Boosted Trees Research Articles

Application of machine learning methods to analyze customer migration risk in terms of corporate financial security

Effective prediction of customer migration is only possible through knowledge of the customer life cycle, which is characterized by the length of the relationship between buyer and provider, i.e. customer retention. A concept of opposite importance is customer migration, defined as the partial or total abandonment of the products or services offered by a company. Its knowledge and ability to predict it is crucial in terms of ensuring the continued financial security of target companies. The primary objective of this article was to present a method for assessing the risk of telecom industry customer migration using machine learning methods. The objective was achieved through the use of research methods, theoretical deductions such as and induction, system analysis and synthesis, and mathematical modelling, which additionally allowed for a practical analysis of the migration of customers of the telecommunications industry. Predictors with the greatest impact on the phenomenon under study were selected. It should be noted that the gain chart indicates that, in the case of contacting the 20% of customers selected by the models, the target coverage would be at the following levels, respectively: 70% for the boosted tree model and the decision tree based on the CART algorithm, and 75% for the random forest model. The research niche addressed in the article is the development of methods for assessing migration risk using machine learning techniques. The tool developed in the article can support decision-making in the creation of marketing campaigns aimed at retaining the largest number of customers.

EXPLORING THE NEXUS OF MACROECONOMIC FACTORS AND FINANCIAL RATIOS: A HOLISTIC ANALYSIS OF COMPANY PROFITABILITY IN DEVELOPING MARKETS

Purpose of the Study; The primary objective of this document is to find out the patterns among macroeconomic factors, related indexes (as external variables), financial ratio indicators (as internal drivers) that had impact on company’s profit with a holistic approach. This research also aims to clarify the threshold values and the margin of these variables to achieve profit for the listed manufacturing companies which are registered to BIST (Istanbul Stock Exchange) and operating in food, chemistry and metalware sectors. The companies which have net profit margin greater than zero are taken into the pool of investigation for the period from June 2007 to December 2022. Methodology; The study utilized supervised machine learning algorithms on KNIME Analytics Platform (The Konstanz Information Miner). A successful model has been achieved by using Random Forest Learner and Gradient Boosted Trees Learner Algorithms. Findings; Ten prominent rules have been extracted by Random Forest algorithm to predict profit/loss probability of companies. Practical implications; The findings derived from this study have direct relevance for decision makers by formulating the values of variables in different combinations to earn profit. Besides, the threshold values of the financial indicators which deepens our knowledge of the internal and external factors is expected to provide a better insight on the markets of developing countries. Originality/Value; Previous studies are mostly concentrated on the relationship of two or three macro variables with the chosen financial ratios of the companies. Besides a few studies were conducted on the markets of developing countries and if not none of them, very few of them have employed machine learning algorithms. This study aims to show what direction the variables play a role on company’s profit with a holistic approach. The diverse combination of the values of independent variables to generate profit will be evaluated with their threshold values under the country specific conditions of the markets.

Value of CT-based radiomics in evaluating the response of bone metastases to systemic drug therapy in breast cancer patients.

This study aimed to investigate the value of nonenhanced computed tomography (CT)-based radiomics in determining disease progression in breast cancer patients with bone marrow metastases and to develop a model for assessing treatment efficacy. A total of 134 breast cancer patients with bone metastases were enrolled from three hospitals. Nonenhanced CT was performed after two cycles of drug treatment. The images were categorized into an invalid and a valid group according to disease progression status. The largest osteolytic lesions' maximum cross-sections in the CT images were selected as regions of interest (ROIs) for feature extraction. Variance threshold, SelectKBest, and least absolute shrinkage and selection operator (LASSO) were used to reduce feature dimensionality. K-nearest neighbor algorithm (KNN), support vector machine (SVM), extreme gradient boosting (XGBoost), random forest (RF), logistic regression (LR), and decision tree (DT) algorithms were trained to establish radiomics models. Receiver operating characteristic (ROC) curves were generated to evaluate the diagnostic performance of the models. The KNN classifier demonstrated the best performance compared to the random grouping method. In the validation group, the area under the ROC curve (AUC) was 0.810. In the cross-validation method, the RF classifier showed the best performance with an AUC of 0.84. Nonenhanced CT-based radiomics provides a promising method for evaluating the efficacy of systemic drug therapy in breast cancer patients with osteolytic bone metastases.

Accident Probability Prediction and Analysis of Bus Drivers Based on Occupational Characteristics

A city bus carries a large number of passengers, and any traffic accidents can lead to severe casualties and property losses. Hence, predicting the likelihood of accidents among bus drivers is paramount. This paper considered occupational driving characteristics such as cumulative driving duration, station entry and exit features, and peak driving times, and categorical boosting (CatBoost) was used to construct an accident probability prediction model. Its effectiveness was confirmed by the daily management data of a Chongqing bus company in June. For data processing, Multiple Imputation by Chained Equations for Random Forests (MICEForest) was used for data filling. In terms of prediction, a comparative analysis of four boosted trees revealed that CatBoost exhibited superior performance. To analyze the critical factors affecting the probability of bus driver accidents, SHapley Additive exPlanations (SHAP) was applied to visualize and interpret the results. In addition to the significant effects of age, rainfall, and azimuthal change, etc., we innovatively discovered that the proportion of driving duration during peak duration, the dispersion when entering and exiting stations, the proportion of driving duration within a week, and the accumulated driving duration of the previous week also had varying degrees of impact on accident probability. Our research and findings provide a new idea of accident prediction for professional drivers and direct theoretical support for the accident risk management of bus drivers.

FRAGSITE2: A structure and fragment-based approach for virtual ligand screening.

Protein function annotation and drug discovery often involve finding small molecule binders. In the early stages of drug discovery, virtual ligand screening (VLS) is frequently applied to identify possible hits before experimental testing. While our recent ligand homology modeling (LHM)-machine learning VLS method FRAGSITE outperformed approaches that combined traditional docking to generate protein-ligand poses and deep learning scoring functions to rank ligands, a more robust approach that could identify a more diverse set of binding ligands is needed. Here, we describe FRAGSITE2 that shows significant improvement on protein targets lacking known small molecule binders and no confident LHM identified template ligands when benchmarked on two commonly used VLS datasets: For both the DUD-E set and DEKOIS2.0 set and ligands having a Tanimoto coefficient (TC) < 0.7 to the template ligands, the 1% enrichment factor (EF1% ) of FRAGSITE2 is significantly better than those for FINDSITEcomb2.0 , an earlier LHM algorithm. For the DUD-E set, FRAGSITE2 also shows better ROC enrichment factor and AUPR (area under the precision-recall curve) than the deep learning DenseFS scoring function. Comparison with the RF-score-VS on the 76 target subset of DEKOIS2.0 and a TC < 0.99 to training DUD-E ligands, FRAGSITE2 has double the EF1% . Its boosted tree regression method provides for more robust performance than a deep learning multiple layer perceptron method. When compared with the pretrained language model for protein target features, FRAGSITE2 also shows much better performance. Thus, FRAGSITE2 is a promising approach that can discover novel hits for protein targets. FRAGSITE2's web service is freely available to academic users at http://sites.gatech.edu/cssb/FRAGSITE2.

Machine learning for layer-by-layer nanofiltration membrane performance prediction and polymer candidate exploration

In this study, machine learning-based models were established for layer-by-layer (LBL) nanofiltration (NF) membrane performance prediction and polymer candidate exploration. Four different models, i.e., linear, random forest (RF), boosted tree (BT), and eXtreme Gradient Boosting (XGBoost), were formed, and membrane performance prediction was determined in terms of membrane permeability and selectivity. The XGBoost exhibited optimal prediction accuracy for membrane permeability (coefficient of determination (R2): 0.99) and membrane selectivity (R2: 0.80). The Shapley Additive exPlanation (SHAP) method was utilized to evaluate the effects of different LBL NF membrane fabrication conditions on membrane performances. The SHAP method was also used to identify the relationships between polymer structure and membrane performance. Polymers were represented by Morgan fingerprint, which is an effective description approach for developing modeling. Based on the SHAP value results, two reference Morgan fingerprints were constructed containing atomic groups with positive contributions to membrane permeability and selectivity. According to the reference Morgan fingerprint, 204 potential polymers were explored from the largest polymer database (PoLyInfo). By calculating the similarities between each potential polymer and both reference Morgan fingerprints, 23 polymer candidates were selected and could be further used for LBL NF membrane fabrication with the potential for providing good membrane performance. Overall, this work provided new ways both for LBL NF membrane performance prediction and high-performance polymer candidate exploration. The source code for the models and algorithms used in this study is publicly available to facilitate replication and further research. https://github.com/wangliwfsd/LLNMPP/

Comparison and analysis of multiple machine learning models for discriminating benign and malignant testicular lesions based on magnetic resonance imaging radiomics.

Accurate identification of testicular tumors through better lesion characterization can optimize the radical surgical procedures. Here, we compared the performance of different machine learning approaches for discriminating benign testicular lesions from malignant ones, using a radiomics score derived from magnetic resonance imaging (MRI). One hundred fifteen lesions from 108 patients who underwent MRI between February 2014 and July 2022 were enrolled in this study. Based on regions-of-interest, radiomics features extraction can be realized through PyRadiomics. For measuring feature reproducibility, we considered both intraclass and interclass correlation coefficients. We calculated the correlation between each feature and the predicted target, removing redundant features. In our radiomics-based analysis, we trained classifiers on 70% of the lesions and compared different models, including linear discrimination, gradient boosting, and decision trees. We applied each classification algorithm to the training set using different random seeds, repeating this process 10 times and recording performance. The highest-performing model was then tested on the remaining 30% of the lesions. We used widely accepted metrics, such as the area under the curve (AUC), to evaluate model performance. We acquired 1,781 radiomic features from the T2-weighted maps of each lesion. Subsequently, we constructed classification models using the top 10 most significant features. The 10 machine-learning algorithms we utilized were capable of diagnosing testicular lesions. Of these, the XGBoost classification emerged as the most superior, achieving the highest AUC value of 0.905 (95% confidence interval: 0.886-0.925) on the testing set and outstripping the other models that typically scored AUC values between 0.697-0.898. Preoperative MRI radiomics offers potential for distinguishing between benign and malignant testicular lesions. An ensemble model like the boosting algorithm embodied by XGBoost may outperform other models.

Artificial hummingbird algorithm-optimized boosted tree for improved rainfall-runoff modelling

Abstract Rainfall-runoff modelling is a critical component of hydrological studies, and its accuracy is essential for water resource management. Recent advances in machine learning have led to the development of more sophisticated rainfall-runoff models, but there is still room for improvement. This study proposes a novel approach to streamflow modelling that uses the artificial hummingbird algorithm (AHA) to optimize the boosted tree algorithm. the AHA-boosted tree algorithm model was compared against two established methods, the support vector machine (SVM) and the Gaussian process regression (GPR), using a variety of statistical and graphical performance measures. The results showed that the AHA-boosted tree algorithm model significantly outperformed the SVM and GPR models, with an R2 of 0.932, RMSE of 5.358 m3/s, MAE of 2.365 m3/s, and MSE of 28.705 m3/s. The SVM model followed while the GPR model had the least accurate performance. However, all models underperformed in capturing the peak flow of the hydrograph. Evaluations using both statistical and graphical performance measures, including time series plots, scatter plots, and Taylor diagrams, were critical in this assessment. The results suggest that the AHA-boosted tree algorithm could potentially be a superior alternative for enhancing the precision of rainfall-runoff modelling, despite certain challenges in predicting peak flow events.

Utilizing an intelligent machine learning strategy for predicting the tensile strength and ductility properties of nitrogen doped CoCrFeMnNi based high entropy alloys

The integration of machine learning (ML) within the realm of artificial intelligence has unveiled remarkable potential for predicting material properties. Particularly, determining critical properties such as yield strength (YS), tensile strength (UTS), and elongation in high entropy alloys (HEAs) has been a formidable challenge due to the extensive composition possibilities. The application of ML methods offers a viable solution for determining the optimal composition and mechanical properties of HEA materials. In this study, six ensemble ML algorithms, including random forest (RF), adaboost, xgboost, gradient boosting, bagging, and extra trees are employed to predict the tensile strength and ductility of nitrogen (N) doped CoCrFeMnNi based HEAs, which includes yield strength, tensile strength, and elongation properties. To explore the correlations between different features in the dataset, both the Pearson correlation and SHAP (SHapley Additive exPlanations) coefficient methods are employed. The gradient boosting ML model, in particular, distinguished itself with remarkable precision, achieving outstanding coefficient of determination (R2) values of approximately 98.25% for YS, 97.39% for UTS, and 94.45% for elongation. Moreover, it demonstrated lower mean absolute error (MAE) values for yield strength (32.62 MPa), tensile strength (37.48 MPa), and elongation (3.40%). This pattern strongly emphasizes its superiority in providing more accurate predictions compared to the other models. Notably, the model's prediction results for all three tensile properties are closely matched with the values obtained through experimental testing. This alignment between predictions and actual results serves as a crucial validation of the model's exceptional accuracy and reliability in precisely predicting these properties. Furthermore, the scrutinizing the impact of both prominent and less influential features on the ML model's performance is analyzed. Thereby, these findings underscore the remarkable effectiveness of the gradient boosting model as a predictive tool, emphasizing its ability to provide highly accurate and reliable predictions for HEAs properties.

Multi-property digital soil mapping at 30-m spatial resolution down to 1 m using extreme gradient boosting tree model and environmental covariates

Information on the variability of soil properties including clay, calcium carbonate equivalent (CCE) and acidity (pH) in space and depth play major role in sustainable agricultural development but scarce in many regions in the world, specifically in developing countries. Digital soil mapping technique has shown strong success in the prediction of soil properties both in space and depth from their relationship with environmental covariates. The aim of the study was to digitally map soil properties including clay, CCE and pH at multiple depths and identify the dominant factors controlling their variability using Minadoab region of Iran as a case study area due to its significance for agricultural production and economic development in the country. A total of 104 soil profiles were randomly selected and described in field during 15–30 July 2017, and 386 samples were collected from each genetic horizon with variable depths. A continuous spline function was fitted to the horizon data and properties were estimated at five standardized depths following GlobalSoilMap project. The soil layers were then grouped into three classes: i) H1: top (0–5 cm); ii) H2–H4: middle (5–15, 15–30 and 30–60 cm); and iii) H5: bottom (60–100 cm) for easy interpretation. A total of 17 static environmental covariates were derived from terrain-related attributes. Additionally, matching with the soil sampling date, a total of eight band ratios in addition to six individual bands were derived from Landsat-8 OLI (Product ID: LC08_L1TP_168034_20170721_20170728_01_T1) for the study area. Finally, all covariates were categorized in nine groups representing various factors controlling soil variations. The digital maps associated with uncertainties were prepared using extreme gradient boosting (XGBoost) Tree model and bootstrapping method, respectively. Overall, the highest accuracy using XGBoost Tree model was found for CCE (R2 = 0.73, on average), followed by pH (R2 = 0.72, on average) and clay (R2 = 0.70, on average). The highest amount of clay was observed for the bottom layer, followed by middle and top layers across the study area. H1 to H3 layers were subjected to tillage operations over the time and may have contributed to the redistribution of clays. A similar trend was also observed for CCE and pH as the location of the study area is underlain by massive limestone. The uncertainties helped quantify over- and under-estimation of the predictions and the factors with the highest variable importance was identified as the dominant factor. The information generated for the study area provides soil variability information that is critical for developing management strategies for sustainable production in the area.

Predictive modelling of sweep's specific draft using machine learning regression approaches

AbstractModelling and optimizing soil‐tool interaction parameters for tillage operations is crucial for developing efficient and precise tools. This study focused on a specific draft of sweep tools in the soil bin filled with vertisol, considering factors such as tool geometry, cone index, working depth and operational speed. Data analysis showed that the range of specific draft values, from 9.51 to 38.95 kN/m2. Machine learning models, including artificial neural network (ANN), support vector machine (SVM), bagged trees (BT) and boosted trees (BoT), were developed using experimental data to predict the specific draft of sweep tools with hyperparameter configuration. The developed machine learning models have also been compared with the predictive multiple linear regression (MLR) model, and it was found that the predictive performance of the machine learning models was better than the MLR model during training and testing. The fine‐tuned ANN model achieved impressive statistical performance with the lowest mean absolute error (MAE) of 0.489 kN/m2, root mean square error (RMSE) of 0.619 kN/m2, standard error of prediction (SEP) of 3.462% and highest coefficient of determination (R2) of .99 during testing. R2 values for BT, BoT, SVM and MLR models were .97, .96, .94 and .83, respectively, for specific draft predictions. The findings from this study have practical implications for optimizing sweep tool design and improving tillage operation. Manufacturers and farmers can benefit from predictive modelling using machine learning to design and select appropriate tillage tools for specific soil conditions. This approach can lead to improved soil health, increased yields and reduced costs.

Impact of environmental variables on the distribution of phytoplankton communities in the Southern Yellow Sea

To gain a comprehensive understanding of the seasonal variation in the structure of phytoplankton communities in the Southern Yellow Sea (SYS), two research expeditions were conducted from 12 to 24 in April 2019, and from 12 to 22 in October of 2019. During the spring season, the phytoplankton community within the SYS was primarily comprised of diatoms and dinoflagellates, while in autumn, diatoms and cyanobacteria dominated. Thalassiosira rotula and Paralia sulcata were the dominant species in both seasons. In spring, P. sulcata displayed no obvious correlation with any environmental parameter, while in autumn, it exhibited negative correlations with environmental factors. According to the cluster and multidimensional scaling analyses, the phytoplankton community was stratified into three distinct ecological provinces in the SYS: the Western Yellow Sea, the Yellow Sea basin, and the southern coastal region. The phytoplankton community composition was predominantly affected by seasonal fluctuations in temperature and nutrient levels. Notably, the Yellow Sea basin exhibited the lowest phytoplankton abundance, largely because of the impact of the Yellow Sea Cold Water Mass. Furthermore, the presence of cyanobacteria, particularly prevalent in the Yellow Sea basin, may have been facilitated by transport mechanisms associated with the Kuroshio current. Aggregated boosted tree (ABT) and Generalized Additive models (GAM) suggested that temperature, DIN, salinity, and DIP were significant parameters of phytoplankton abundance in SYS. Additionally, the N:P nutrient ratio was a key parameter in governing the structure of phytoplankton communities during both seasons.

Development of Machine-Learning Models to Predict Ambulation Outcomes Following Spinal Metastasis Surgery.

Retrospective cohort study. This study aimed to develop machine-learning algorithms to predict ambulation outcomes following surgery for spinal metastasis. Postoperative ambulation status following spinal metastasis surgery is currently difficult to predict. The improved ability to predict this important postoperative outcome would facilitate management decision-making and help in determining realistic treatment goals. This retrospective study included patients who underwent spinal metastasis at a university-based medical center in Thailand between January 2009 and November 2021. Collected data included preoperative parameters and ambulatory status 90 and 180 days following surgery. Thirteen machine-learning algorithms, namely, artificial neural network, logistic regression, CatBoost classifier, linear discriminant analysis, extreme gradient boosting, extra trees classifier, random forest classifier, gradient boosting classifier, light gradient boosting machine, naïve Bayes, K-neighbor classifier, Ada boost classifier, and decision tree classifier were developed to predict ambulatory status 90 and 180 days following surgery. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and F1-score. In total, 167 patients were enrolled. The number of patients classified as ambulatory 90 and 180 days following surgery was 140 (81.9%) and 137 (82.0%), respectively. The extreme gradient boosting algorithm was found to most accurately predict 180-day ambulatory outcome (AUC, 0.85; F1-score, 0.90), and the decision tree algorithm most accurately predicted 90-day ambulatory outcome (AUC, 0.94; F1-score, 0.88). Machine-learning algorithms were effective in predicting ambulatory status following surgery for spinal metastasis. Based on our data, the extreme gradient boosting and decision tree best predicted postoperative ambulatory status 180 and 90 days after spinal metastasis surgery, respectively.

Prediction of lymph node metastasis of lung squamous cell carcinoma by machine learning algorithm classifiers.

Lymph node metastasis (LNM) is an essential factor affecting the prognosis of patients with lung squamous cell carcinoma (LUSC), as well as a critical consideration for the choice of treatment strategy. Exploring effective methods for predicting LNM in LUSC may benefit clinical decision making. We used data collected from the Surveillance, Epidemiology, and End Results (SEER) database to develop machine learning algorithm classifiers, including boosted trees (BTs), based on the primary clinical parameters of patients to predict LNM in LUSC. Training on a large-sample training cohort (n = 8,063) allowed for the construction of several concise classifiers for LNM prediction in LUSC, which were then validated using test and in-house cohorts (n = 2,017 and 57, respectively). The six classifiers established in this research enabled distinction between patients with and without LNM. Among these classifiers, the BT classifier was the top performer, with accuracy, F1 scores, precision, recall, sensitivity, and specificity values of 0.654, 0.621, 0.654, 0.592, 0.592, and 0.711, respectively. The precision recall (PR) and receiver operating characteristic (ROC) (with area under the curve = 0.714) curves also supported this result, which was validated by the in-house cohort. Notably, the tumor stage was a critical factor in determining LNM in patients with LUSC. The use of classifiers, especially the BT classifier, may serve as a useful tool for improving clinical precision and individualized treatment of patients with LUSC.

Integration of multiple single cell microglial datasets reveals radial differentiation into long‐lived substates associated with Alzheimer’s pathology

AbstractBackgroundUnsupervised classification of brain cell types can be readily achieved through analysis of gene expression patterns in multidimensional space. However, the small transcriptional differences between microglia subtypes require more principled, robust, and reproducible approaches to expose and distinguish biological differences from noise.MethodHere we leverage Fokker‐Planck diffusion maps [1,2] to examine the dynamics of microglia subtypes by finding a low dimensional representation of the underlying stochastic dynamical system responsible for generating these transcriptional states. Clustering directly on this projection allows us to reduce noise, assign time scales to these substates, and generate a hierarchy of microglial cell states. Once these subtypes have been defined, we apply pseudobulk differential expression analysis to identify marker genes, and use those genes to build a boosted tree model to classify cells states. We then apply Shapley additive explanations (SHAP) to identify which genes are most important for distinguishing between cell states.ResultWe observe a radial transition pattern emanating, with a subtype that appears homeostatic, inactivated, and poised for transition. This is consistent with the observation that microglia dynamics are sensitive to their microenvironment. Deconvolution of an independent bulk microglia dataset (n = 130) showed depletion in subtypes linked to protein misfolding and myelin phagocytosis, as well as enrichment in immunoreactive microglia in Alzheimer’s patients. SHAP reveals DUSP1, CD83, PLCG2, OLR1,CCL2, and JUN among the most important genes for differentiating into these AD‐associated clusters.ConclusionOur approach enables us to reproducibly identify microglial subtypes across sets of single cell‐resolution high dimensional molecular profile data, identifying likely drivers of subtype differentiation. With several of our driver genes already associated with Alzheimer’s via GWAS and other analyses, our results will enable us to elucidate the role of these genes in determining microglial subtypes.

Explainable Boosting Machine: A Contemporary Glass-Box Model to Analyze Work Zone-Related Road Traffic Crashes

Examining the factors contributing to work zone crashes and implementing measures to reduce their occurrence can significantly improve road safety. In this research, we utilized the explainable boosting machine (EBM), a modern glass-box machine learning (ML) model, to categorize and predict work zone-related crashes and to interpret the various contributing factors. The issue of data imbalance was also addressed by utilizing work zone crash data from the state of New Jersey, comprising data collected over the course of two years (2017 and 2018) and applying data augmentation strategies such synthetic minority over-sampling technique (SMOTE), borderline-SMOTE, and SVM-SMOTE. The EBM model was trained using augmented data and Bayesian optimization for hyperparameter tuning. The performance of the EBM model was evaluated and compared to black-box ML models such as combined kernel and tree boosting (KTBoost, python 3.7.1 and KTboost package version 0.2.2), light gradient boosting machine (LightGBM version 3.2.1), and extreme gradient boosting (XGBoost version 1.7.6). The EBM model, using borderline-SMOTE-treated data, demonstrated greater efficacy with respect to precision (81.37%), recall (82.53%), geometric mean (75.39%), and Matthews correlation coefficient (0.43). The EBM model also allows for an in-depth evaluation of single and pairwise factor interactions in predicting work zone-related crash severity. It examines both global and local perspectives, and assists in assessing the influence of various factors.

STB: synthetic minority oversampling technique for tree-boosting models for imbalanced datasets of intrusion detection systems

Attacks on the Intrusion Detection System (IDS) can result in an imbalanced dataset, making it difficult to predict what types of attacks will occur. A novel method called SMOTE Tree Boosting (STB) is proposed to generate synthetic tabular data from imbalanced datasets using the Synthetic Minority Oversampling Technique (SMOTE) method. In this experiment, multiple datasets were used along with three boosting-based machine learning algorithms (LightGBM, XGBoost, and CatBoost). Our results show that using SMOTE improves the content accuracy of the LightGBM and XGBoost algorithms. Using SMOTE also helps to better predict computational processes. proven by its accuracy and F1 score, which average 99%, which is higher than several previous studies attempting to solve the same problem known as imbalanced IDS datasets. Based on an analysis of the three IDS datasets, the average computation time required for the LightGBM model is 2.29 seconds, 11.58 seconds for the XGBoost model, and 52.9 seconds for the CatBoost model. This shows that our proposed model is able to process data quickly.

Human mobility and medical costs of lifestyle-related diseases during the COVID-19 pandemic: A cross-sectional study in Japan

IntroductionDuring the COVID-19 pandemic, restrictions on human mobility caused health problems. Therefore, it is valuable to evaluate the human mobility restrictions during the pandemic from the population health viewpoint. This study aimed to clarify the correlation between changes in human mobility types and medical costs of lifestyle-related diseases during the pandemic. MethodsThe study design was set as a cross-sectional study regarding the human mobility types and the medical cost of lifestyle-related diseases. The population was Japanese people. Boosted tree analysis analyzed the nonlinear relationship between human mobility types and medical costs of lifestyle-related diseases in Japan. The boosted tree analysis can obtain high accurate models. ResultsThe results of this analysis indicated that medical costs were differently affected by walking, driving, and public transit, depending on the type of prefecture. Increasing walking by over 70% reduced the medical costs of lifestyle-related diseases, even during the COVID-19 pandemic. In metropolitan prefectures, the total effect on medical cost was higher for walking and public transit. In addition, medical costs decreased by gradually increasing public transit use by over 110%. On the other hand, in other prefectures, the total effect of public transit was lower than driving, and medical costs increased from 80% to 160%. These results were significant because they indicated the target value for each human mobility type in metropolitan areas and other prefectures. ConclusionsIn conclusion, this analysis indicated that increasing walking and public transit use correlated with a decreasing in the medical costs of lifestyle-related diseases even during the COVID-19 pandemic. The results were significant because they indicate the target value for each human mobility type according to the metropolitan and the other prefectures. Based on the target values, our findings implicate that governments can take measures other than restricting walking and public transit during the pandemic.

Biomarkers for predicting diabetes in gastric cancer patients with machine learning methods based on proteomic data

Gastric cancer is a type of cancer that occurs when cells in the stomach tissue grow and multiply abnormally. Gastric cancer usually starts in the inner layer of the stomach wall and can spread to other layers over time. This type of cancer is most common in people over the age of 50, but it can also occur in younger people. Symptoms of gastric cancer include indigestion and stomach pain, nausea and vomiting, loss of appetite and weight loss, bloody stools, fatigue and weakness. Although the exact cause of stomach cancer is not known, several risk factors have been identified. These risk factors include infection with the bacterium Helicobacter pylori, a family history of stomach cancer, consumption of excessively salty foods, smoking, heavy alcohol use and some genetic factors. Diabetes, on the other hand, is a hormonal disorder that regulates the body's blood sugar levels. Normally, an organ called the pancreas controls blood sugar by producing a hormone called insulin. Insulin helps glucose (sugar) enter the cells so that they can make energy. In diabetes, this regulation is disrupted, which can lead to high blood sugar and various health problems. The relationship between stomach cancer and diabetes is not yet fully understood. In this study, machine learning models (Stochastic Gradient Boosting, Bagged Classification and Regression Trees) based on proteomic data were used to predict the diabetes risk of 40 gastric cancer patients, 21 with DM and 19 with non-DM. Performance metrics for the optimal model (Stochastic Gradient Boosting) the accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value and F1-score values are 0.86, 0.83, 0.67, 1.00, 1.00, 0.80, 0.80, respectively. According to the variable importance values obtained as a result of the model, Mucin-13 protein has a positive predictive value in predicting the diabetes risk of gastric cancer patients in the clinic.

Artificial Intelligence Algorithms for Benign vs. Malignant Dermoscopic Skin Lesion Image Classification.

In recent decades, the incidence of melanoma has grown rapidly. Hence, early diagnosis is crucial to improving clinical outcomes. Here, we propose and compare a classical image analysis-based machine learning method with a deep learning one to automatically classify benign vs. malignant dermoscopic skin lesion images. The same dataset of 25,122 publicly available dermoscopic images was used to train both models, while a disjointed test set of 200 images was used for the evaluation phase. The training dataset was randomly divided into 10 datasets of 19,932 images to obtain an equal distribution between the two classes. By testing both models on the disjoint set, the deep learning-based method returned accuracy of 85.4 ± 3.2% and specificity of 75.5 ± 7.6%, while the machine learning one showed accuracy and specificity of 73.8 ± 1.1% and 44.5 ± 4.7%, respectively. Although both approaches performed well in the validation phase, the convolutional neural network outperformed the ensemble boosted tree classifier on the disjoint test set, showing better generalization ability. The integration of new melanoma detection algorithms with digital dermoscopic devices could enable a faster screening of the population, improve patient management, and achieve better survival rates.