Credibility Based Imbalance Boosting Method for Software Defect Proneness Prediction

Assessment of socioeconomic and demographic risk factors for low birth weight using model-agnostic explainable ensembles.

To evaluate the feasibility of using deep learning models applied to digital breast tomosynthesis (DBT) images for non-invasive prediction of breast cancer biomarkers, including estrogen receptor (ER), progesterone receptor (PR), human epithelial growth factor receptor 2 (HER2), Ki-67 proliferation index, and triple-negative breast cancer (TNBC). In this retrospective study, patients with histopathologically-confirmed, invasive breast cancer were included. Furthermore, all included patients had complete, immunohistochemically-assessed biomarker data available. For each case, a representative DBT slice showing the tumor was selected and preprocessed using histogram equalization. Two pretrained convolutional neural networks (VGG19 and ResNet50) were fine-tuned for binary classification of each biomarker. Model performance was evaluated using accuracy, area under the curve (AUC), F1 score, and Matthews correlation coefficient. The study sample included 43 anonymized female patients. Deep learning models achieved strong predictive performance for ER (AUC = 0.81) and TNBC (AUC = 0.93). HER2 (AUC = 0.74) and Ki-67 index (AUC = 0.70) were predicted with moderate accuracy. PR results varied, with VGG19 reaching AUC = 0.76 while ResNet50 performed poorly (AUC = 0.24). Deep learning models applied to DBT images enabled non-invasive prediction of some key breast cancer biomarkers, especially ER status and TNBC type. This approach may function as a virtual biopsy to complement histopathology, guide biopsy targeting, and support treatment planning. Although preliminary, the findings highlight the potential of artificial intelligence-enhanced DBT assessment and warrant validation in larger, multi-center prospective studies.

Software defect prediction technology aids the reliability assurance team in identifying defect-prone code and assists the team in reasonably allocating limited testing resources. Recently, researchers assumed that the topological associations among code fragments could be harnessed to construct defect prediction models. Nevertheless, existing graph-based methods only concentrate on features of single-view association, which fail to fully capture the rich information hidden in the code. In addition, software defects may involve multiple code fragments simultaneously, but traditional binary graph structures are insufficient for representing these multivariate associations. To address these two challenges, this article proposes a multiview hypergraph representation learning approach (MVHR-DP) to amplify the potency of code features in defect prediction. MVHR-DP initiates by creating hypergraph structures for each code view, which are then amalgamated into a comprehensive fusion hypergraph. Following this, a hypergraph neural network is established to extract code features from multiple views and intricate associations, thereby enhancing the comprehensiveness of representation in the modeling data. Empirical study shows that the prediction model utilizing features generated by MVHR-DP exhibits superior area under the curve (AUC), F-measure, and matthews correlation coefficient (MCC) results compared to baseline approaches across within-project, cross-version, and cross-project prediction tasks.

Newer analytic approaches for developing predictive models provide a method of creating decision support to translate findings into practice. The aim of this study was to develop and validate a clinically interpretable predictive model for 12-month mortality risk among community-dwelling older adults. This is done by using routinely collected nursing assessment data to aide homecare nurses in identifying older adults who are at risk for decline, providing an opportunity to develop care plans that support patient and family goals for care. A retrospective secondary analysis of Medicare and Medicaid data of 635,590 Outcome and Assessment Information Set (OASIS-C) start-of-care assessments from January 1, 2012, to December 31, 2012, was linked to the Master Beneficiary Summary File (2012-2013) for date of death. The decision tree was benchmarked against gold standards for predictive modeling, logistic regression, and artificial neural network (ANN). The models underwent k-fold cross-validation and were compared using area under the curve (AUC) and other data science metrics, including Matthews correlation coefficient (MCC). Decision tree variables associated with 12-month mortality risk included OASIS items: age, (M1034) overall status, (M1800-M1890) activities of daily living total score, cancer, frailty, (M1410) oxygen, and (M2020) oral medication management. The final models had good discrimination: decision tree, AUC = .71, 95% confidence interval (CI) [.705, .712], sensitivity = .73, specificity = .58, MCC = .31; ANN, AUC = .74, 95% CI [.74, .74], sensitivity = .68, specificity = .68, MCC = .35; and logistic regression, AUC = .74, 95% CI [.735, .742], sensitivity = .64, specificity = .70, MCC = .35. The AUC and 95% CI for the decision tree are slightly less accurate than logistic regression and ANN; however, the decision tree was more accurate in detecting mortality. The OASIS data set was useful to predict 12-month mortality risk. The decision tree is an interpretable predictive model developed from routinely collected nursing data that may be incorporated into a decision support tool to identify older adults at risk for death.

Synthetic Bone Marrow Smears Are a Privacy-Preserving Substitute for Developing Accurate Leukemia Classification Models in Hematological Microscopy

This study applies machine learning (ML) techniques to classify fertile [for porphyry Cu and (or) Au systems] and barren adakites using geochemical data from New Brunswick, Canada. It emphasizes that not all intrusive units, including adakites, are inherently fertile and should not be directly used as the heat source evidence layer in mineral prospectivity mapping without prior analysis. Adakites play a crucial role in mineral exploration by helping distinguish between fertile and barren intrusive units, which significantly influence ore-forming processes. A dataset of 99 fertile and 66 barren adakites was analyzed using seven ML models: support vector machine (SVM), neural network, random forest (RF), decision tree, AdaBoost, gradient boosting, and logistic regression. These models were applied to classify 829 adakite samples from around the world into fertile and barren categories, with performance evaluated using area under the curve (AUC), classification accuracy, F1 score, precision, recall, and Matthews correlation coefficient (MCC). SVM achieved the highest performance (AUC = 0.91), followed by gradient boosting (0.90) and RF (0.89). For model validation, 160 globally recognized fertile adakites were selected from the dataset based on well-documented fertility characteristics. Among the tested models, SVM demonstrated the highest classification accuracy (93.75%), underscoring its effectiveness in distinguishing fertile from barren adakites for mineral prospectivity mapping. Statistical analysis and feature selection identified middle rare earth elements (REEs), including Gd and Dy, with Hf, as key indicators of fertility. A comprehensive analysis of 1596 scatter plots, generated from 57 geochemical variables, was conducted using linear discriminant analysis (LDA) to determine the most effective variable pairs for distinguishing fertile and barren adakites. The most informative scatter plots featured element vs. element combinations (e.g., Ga vs. Dy, Ga vs. Gd, and Pr vs. Gd), followed by element vs. major oxide (e.g., Fe2O3T vs. Gd and Al2O3 vs. Hf) and ratio vs. element (e.g., La/Sm vs. Gd, Rb/Sr vs. Hf) plots, whereas major oxide vs. major oxide, ratio vs. ratio, and major oxide vs. ratio plots had limited discriminatory power.

BackgroundMetastasis in the lungs is common in patients with rectal cancer, and it can have severe consequences on their survival and quality of life. Therefore, it is essential to identify patients who may be at risk of developing lung metastasis from rectal cancer.MethodsIn this study, we utilized eight machine-learning methods to create a model for predicting the risk of lung metastasis in patients with rectal cancer. Our cohort consisted of 27,180 rectal cancer patients selected from the Surveillance, Epidemiology and End Results (SEER) database between 2010 and 2017 for model development. Additionally, we validated our models using 1118 rectal cancer patients from a Chinese hospital to evaluate model performance and generalizability. We assessed our models’ performance using various metrics, including the area under the curve (AUC), the area under the precision-recall curve (AUPR), the Matthews Correlation Coefficient (MCC), decision curve analysis (DCA), and calibration curves. Finally, we applied the best model to develop a web-based calculator for predicting the risk of lung metastasis in patients with rectal cancer.ResultOur study employed tenfold cross-validation to assess the performance of eight machine-learning models for predicting the risk of lung metastasis in patients with rectal cancer. The AUC values ranged from 0.73 to 0.96 in the training set, with the extreme gradient boosting (XGB) model achieving the highest AUC value of 0.96. Moreover, the XGB model obtained the best AUPR and MCC in the training set, reaching 0.98 and 0.88, respectively. We found that the XGB model demonstrated the best predictive power, achieving an AUC of 0.87, an AUPR of 0.60, an accuracy of 0.92, and a sensitivity of 0.93 in the internal test set. Furthermore, the XGB model was evaluated in the external test set and achieved an AUC of 0.91, an AUPR of 0.63, an accuracy of 0.93, a sensitivity of 0.92, and a specificity of 0.93. The XGB model obtained the highest MCC in the internal test set and external validation set, with 0.61 and 0.68, respectively. Based on the DCA and calibration curve analysis, the XGB model had better clinical decision-making ability and predictive power than the other seven models. Lastly, we developed an online web calculator using the XGB model to assist doctors in making informed decisions and to facilitate the model’s wider adoption (https://share.streamlit.io/woshiwz/rectal_cancer/main/lung.py).ConclusionIn this study, we developed an XGB model based on clinicopathological information to predict the risk of lung metastasis in patients with rectal cancer, which may help physicians make clinical decisions.

Objectives: To create a novel preoperative prediction model based on a deep learning algorithm to predict neoplasm T staging and grading in patients with upper tract urothelial carcinoma (UTUC). Methods: We performed a retrospective cohort study of patients diagnosed with UTUC between 2001 and 2012 at our institution. Five deep learning algorithms (CGRU, BiGRU, CNN-BiGRU, CBiLSTM, and CNN-BiLSTM) were used to develop a preoperative prediction model for neoplasm T staging and grading. The Matthews correlation coefficient (MMC) and the receiver-operating characteristic curve with the area under the curve (AUC) were used to evaluate the performance of each prediction model. Results: The clinical data of a total of 884 patients with pathologically confirmed UTUC were collected. The T-staging prediction model based on CNN-BiGRU achieved the best performance, and the MMC and AUC were 0.598 (0.592–0.604) and 0.760 (0.755–0.765), respectively. The grading prediction model [1973 World Health Organization (WHO) grading system] based on CNN-BiGRU achieved the best performance, and the MMC and AUC were 0.612 (0.609–0.615) and 0.804 (0.801–0.807), respectively. The grading prediction model [2004 WHO grading system] based on BiGRU achieved the best performance, and the MMC and AUC were 0.621 (0.616–0.626) and 0.824 (0.819–0.829), respectively. Conclusions: We developed an accurate UTUC preoperative prediction model to predict neoplasm T staging and grading based on deep learning algorithms, which will help urologists to make appropriate treatment decisions in the early stage.

Objective: In this study, it was aimed to find the method with high classification success among the methods used in the study by comparing the supervised machine learning methods according to the classification performance. Material and Methods: In our study, both the real data set obtained from 302 patients with invasive ductal carcinoma and 24 different data sets obtained by simulation were used to compare the classification performance of support vector machines, random forest and artificial neural networks. The success of classifications of the methods used was compared according to the general accuracy, F-measure, Matthews correlation coefficient, area under the curve (AUC) and discriminant power in breast cancer data. In addition, the difference in training-test accuracy in the simulation data and the significance of this difference were also evaluated. Results: The highest survival classification accuracy (80%) for the test set of stage III patients with invasive ductal carcinoma was obtained from support vector machines (SVM) with the radial-based kernel. The highest values in other performance metrics (F-measure=0.87, Matthews correlation coefficient=0.22, AUC=0.89 and discriminant power=0.52), and the most successful results in simulation data were generally obtained from SVM. Conclusion: SVM had higher accuracy in both the real data set and simulation data than random forest and artificial neural networks.

In mucinous rectal cancer, it can be difficult to differentiate between cellular and acellular mucin. The purpose of this study was to evaluate, in patients with mucinous rectal cancer, the value of static enhancement (enh) and pharmacokinetic parameters of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) in predicting pathologic complete response. This retrospective cross-sectional study performed at Memorial Sloan Kettering Cancer Center included 43 patients (24 males and 19 females; mean age, 57 years) with mucinous rectal cancer who underwent MRI at baseline as well as after neoadjuvant chemoradiotherapy but before surgical resection between 2008 and 2019. Two radiologists independently segmented tumors on contrast-enhanced axial 3D T1-weighted images and sagittal DCE magnetic resonance images. On contrast-enhanced axial T1-weighted images, the static parameters enh and relative enhancement (renh) were estimated. On DCE images, the pharmacokinetic parameters Ktrans, kep, relative Ktrans (rKtrans), and relative kep (rkep) were estimated. Associations between all parameters with pathologic complete response were tested using Wilcoxon signed-rank tests. Receiver operating characteristic (ROC) analysis was performed to assess the area under the curve (AUC) for each parameter. Of the 43 patients who were included in the study, 42/43 (98%) had evaluable contrast-enhanced axial T1-weighted images and 35/43 (81%) had evaluable DCE images. Of the patients with evaluable contrast-enhanced axial T1-weighted images, 9/42 (21%) had pathologic complete response and 33/42 (79%) did not have pathologic complete response. For reader 1, enh(pre-neoadjuvant chemotherapy), enh(post-neoadjuvant chemotherapy), and renh were significant predictors of pathologic complete response [P=0.045 (AUC =0.73), 0.039 (AUC =0.74), and 0.0042, respectively]. For reader 2, enh(pre-neoadjuvant chemotherapy) and renh were significant predictors [P=0.021 (AUC =0.77) and 0.002, respectively]. For renh, the AUC was 0.83 for reader 1, and 0.82 for reader 2. Meanwhile, of those patients with evaluable DCE images, 9/35 (26%) had pathologic complete response and 26/35 (74%) did not have pathologic complete response. Ktrans(pre-neoadjuvant chemotherapy), kep(pre-neoadjuvant chemotherapy), and rkep were significant predictors [P=0.016 (AUC =0.73), 0.00057 (AUC =0.81), and 0.0096 (AUC =0.74), respectively]. Static and pharmacokinetic parameters of contrast-enhanced MRI show promise to predict neoadjuvant treatment response. Static enh parameters, which are simpler to assess, showed the strongest prediction.

The understanding of rock characteristic and fluid flow behavior at the near-wellbore region is an important topic. Triaxial experiment setup can help to investigate these properties. In this research, a new triaxial experimental setup has been developed where the higher scale of the parameters such as higher reservoir pressure, and comparatively larger core sample can be used. High permeable synthetic porous samples are prepared to validate the device. The new triaxial experimental setup is validated with water as a base fluid. In the validation test, real samples and synthetic samples are used. First, flow in convergent direction is studied which represents as production at the in-situ condition. Then, the flow in divergent direction is examined that may represent the injection of fluid to enhance the hydrocarbon production. The near-wellbore flow phenomena are studied with real and synthetic samples. The results indicate that using this triaxial setup pressure drop and pressure buildup test can be explained. The new scientific setup is able to reduce the scale-up gap between laboratory data and field data to get actual reservoir flow phenomena.

Previously, many researchers have performed analysis of various techniques for the software fault prediction (SFP). Oddly, the majority of such studies have shown the limited prediction capability and their performance for given software fault datasets was not persistent. In contrast to this, recently, ensemble techniques based SFP models have shown promising and improved results across different software fault datasets. However, many new as well as improved ensemble techniques have been introduced, which are not explored for SFP. Motivated by this, the paper performs an investigation on ensemble techniques for SFP. We empirically assess the performance of seven ensemble techniques namely, Dagging, Decorate, Grading, MultiBoostAB, RealAdaBoost, Rotation Forest, and Ensemble Selection. We believe that most of these ensemble techniques are not used before for SFP. We conduct a series of experiments on the benchmark fault datasets and use three distinct classification algorithms, namely, naive Bayes, logistic regression, and J48 (decision tree) as base learners to the ensemble techniques. Experimental analysis revealed that rotation forest with J48 as the base learner achieved the highest precision, recall, and G-mean 1 values of 0.995, 0.994, and 0.994, respectively and Decorate achieved the highest AUC value of 0.986. Further, results of statistical tests showed used ensemble techniques demonstrated a statistically significant difference in their performance among the used ones for SFP. Additionally, the cost-benefit analysis showed that SFP models based on used ensemble techniques might be helpful in saving software testing cost and effort for twenty out of twenty-eight used fault datasets.

There is limited understanding of the link between exposure to heavy metals and ischemic stroke (IS). This research aimed to develop efficient and interpretable machine learning (ML) models to associate the relationship between exposure to heavy metals and IS. The data of this research were obtained from the National Health and Nutrition Examination Survey (US NHANES, 2003-2018) database. Seven ML models were used to identify IS caused by exposure to heavy metals. To assess the strength of the models, we employed 10-fold cross-validation, the area under the curve (AUC), F1 scores, Brier scores, Matthews correlation coefficient (MCC), precision-recall (PR) curves, and decision curve analysis (DCA) curves. Following these tests, the best-performing model was selected. Finally, the DALEX package was used for feature explanation and decision-making visualization. A total of 15,575 participants were involved in this study. The best-performing ML models, which included logistic regression (LR) (AUC: 0.796) and XGBoost (AUC: 0.789), were selected. The DALEX package revealed that age, total mercury in blood, poverty-to-income ratio (PIR), and cadmium were the most significant contributors to IS in the logistic regression and XGBoost models. The logistic regression and XGBoost models showed high efficiency, accuracy, and robustness in identifying associations between heavy metal exposure and IS in NHANES 2003-2018 participants.

<strong class="journal-contentHeaderColor">Abstract.</strong> This study aims to identify key fire factors via recursive feature elimination (RFE) to generate a forest fire susceptibility map (FSM) using support vector machine (SVM), and random forest (RF) models. The fire zones were derived from MODIS satellite imagery from 2012 to 2017. Further validation of these data has been provided by field surveys and reviews of land records in rangelands and forests; a total of 352 fire points were determined in this study. Seventeen factors involving topography, geomorphology, meteorology, hydrology, and anthropology were identified as being effective primary factors in triggering and spreading fires in the selected mountainous case study area. As a first step, the RFE models of the RF, Extra trees, Gradient boosting, and AdaBoost was used to identify important fire factors among all selected primary factors. The SVM and RF models were applied once on all factors and the second on those derived from RFE models as the key factors in FSM. Training and testing data were divided tenfold, and the model's performance was evaluated using cross-validation (CV). Different metrics were used to measure accuracy, including recall, precision, F1, accuracy, the area under the curve (AUC), Matthews correlation coefficient (MCC), and Kappa. The accuracy assessment process shows that the FSM results are further improved by leveraging RFE models to distinguish the key factors and not include unnecessary factors. The greatest improvement is for SVM, with more than 10.97 % and 8.61 % in the accuracy and AUC metrics, respectively.

Landslides are among the most hazardous geomorphological processes, especially in mountainous terrains where they threaten lives, disrupt infrastructure, and degrade ecosystems. The Chamoli district in Uttarakhand, India, with its rugged topography, erratic rainfall, and anthropogenic disturbances, is highly susceptible to such events. This research focuses on generating a detailed landslide susceptibility map for Chamoli using four machine learning algorithms Naïve Bayes (NB), K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGBoost). A total of sixteen causative factors were selected and processed using Geographic Information System (GIS) techniques. To avoid multicollinearity and ensure the reliability of input variables, statistical validation was performed. The landslide inventory, consisting of 778 past events, was split into 70% training and 30% testing datasets for model development and evaluation. The models were assessed using statistical indicators such as sensitivity, specificity, precision, accuracy, F1-score, Matthews Correlation Coefficient (MCC), and the Area Under the Curve (AUC) of the Receiver Operating Characteristic (ROC). Among the models, XGBoost showed the highest performance (AUC = 0.95), followed by RF (0.83), KNN (0.79), and NB (0.78). The susceptibility analysis revealed that XGBoost categorized 17.53% of the area as highly vulnerable, outperforming RF (14.08%), KNN (14.00%), and NB (4.55%). The enhanced accuracy of XGBoost and RF stems from their ensemble learning approach, which effectively captures nonlinear relationships and mitigates overfitting. The resulting susceptibility maps are crucial tools for risk management, infrastructure planning, and sustainable development in hazard-prone Himalayan regions. This study reinforces the importance of machine learning in natural hazard assessment and suggests that future efforts should incorporate real-time data, finer-resolution remote sensing, and deep learning methods to further refine prediction accuracy.