning and deep learning techniques. The primary objective is to develop accurate EEG-based screening tools to aid clinical diagnosis and enable early intervention for ADHD. The proposed system utilizes a publicly available dataset consisting of raw EEG recordings from 61 individuals with ADHD and 60 control subjects during a visual attention task. The methodology involves meticulous preprocessing of raw EEG recordings to isolate brain signals and extract informative features, including time, frequency, and entropy signal characteristics. The feature selection techniques, including least absolute shrinkage and selection operator (LASSO) regularization and recursive elimination, were applied to identify relevant variables and enhance generalization. The obtained features are processed by employing various machine learning and deep learning algorithms, namely CatBoost, Random Forest Decision Trees, Convolutional Neural Networks (CNNs), and Long Short-Term Memory Networks (LSTMs). The empirical results of the proposed algorithms highlight the effectiveness of feature selection approaches in matching informative biomarkers with optimal model classes. The convolutional neural network model achieves superior testing accuracy of 97.75% using LASSO-regularized biomarkers, underscoring the strengths of deep learning and customized feature optimization. The proposed framework advances EEG analysis to uncover discriminative patterns, significantly contributing to the field of ADHD screening and diagnosis. The suggested methodology achieved high performance compared with different existing systems based on AI approaches for diagnosing ADHD.

Computational intelligence for early detection of infertility in women

Polycystic Ovary Syndrome (PCOS) is a major cause of female infertility. Early detection and treatment are critical in improving patients' prognoses. The current fertility conditions in India are sceptic, with women being more vulnerable. PCOS is one of the leading causes of infertility, affecting up to 20% of women in India. This necessitates an accurate and timely diagnosis, which can be accomplished by developing automated diagnosing models. Given that the data to be dealt with includes both clinical and non-clinical inputs, the effective information must be considered alone for the diagnosis. This necessitates a careful selection of features prior to diagnosing. The objective of this work is to identify prominent features in the dataset to develop a reliable yet simple diagnostic model to detect PCOS. To develop such a model, swarm intelligence (SI) is used for feature selection and machine learning (ML) is used for classification. Initially, optimal features are chosen using statistical methods such as correlation and Chi Square tests, as well as an exhaustive search procedure based on recursive elimination. Additionally, the SI algorithms, Particle Swarm Optimization (PSO), and Flashing Firefly (FF) algorithms are used to determine the optimal number and feasible combination of features. In the ML model, Random Forest (RF) and XGBoost classifiers were used for classification. The Synthetic Minority Oversampling Technique for Nominal and Continuous Features (SMOTENC) was employed to create a balanced dataset because the original dataset was unbalanced and all of the investigations were carried out for original and balanced datasets. Based on the metrics accuracy of training and testing, precision, recall, F1-score, AUC-ROC, and Matthew's Correlation Coefficient (MCC), a comparative analysis of the results is discussed and validated. The findings show that ML models with various feature selection algorithms perform best for various feature dimensions, with the model with RF classifier and features selected by PSO performed best with highest accuracy. A user interface module was developed with minimum features to diagnose PCOS. The performance of the model was also compared with the state of the art deep learning techniques.

Predicting the risk stratification of gastrointestinal stromal tumors using machine learning-based ultrasound radiomics.

This study aimed to use conventional ultrasound features, ultrasound radiomics, and machine learning algorithms to establish a predictive model to assess the risk of post-surgical recurrence of gastrointestinal stromal tumors (GISTs). This retrospective analysis included 230 patients with pathologically diagnosed GISTs. Radiomic features were extracted from manually annotated images. Radiomic features plus conventional ultrasound features were selected using the SelectKbest analysis of variance and stratified tenfold cross-validation recursive elimination methods. Finally, five different machine learning algorithms (logistic regression [LR], support vector machine [SVM], random forest [RF], extreme gradient boosting [XGBoost], and multilayer perceptron [MLP]) were established to predict risk stratification of GISTs. The predictive performance of the established model was mainly evaluated based on the area under the receiver operating characteristic (ROC) curve (AUC) and accuracy, whereas the predictive performance of the optimal machine learning algorithm and a radiologist's subjective assessment were compared using McNemar's test. Seven radiomics features and one conventional ultrasound feature were selected to construct the machine learning models for GIST risk classification. The mentioned five machine learning models were able to predict the malignant potential of GISTs. LR and SVM outperformed other classifiers on the test set, with LR achieving an accuracy of 0.852 (AUC, 0.881; sensitivity, 0.871; specificity, 0.826) and SVM achieving an accuracy of 0.852 (AUC, 0.879; sensitivity, 0.839; specificity, 0.870), and proved significantly better than the radiologist (accuracy, 0.691; sensitivity, 0.645; specificity, 0.813). Machine learning-based ultrasound radiomics features are able to noninvasively predict the biological risk of GISTs.

An Identification Method of Feature Interpretation for Melanoma Using Machine Learning

Melanoma is a fatal skin cancer that can be treated efficiently with early detection. There is a pressing need for dependable computer-aided diagnosis (CAD) systems to address this concern effectively. In this work, a melanoma identification method with feature interpretation was designed. The method included preprocessing, feature extraction, feature ranking, and classification. Initially, image quality was improved through preprocessing and k-means segmentation was used to identify the lesion area. The texture, color, and shape features of this region were then extracted. These features were further refined through feature recursive elimination (RFE) to optimize them for the classifiers. The classifiers, including support vector machine (SVM) with four kernels, logistic regression (LR), and Gaussian naive Bayes (GaussianNB) were applied. Additionally, cross-validation and 100 randomized experiments were designed to guarantee the generalization of the model. The experiments generated explainable feature importance rankings, and importantly, the model demonstrated robust performance across diverse datasets.