Search

Background: Several studies have proposed grading systems for risk stratification of early‐stage lung adenocarcinoma based on histological patterns. However, the reproducibility of these systems is poor in clinical practice, indicating the need to develop a new grading system which is easy to apply and has high accuracy in prognostic stratification of patients. Methods: Patients with stage I invasive nonmucinous lung adenocarcinoma were retrospectively collected from pathology archives between 2009 and 2016. The patients were divided into a training and validation set at a 6:4 ratio. Histological features associated with patient outcomes (overall survival [OS] and progression‐free survival [PFS]) identified in the training set were used to construct a new grading system. The newly proposed system was validated using the validation set. Survival differences between subgroups were assessed using the log‐rank test. The prognostic performance of the novel grading system was compared with two previously proposed systems using the concordance index. Results: A total of 539 patients were included in this study. Using a multioutcome decision tree model, four pathological factors, including the presence of tumor spread through air space (STAS) and the percentage of lepidic, micropapillary and solid subtype components, were selected for the proposed grading system. Patients were accordingly classified into three groups: low, medium, and high risk. The high‐risk group showed a 5‐year OS of 52.4% compared to 89.9% and 97.5% in the medium and low‐risk groups, respectively. The 5‐year PFS of patients in the high‐risk group was 38.1% compared to 61.7% and 90.9% in the medium and low‐risk groups, respectively. Similar results were observed in the subgroup analysis. Additionally, our proposed grading system provided superior prognostic stratification compared to the other two systems with a higher concordance index. Conclusion: The newly proposed grading system based on four pathological factors (presence of STAS, and percentage of lepidic, micropapillary, and solid subtypes) exhibits high accuracy and good reproducibility in the prognostic stratification of stage I lung adenocarcinoma patients. [ABSTRACT FROM AUTHOR]

Background: This study aimed to evaluate the cost-effectiveness of a telehealth coaching intervention to prevent gestational diabetes mellitus (GDM) and to calculate the breakeven point of preventing GDM. Methods: Data to inform the economic evaluation model was sourced directly from the large quaternary hospital in Brisbane, where the Living Well during Pregnancy (LWdP) program was implemented, and further supplemented with literature-based estimates where data had not been directly collected in the trial. A cost-effectiveness model was developed using a decision tree framework to estimate the potential for cost savings and quality of life improvement. A total of 1,315 pregnant women (49% with a BMI 25-29.9, and 51% with a BMI ≥ 30) were included in the analyses. Results: The costs of providing routine care and routine care plus LWdP coaching intervention to pregnant women were calculated to be AUD 20,933 and AUD 20,828, respectively. The effectiveness of the LWdP coaching program (0.894 utility) was slightly higher compared to routine care (0.893). Therefore, the value of the incremental cost-effectiveness ratio (ICER) was negative, and it indicates that the LWdP coaching program is a dominant strategy to prevent GDM in pregnant women. We also performed a probabilistic sensitivity analysis using Monte Carlo simulation through 1,000 simulations. The ICE scatter plot showed that the LWdP coaching intervention was dominant over routine care in 93.60% of the trials using a willingness to pay threshold of AUD 50,000. Conclusion: Findings support consideration by healthcare policy and decision makers of telehealth and broad-reach delivery of structured lifestyle interventions during pregnancy to lower short-term costs associated with GDM to the health system. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to evaluate the cost-utility and the budgetary impact of isavuconazole compared to voriconazole in patients with suspected invasive aspergillosis (IA) from the perspective of the Brazilian supplementary health system (SHS). Methods: In this model, a decision tree was developed and included patients with possible IA. Efficacy parameters were extracted from the clinical studies. Drug acquisition, hospitalization costs and adverse events were also collected. Alternative 3- and 10-year time horizon scenarios were used. In addition, deterministic and probabilistic sensitivity analyses were simulated. A budget impact analysis of isavuconazole versus voriconazole was performed, assuming a time horizon of 5 years. In addition, sensitivity analyses were conducted to assess the robustness of the model. Results are reported in Brazilian Real (BRL), year values 2022. Results: The economic analysis of the base case showed that isavuconazole is associated with a saving of 95,174.00 BRL per patient compared to voriconazole. All other simulated scenarios showed that isavuconazole is dominant versus comparators when considering a willingness to pay 40,688.00 BRL/Quality-Adjusted Life Years (QALY). The results were considered robust by the sensitivity analyses. The budget impact analysis showed that the incorporation of isavuconazole generates savings to the SHS, compared to voriconazole, of approximately 20.5 million BRL in the first year. This reaches about 54 million BRL in the fifth incorporation year, considering the market penetration of 20% in the first year, and 50% in the fifth year. Conclusion: Compared with voriconazole, isavuconazole is regarded as a dominant treatment strategy for patients with suspected IA and generates savings for the SHS. [ABSTRACT FROM AUTHOR]

Research has demonstrated concussion likely causes autonomic dysfunction leading to exercise intolerance. To measure improvement in exercise intolerance due to suspected dysautonomia associated with protracted concussion recovery, using objective measurements on a Buffalo Concussion Treadmill Test (BCTT) following participation in a prescribed exercise program. This is a retrospective cohort study of 101 patient charts post-concussion. Exercise intolerance was assessed using a BCTT to identify suspected dysautonomia and an exercise prescription was provided using guidelines for treating concussion-associated exercise intolerance. Patients without symptom improvement and/or inability to achieve 80–85% of age-expected maximum heart rate (HR) without symptom exacerbation received a repeat BCTT. Twelve patient charts met inclusion criteria and were included in data analysis. There were significant improvements from pre-intervention to post-intervention testing in: maximum BCTT stage mean scores (p =.02); maximum HR mean scores (p =.01); prescription HR (RxHR) mean scores (p =.01); and HR delta (HR $$\delta $$ δ) mean scores (p =.00). Maximum stage, HR threshold, RxHR, and newly identified HR delta (HR $$\delta $$ δ) are potential objective measurements of progress for dysautonomia treatment post-concussion. Future studies are indicated to create a tailored protocol in the management of protracted concussion-associated dysautonomia. [ABSTRACT FROM AUTHOR]

Anxiety and stress are common emotional responses for human beings, but their chronic manifestation can lead to physical and psychological illnesses. The advancement of sensing technologies, such as Internet of Things, has contributed to the understanding and assisting events related to anxiety and stress. However, the main challenge is knowing which approaches can be used to better monitor these emotions and assist people. Based on a systematic literature review, this work analyzed studies both to determine how data is collected, and to monitor anxiety and stress levels. Two taxonomies synthesize the techniques mapped. The results indicated more emphasis on studying stress than anxiety and more focus on detecting anxiety and stress levels than on assisting the user. Among the main techniques to collect data, 62.5% of the studies used physiological data like heart data, and for data analysis techniques, 48% of the studies used Decision Trees. [ABSTRACT FROM AUTHOR]

Accurately estimating the prognosis of septic patients on arrival in the emergency department (ED) is clinically challenging. The lactate-to-albumin ratio (LAR) has recently been proposed to improve the predictive performance of septic patients admitted to the ICU. This study aims to assess whether the LAR could be used as an early prognostic marker of 30-day mortality in patients with sepsis in the ED. A prospective observational study was conducted in the ED of the Hospital of Merano. All patients with a diagnosis of sepsis were considered. The LAR was recorded on arrival in the ED. The primary outcome measure was mortality at 30 days. The predictive role of the LAR for mortality was evaluated with the area under the ROC curve, logistic regression adjusted for the Charlson Comorbidity Index value, National Early Warning Score, and Sequential Organ Failure score, and with decision tree analysis. 459 patients were enrolled, of whom 17% (78/459) died at 30 days. The median LAR of the patients who died at 30 days (0.78 [0.45–1.19]) was significantly higher than the median LAR of survivors (0.42 [0.27–0.65]) (p < 0.001). The discriminatory ability of the LAR for death at 30 days was 0.738, higher than that of lactate alone (0.692), and slightly lower than that of albumin alone (0.753). The decision trees confirmed the role of the LAR as an independent risk factor for mortality. The LAR can be used as an index to better predict the 30-day risk of death in septic patients. [ABSTRACT FROM AUTHOR]

Market economies are often characterised by a failure to self-regulate. One of the most enduring of these 'market failures' is the ability to maximise the entrepreneurial potential to generate growth. Within this context, gender remains one of, and probably, the most prevalent dimension of this perceived failure to maximise entrepreneurial potential. Feminist political economy provides a starting point for understanding this reproduction of inequalities via policy interventions that have sought to address perceived market failure. This paper analyses how such gendered inequalities are reproduced. Through the critical assessment of Spain's Emprendetur funding scheme, active from 2012 to 2016, 996 applications were analysed, through a content analysis, applying a gender perspective. The findings, including a decision tree analysis, demonstrate not only that women participate less as applicants in the funding scheme but are also less successful. This can be partly explained because women apply via business typologies that are less successful in relation to the dominance of ICT and technologically informed innovations. However, the barriers extend beyond these typologies; for even when controlling for critical success factors like project size, women are less successful, experiencing a double gender gap, that underlines the need for a gender lens policy approach. [ABSTRACT FROM AUTHOR]

Detecting building rooftops with very high-resolution (VHR) images is an important issue in many fields, including disaster management, urban planning, and climate change research. Buildings with varying geometrical features are challenging to detect accurately from VHR image due to complicated image scenes containing spectrally similar objects, illumination, occlusions, viewing angles, and shadows. This study aims to detect building rooftops with high accuracy using a new framework that includes VHR image, visible band difference vegetation index, digital surface and elevation models, the terrain ruggedness and the topographic position index. Five distinct feature sets were generated in order of importance by exposing the ten related stacking features to a feature selection procedure using the maximum relevance minimum redundancy method. Then, Auto-Encoder, k-NN, decision tree, RUSBoost, and random forest machine learning algorithms were utilized for binary classification. Random forest yielded the highest accuracy (97.2% F-score, 98.72% accuracy) when all features (F10) were used, while decision tree was the least successful (59.16% F-score, 83.56% accuracy) for RGB feature set (FRGB). It was revealed that classification of F10 with random forest increased F-score by about 23% compared to classification with FRGB. Additionally, McNemar's tests showed no statistically significant difference between random forest vs k-NN and decision tree vs RUSBoost. [ABSTRACT FROM AUTHOR]

Purpose: Laryngeal cancer (LC) is the most common head and neck cancer, which often goes undiagnosed due to the inaccessible nature of current diagnosis methods in some parts of the world. Many recent studies have shown that microRNAs (miRNAs) are crucial biomarkers for a variety of cancers. Methods: In this study, we create a decision tree model for the diagnosis of laryngeal cancer using a created series of miRNA attributes, such as sequence-based characteristics, predicted miRNA target genes, and gene pathways. This series of attributes is extracted from both differentially expressed blood-based miRNAs in laryngeal cancer and random, non-associated with cancer miRNAs. Results: Several machine-learning (ML) algorithms were tested in the ML model, and the Hoeffding Tree classifier yields the highest accuracy (86.8%) in miRNAs-based recognition of laryngeal cancer. Furthermore, our model is validated with the independent laryngeal cancer datasets and can accurately diagnose laryngeal cancer with 86% accuracy. We also explored the biological relationships of the attributes used in our model to understand their relationship with cancer proliferation or suppression pathways. Conclusion: Our study demonstrates that the proposed model and an inexpensive miRNA testing strategy have the potential to serve as an additional method for diagnosing laryngeal cancer. [ABSTRACT FROM AUTHOR]

The analysis of gases dissolved in oil is the main technique used to predict possible failures in power transformers. Currently, there are some assessment algorithms for the predictive analysis, but all of them have in common the fact that they are based on the classical gas formation theory. This work aims to analyze the use of decision trees (DTs) for the analysis of gases dissolved in mineral oil, also establishing a relationship associated with decision making during the formation of trees and the formation of gases. In this way, some important aspects involving the insulating mineral oil can be better understood and quantified. For this purpose, one dataset containing 201 samples is used in the study. The results provided by the tree are arranged in a Cartesian plane, and the gases are analyzed based on the ratios used by Doernenburg. DT is discussed in detail to validate the algorithm performance based on the classical gas formation theory. [ABSTRACT FROM AUTHOR]

Machine learning and emergency evacuation prediction share a meaningful association in the context of the Industrial Revolution 4.0 era, given that machine learning can potentially enhance emergency evacuation prediction processes. Machine learning has the potential to revolutionise emergency evacuation prediction by providing a data-driven approach that aids decision-making and response time in emergencies. The complexity of emergency situations can lead to tragic accidents, as individual behaviour heavily influences evacuation time. While some researchers have explored emergency evacuation, existing computer evacuation models lack detailed analysis. To address this gap, this study focuses on reviewing the Random Forest algorithm, an advanced machine learning algorithm based on Decision Trees, in the application of forecasting emergency evacuation time. Through a qualitative research approach using the innovative Hand-searching technique, we conducted a systematic review employing Content Analysis Theory. Multiple sources were examined, including Google Scholar, Science Direct, Scopus, and Universiti Kebangsaan Malaysia e-Journal System. The study's findings shed light on the performance, prediction factors, advantages, and limitations of Random Forest in identifying impacts during an emergency evacuation. These insights hold significant implications for emergency responders, building designers, and policymakers. [ABSTRACT FROM AUTHOR]

Sexually oriented establishments across the United States often pose as massage businesses and force victim workers into a hybrid of sex and labor trafficking, simultaneously harming the legitimate massage industry. Stakeholders with varied goals and approaches to dismantling the illicit massage industry all report the need for multi-source data to clearly and transparently identify the worst offenders and highlight patterns in behaviors. We utilize findings from primary stakeholder interviews with law enforcement, regulatory bodies, legitimate massage practitioners, and subject-matter experts from nonprofit organizations to identify data sources and potential indicators of illicit massage businesses (IMBs). We focus our analysis on data from open sources in Texas and Florida including customer reviews and business data from Yelp.com, the U.S. Census, and GIS files such as truck stop, highway, and military base locations. We build two interpretable prediction models, risk scores and optimal decision trees, to determine the risk that a given massage establishment is an IMB. The proposed multi-source data-based approach and interpretable models can be used by stakeholders at all levels to save time and resources, serve victim-workers, and support well informed regulatory efforts. [ABSTRACT FROM AUTHOR]

The peroxisome proliferator-activated receptor (PPAR) signaling pathway plays a crucial role in systemic cell metabolism, energy homeostasis and immune response inhibition. However, its significance in hepatocellular carcinoma (HCC) has not been well documented. In our study, based on the RNA sequencing data of HCC, consensus clustering analyses were performed to identify PPAR signaling pathway-related molecular subtypes, each of which displaying varying survival probabilities and immune infiltration status. Following, a prognostic prediction model of HCC was developed by using the random survival forest method and Cox regression analysis. Significant difference in survival outcome, immune landscape, drug sensitivity and pathological features were observed between patients with different prognosis. Additionally, decision tree and nomogram models were adopted to optimize the prognostic prediction model. Furthermore, the robustness of the model was verified through single-cell RNA-sequencing data. Collectively, this study systematically elucidated that the PPAR signaling pathway-related prognostic model has good predictive efficacy for patients with HCC. These findings provide valuable insights for further research on personalized treatment approaches for HCC. [ABSTRACT FROM AUTHOR]

AbstractImpurity functions are crucial in decision trees. These functions help determine the impurity level of a node in a decision tree, guiding the splitting criteria. However, two primary ambiguities have surrounded impurity functions: (1) the question of their non negativity and (2) the debate over their concavity. In this paper, we address these uncertainties by delving into the characteristics of impurity functions. We establish that the non negativity of an impurity function is inconsequential. Through counter examples, we disprove the equivalence between an impurity function and a concave function. We identify an impurity function that is not concave and a concave function that is not an impurity function. Interestingly, we find an impurity function that results in a negative impurity reduction. Furthermore, we validate several significant properties of impurity functions. For example, we demonstrate that when an impurity function is concave, the impurity reduction remains nonnegative for multiway divisions. We also discuss the sufficient conditions for a concave function to be an impurity function. Our numerical results further indicate that a positive linear combination of the two most popular impurity functions, namely Gini Index and Entropy, may surpass the individual performance of each when applied to the well-known German credit dataset. [ABSTRACT FROM AUTHOR]

Systematic reviews and meta-analyses typically require significant time and effort. Machine learning models have the potential to enhance screening efficiency in these processes. To effectively evaluate such models, fully labeled datasets—detailing all records screened by humans and their labeling decisions—are imperative. This paper presents the creation of a comprehensive dataset for a systematic review of treatments for Borderline Personality Disorder, as reported by Oud et al. (2018) for running a simulation study. The authors adhered to the PRISMA guidelines and published both the search query and the list of included records, but the complete dataset with all labels was not disclosed. We replicated their search and, facing the absence of initial screening data, introduced a Noisy Label Filter (NLF) procedure using active learning to validate noisy labels. Following the NLF application, no further relevant records were found. A simulation study employing the reconstructed dataset demonstrated that active learning could reduce screening time by 82.30% compared to random reading. The paper discusses potential causes for discrepancies, provides recommendations, and introduces a decision tree to assist in reconstructing datasets for the purpose of running simulation studies. [ABSTRACT FROM AUTHOR]

The conventional method for the color-matching process involves the compounding of polymers with pigments and then preparing plaques by using injection molding before measuring the color by an offline spectrophotometer. If the color fails to meet the L*, a*, and b* standards, the color-matching process must be repeated. In this study, the aim is to develop a machine learning model that is capable of predicting offline color using data from inline color measurements, thereby significantly reducing the time that is required for the color-matching process. The inline color data were measured using an inline process spectrophotometer, while the offline color data were measured using a bench-top spectrophotometer. The results showed that the Bagging with Decision Tree Regression and Random Forest Regression can predict the offline color data with aggregated color differences (dE) of 10.87 and 10.75. Compared to other machine learning methods, Bagging with Decision Tree Regression and Random Forest Regression excel due to their robustness, ability to handle nonlinear relationships, and provision of insights into feature importance. This study offers valuable guidance for achieving Bagging with Decision Tree Regression and Random Forest Regression to correlate inline and offline color data, potentially reducing time and material waste in color matching. Furthermore, it facilitates timely corrections in the event of color discrepancies being observed via inline measurements. [ABSTRACT FROM AUTHOR]

Simple Summary: The distinction between entirely benign and potentially mis-sampled cases presents a notable challenge in the histological examination of transbronchial lung biopsy (TBLB) specimens derived from pulmonary nodules that lack tumor or atypical cells. Such cases are often categorized as non-diagnostic. This study aims to develop a machine learning-based classifier for TBLB specimens, with a specific focus on analyzing the micro-environmental histological reactions present in TBLB and correlating these changes to either benign or malignant status, and to avoid unnecessary sampling procedures and lead to prompt treatment initiation. Background: When obtaining specimens from pulmonary nodules in TBLB, distinguishing between benign samples and mis-sampling from a tumor presents a challenge. Our objective is to develop a machine-learning-based classifier for TBLB specimens. Methods: Three pathologists assessed six pathological findings, including interface bronchitis/bronchiolitis (IB/B), plasma cell infiltration (PLC), eosinophil infiltration (Eo), lymphoid aggregation (Ly), fibroelastosis (FE), and organizing pneumonia (OP), as potential histologic markers to distinguish between benign and malignant conditions. A total of 251 TBLB cases with defined benign and malignant outcomes based on clinical follow-up were collected and a gradient-boosted decision-tree-based machine learning model (XGBoost) was trained and tested on randomly split training and test sets. Results: Five pathological changes showed independent, mild-to-moderate associations (AUC ranging from 0.58 to 0.75) with benign conditions, with IB/B being the strongest predictor. On the other hand, FE emerged to be the sole indicator of malignant conditions with a mild association (AUC = 0.66). Our model was trained on 200 cases and tested on 51 cases, achieving an AUC of 0.78 for the binary classification of benign vs. malignant on the test set. Conclusion: The machine-learning model developed has the potential to distinguish between benign and malignant conditions in TBLB samples excluding the presence or absence of tumor cells, thereby improving diagnostic accuracy and reducing the burden of repeated sampling procedures for patients. [ABSTRACT FROM AUTHOR]

Background: 1-methyladenosine (m1A) is a variant of methyladenosine that holds a methyl substituent in the 1st position having a prominent role in RNA stability and human metabolites. Objective: Traditional approaches, such as mass spectrometry and site-directed mutagenesis, proved to be time-consuming and complicated. Methodology: The present research focused on the identification of m1A sites within RNA sequences using novel feature development mechanisms. The obtained features were used to train the ensemble models, including blending, boosting, and bagging. Independent testing and k-fold cross validation were then performed on the trained ensemble models. Results: The proposed model outperformed the preexisting predictors and revealed optimized scores based on major accuracy metrics. Conclusion: For research purpose, a user-friendly webserver of the proposed model can be accessed through https://taseersuleman-m1a-ensem1.streamlit.app/. [ABSTRACT FROM AUTHOR]

Background: 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. Methods: 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. Results: 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. Conclusion: Nonenhanced CT‐based radiomics provides a promising method for evaluating the efficacy of systemic drug therapy in breast cancer patients with osteolytic bone metastases. [ABSTRACT FROM AUTHOR]

Heart disease is one of the most dangerous diseases in the world. People with these diseases, most of them end up losing their lives. Therefore, machine learning algorithms have proven to be useful in this sense to help decision-making and prediction from the large amount of data generated by the healthcare sector. In this work, we have proposed a novel method that allows increasing the performance of the classical random forest technique so that this technique can be used for the prediction of heart disease with its better performance. We used in this study other classifiers such as classical random forest, support vector machine, decision tree, Naïve Bayes, and XGBoost. This work was done in the heart dataset Cleveland. According to the experimental results, the accuracy of the proposed model is better than that of other classifiers with 83.5%.This study contributed to the optimization of the random forest technique as well as gave solid knowledge of the formation of this technique. [ABSTRACT FROM AUTHOR]

In recent years, rapid technological advancements in artificial intelligence (AI) and the Internet of Things (IoT) have brought significant transformations across various industries and sectors. These advancements have created unprecedented opportunities for leveraging data-driven insights and informed decision-making. Urban populations swiftly adopt information technology solutions to monitor and regulate noise levels and environmental pollutants effectively. This research aims to bridge the traditional gap between environmental science and economics by harnessing cutting-edge AI and IoT technologies. Support vector machine (SVM) is a robust machine learning algorithm known for its ability to decipher complex, non-linear relationships within large and intricate datasets. This study constructs a robust simultaneous equation model by integrating economic indicators, real-time IoT sensor data, and relevant covariates. Mitigate the health risks associated with air pollution and raise awareness of its detrimental impacts. Air pollution continues to pose challenges to intelligent and sustainable healthcare systems. The healthcare ecosystem, coupled with various machine learning techniques, seeks to mitigate pollution's impact and enhance residents' quality of life by offering intelligent services. The analysis of the reciprocal relationship and impact mechanisms between economic development and air pollution is substantiated by empirical data. Formulates an air pollution index using principal component analysis but also develops simultaneous equations that account for spatial effects, urban panel data, and interactions between economic development and air pollution. The experimental results highlight the efficacy of the proposed SVM, achieving an impressive accuracy rate of 84.5%. This performance outstrips alternative methods such as K-Nearest Neighbors, Random Forest, Decision Trees, Logistic Regression, and XGBoost algorithms, reaffirming SVM's prowess in accurately modeling the intricate relationship between economic development and air pollution, particularly when utilizing IoT data. [ABSTRACT FROM AUTHOR]

Sports effect evaluation is the main module of modern information construction. To improve the accuracy of sports effect evaluation and enhance the training level of athletes, this paper aims to conduct in-depth research on sports effect evaluation based on feature selection under the background of big data. Firstly, a sports evaluation system is designed based on the Window Presentation Foundation (WPF) that adopts a Client–Server (C/S) mode. The overall architecture of the system is proposed by expounding the functional modules and the schema of information tables in the database. To assess the impact of sports, the data mining algorithm and big data analytics technique called Random Forest (RF) is used as the core evaluation system. With the help of information gain, feature selection is performed, based on which decision trees are constructed by generating branch nodes. The random forest is created by combining all the decision trees, which helps in improving the generalization. The proposed method is experimentally verified and it is found that the overall stability of the effect evaluation system is good and it effectively improves the efficiency and accuracy of sports effect evaluation, thus enhancing the level of athletes' training. The proposed sports effect evaluation method performs excellently in the experimental validation, as seen by the remarkable F1 Score of 85.32%, average accuracy of 84.28%, precision of 86%, and recall of 82.28%. In comparison, this performs noticeably better than current approaches, proving its improved efficacy in assessing the effects of sports and confirming its ability to improve athlete training proficiency. [ABSTRACT FROM AUTHOR]

Accurately predicting prognosis subcutaneous leiomyosarcoma (LMS) is crucial for guiding treatment decisions in patients. The objective of this study was to develop prediction models for cancer-specific survival (CSS) in patients with subcutaneous LMS. The collected cases of diagnosed subcutaneous LMS were randomly divided into a training cohort and a validation cohort at a 6:4 ratio based on tumor location and histological code. The X-tile program was utilized to determine the optimal cutoff points for age index. Univariate and Cox multivariate regression analyses were conducted to identify independent risk factors for subcutaneous LMS patients. Nomograms were constructed to predict CSS, and their performance was assessed using C-index and calibration plots. Additionally, a decision tree model was established using recursive partitioning analysis to determine the total score for CSS prediction in subcutaneous LMS patients based on the nomogram model. A total of 1793 patients with subcutaneous LMS were found. X-tile software divides all patients into ≤ 61 years old, 61–82 years old, and ≥ 82 years old. The most important anatomical sites were the limbs (including the upper and lower limbs, 48.0%). Only 6.2% of patients received chemotherapy, while 44% had a history of radiotherapy and 92.9% underwent surgery. The independent risk factors for patients with subcutaneous LMS were age, summary stage, grade, and surgery. CSS was significantly decreased in patients with distant metastases, which showed the highest independent risk predictor (HR 4.325, 95% CI 3.010–6.214, p < 0.001). The nomogram prediction model of LMS was constructed based on four risk factors. The C-index for this model was 0.802 [95% CI 0.781–0.823] and 0.798 [95% CI 0.768–0.829]. The training cohort's 3-, 5-, and 10-year AUCs for CSS in patients with subcutaneous LMS were 0.833, 0.830, and 0.859, and the validation cohort's AUC for predicting CSS rate were 0.849, 0.830, and 0.803, respectively. Recursive segmentation analysis divided patients into 4 risk subgroups according to the total score in the nomogram, including low-risk group < 145, intermediate-low-risk group ≥ 145 < 176, intermediate-high-risk group ≥ 176 < 196, and high-risk group ≥ 196; The probability of the four risk subgroups is 9.1%, 34%, 49%, and 79% respectively. In this retrospective study, a novel nomogram or corresponding risk classification system for patients with subcutaneous LMS were developed, which may assist clinicians in identifying high-risk patients and in guiding the clinical decision. [ABSTRACT FROM AUTHOR]

Purpose: This study assessed the influences of different lifestyle on mild cognitive impairment (MCI) progression and established a decision tree prediction model to analyse their predictive significance on MCI progression incidence. Patients and Methods: From October 2015 to February 2020,330 patients with MCI were recruited, and demographic and lifestyle information collected. They were followed up for 19.04 ± 10.227 months. Cognitive function was assessed using the Mini-Mental State Examination Scale every 6 months, and they were divided into MCI stable group and MCI progression group. Results: The Kaplan Meier survival analysis showed an overall cohort survival rate of 33.2%; the annual conversion rate of MCI progression was 20%. Physical exercise, social engagement, high-fat diet, age, napping, and tea drinking were decision tree prediction model nodes. Hobbies were the most important factor for predicting MCI progression. The MCI progression probability rates were: with hobbies 26.829% (44 cases), without hobbies 57.831% (96 cases); for those withot hobbies, with physical exercise 43.077% (28 cases) without physical exercise 72.340% (68 cases); for those without hobbies with physical exercise and social engagement 20.000% (4 cases), without social engagement 53.333% (24 cases); for those without hobbies, physical exercises and social engagement and with nap habits 48.485% (16 cases), without nap habits 66.667% (8 cases). The decision tree prediction model AUC for predicting the MCI progression receiver operating characteristic curve was 0.737 (95% confidence interval: 0.685– 0.785) (75.71% sensitivity, 71.75% specificity, P < 0.001. Conclusion: Hobbies, physical exercise, social engagement, napping, and drinking tea can help prevent MCI progression, while a high-fat diet may exacerbate MCI progression. In this study the rule with the lowest MCI progress probability for those who had hobbies, high-fat diet, and social engagement. And the decision tree model had good prediction efficiency. [ABSTRACT FROM AUTHOR]

Background: Breast cancer (BC) treatment decreases fertility capacity, but unnecessary fertility preservation procedures in women who would not be infertile after treatment would be a waste of time and resources and could cause the unwarranted exposure of cancer cells to exogenous sex hormones. It has been largely shown that post-treatment ovarian reserve is directly associated with pre-treatment anti-mullerian hormone levels (AMH0). A threshold for AMH0, or a model including AMH0 and patient characteristics that could distinguish the patients who will be infertile after treatments, still needs to be defined. Accordingly, this study was performed to specifically target this high-priority concern. Methods: Women ≤ 45 years old with newly diagnosed non-metastatic BC were entered in this multicenter prospective cohort study. AMH0 and two-year post-treatment AMH (AMH2) were measured, and hormonal patient features were recorded as well. Receiver operating characteristic (ROC) curve analysis, decision tree (DT), and random forest analyses were performed to find a cut-off point for AMH0 and define a model involving related features for the prediction of AMH2. Results: The data from 84 patients were analyzed. ROC curve analysis revealed that AMH0 > 3 ng/mL (Area under the curve = 0.69, 95% CI: 0.54-0.84) was the best indicator for predicting AMH2 ≥ 0.7 (sensitivity = 79%, specificity = 60%). The best model detected by DT and random forest for predicting an AMH2 > 0.7 with a probability of 93% consisted of a combination of AMH0 > 3.3, menarche age < 14, and age < 31. Conclusion: This combination model can be used to withhold fertility preservation procedures in BC patients. Performing larger studies is suggested to further test this model. [ABSTRACT FROM AUTHOR]

Peanuts grown in tropical, subtropical, and temperate regions are susceptible to stem rot, which is a soilborne disease caused by Athelia rolfsii. Due to the lack of reliable environmental-based scheduling recommendations, stem rot control relies heavily on fungicides that are applied at predetermined intervals. We conducted inoculated field experiments for six site-years in North Florida to examine the relationship between germination of A. rolfsii sclerotia: the inoculum, stem rot symptom development in the peanut crop, and environmental factors such as soil temperature (ST), soil moisture, relative humidity (RH), precipitation, evapotranspiration, and solar radiation. Window-pane analysis with hourly and daily environmental data for 5- to 28-day periods before each disease assessment were evaluated to select model predictors using correlation analysis, regularized regression, and exhaustive feature selection. Our results indicated that within-canopy ST (at 0.05 m belowground) and RH (at 0.15 m aboveground) were the most important environmental variables that influenced the progress of mycelial activity in susceptible peanut crops. Decision tree analysis resulted in an easy-to-interpret one-variable model (adjusted R2 = 0.51, Akaike information criterion [AIC] = 324, root average square error [RASE] = 14.21) or two-variable model (adjusted R2 = 0.61, AIC = 306, RASE = 10.95) that provided an action threshold for various disease scenarios based on number of hours of canopy RH above 90% and ST between 25 and 35°C in a 14-day window. Coupling an existing preseason risk index for stem rot, such as Peanut Rx, with the environmentally based predictors identified in this study would be a logical next step to optimize stem rot management. [ABSTRACT FROM AUTHOR]

This study develops statistical learning models to assess the probability of undergraduate students graduating within a predetermined period, utilizing admission, performance, and demographic data. The urgency of addressing student attrition is highlighted by recent data from the National Center for Education Statistics (NCES), indicating a 59% completion rate by full-time undergraduates within six years. This research leverages institutional data from a Saudi University, focusing on freshmen enrolled in the 2012-2013 and 2013-2014 academic years, to identify students at risk of dropping out, thereby enabling timely interventions. Ten algorithms, including decision trees, ensemble models, SVM, and ANN, were built and evaluated on a test set representing 33.3% of the entire dataset using precision, recall, accuracy, and Matthews correlation coefficient (MCC). The findings show that SVM and Random Forest models were the most reliable, achieving accuracies of 0.830 and 0.831 respectively, and maintaining balance in precision, recall, and MCC. Conversely, the naïve Bayes model recorded the worst performance. The comparative analysis revealed the superior performance of ensemble models over decision tree models in predicting student attrition, emphasizing the importance of model selection in developing effective early intervention strategies. In addition, our analysis revealed that academic data is a better predictor of ontime graduation than admission data, emphasizing the need for institutions to focus on continuous academic assessment data. [ABSTRACT FROM AUTHOR]

Quarks (except top quarks) and gluons produced in collider experiments hadronize and fragment into sprays of stable particles, called jets. Identification of quark flavor is desired for collider experiments in high-energy physics, relying on flavor tagging algorithms. In this study, using a full simulation of the Circular Electron Positron Collider (CEPC), we investigate the flavor tagging performance of two different algorithms: ParticleNet, based on a Graph Neural Network, and LCFIPlus, based on the Gradient Booted Decision Tree. Compared to LCFIPlus, ParticleNet significantly enhances flavor tagging performance, resulting in a significant improvement in benchmark measurement accuracy, i.e., a 36% improvement for σ (Z H) · B r (Z → ν ν ¯ , H → c c ¯) measurement and a 75% improvement for | V cb | measurement via W boson decay, respectively, when the CEPC operates as a Higgs factory at the center-of-mass energy of 240 GeV and collects an integrated luminosity of 5.6 ab - 1 . We compare the performance of ParticleNet and LCFIPlus at different vertex detector configurations, observing that the inner radius is the most sensitive parameter, followed by material budget and spatial resolution. [ABSTRACT FROM AUTHOR]

In the present study, based on the multivariate nature of images from lung cancer, we extracted autoencoder, reconstruction independent component analysis (RICA) and sparse filters features along with traditional texture and morphological features. The machine learning techniques such as Support Vector Machine (SVM) with Gaussian, radial base function (RBF) and polynomial kernels, decision tree and Naïve Bayes were used classification purpose. The Jackknife 10-fold cross validation (CV) was used for training/testing data formulation and performance was evaluated in terms of sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), total accuracy (TA), false positive rate (FPR) and area under the receiving operating curve (AUC) to distinguish the small cell lung cancer (SCLC) from non-small cell lung cancer (NSCLC) images. The highest detection performance was obtained by extracting RICA and Sparse filters with 100% of sensitivity, specificity, PPV, NPV and TA using SVM with RBF, polynomial kernels and Naïve Bayes followed by Sparse filter with decision tree with TA (99.78%). The highest AUC of 1.00 was obtained by extracting RICA and Sparse filters using decision tree, SVM Gaussian, RBF and polynomial and Naïve Bayes. The results showed the good potential of these methods for lung cancer detection (LCD). [ABSTRACT FROM AUTHOR]

In this paper, "Machine learning" is introduced to motor efficiency optimization control to improve the operating efficiency of the permanent magnet synchronous motors (PMSMs) for pure electric vehicles. A current distribution method based on the gradient boosting decision tree (GBDT) is proposed. The efficiency of the motor operation can be improved by coordinating the current control. First, a mathematical model of the motor efficiency is established, and the current distribution law of the optimal efficiency of the motor in different operating regions is qualitatively analyzed. The control system is based on this current distribution. Second, the sample space is established based on measured data, where the current regression model of the GBDT is introduced. Then by analyzing the importance of characteristic variables, the structure of the model is optimized, and the input and output of the model are reasonably selected, which are embedded into the control system to realize the coordinated control of the current. Finally, comparative experiment shows that the proposed method can improve the efficiency of PMSMs in the whole speed range. [ABSTRACT FROM AUTHOR]

The aim of this study was to predict the subgroups vulnerable to poorer health-related quality of life (HRQoL) according to gender in older adults. Methods: Data from 5,553 Koreans aged 65 or older were extracted from the Korea National Health and Nutrition Examination Survey. HRQoL was assessed using the EQ-5D tool. Complex sample analysis and decision-tree analysis were conducted using SPSS for Windows version 27.0. Results: The mean scores of the EQ-5D index were 0.93 ± 0.00 in men and 0.88 ± 0.00 in women. In men, poorer HRQoL groups were identified with seven different pathways, which were categorized based on participants’ characteristics, such as restriction of activity, perceived health status, muscle exercise, age, relative hand grip strength, suicidal ideation, the number of chronic diseases, body mass index, and income status. Restriction of activity was the most significant predictor of poorer HRQoL in elderly men. In women, the poorer HRQoL groups were identified with nine different pathways, which were categorized based on participants’ characteristics, such as perceived health status, restriction of activity, age, education, unmet medical service needs, anemia, body mass index, relative hand grip, and aerobic exercise. Perceived health status was the most significant predictor of poorer HRQoL in elderly women. Conclusion: This study presents a predictive model of HRQoL in older adults according to gender and can be used to detect individuals at risk of poorer HRQoL. [ABSTRACT FROM AUTHOR]

Background There is no risk and benefit assessment of COVID-19 vaccination for children younger than 5 years using a single health outcomes scale. The objective of this study is to compare the expected risk and benefits of the mRNA primary series of COVID-19 vaccines for children aged 6 months to 4 years in the United States using a single health outcome scale in the Omicron era. Methods The expected benefits and risks of the primary two-dose series of mRNA COVID-19 vaccines for children aged 6 months to 4 years were stratified by sex, the presence of underlying medical conditions, the presence of infection-induced immunity, and the type of mRNA vaccine (BNT162b2 or mRNA-1273). A scoping literature review was conducted to identify the indicators in the decision tree model. The benefit–risk ratio was the outcome of interest. Results The benefit–risk ratios ranged from 200.4 in BNT162b2 for males aged 6–11 months with underlying medical conditions and without infection-induced immunity to 3.2 in mRNA-1273 for females aged 1–4 years without underlying medical conditions and with infection-induced immunity. Conclusions The expected benefit of receiving the primary series of mRNA vaccines outweighed the risk among children ages 6 months to 4 years regardless of sex, presence of underlying medical conditions, presence of infection-induced immunity, or type of mRNA vaccines. However, the continuous monitoring of the COVID-19 epidemiology as well as vaccine effectiveness and safety is important. [ABSTRACT FROM AUTHOR]

Analysis of factors influencing the severity of occupational accidents in manufacturing systems is of vital importance for sustainable manufacturing in a business environment. The aim of this study is to identify occupational health and safety risks in the Turkish textile manufacturing industry, which includes "manufacturing of textiles," "manufacturing of wearing apparel," and "manufacturing of leather and related products". There is no study in the literature that examines the risks related to occupational health and safety in Turkish textile manufacturing based on occupational accident records from 2013 to 2019. To fill this gap in the literature, data-driven modeling is conducted to analyze 139,092 accident records including enterprise information, accident information, injured person information, and accident outcome information, which are obtained from the Ministry of Family, Labor, and Social Services in Türkiye. The result of this study showed that there are 50 injury accident decision rules based on 15 distinct accident predictors, which will support decisions for the efficient use of limited resources, the development of effective accident prevention policies, and the stability of the sector. [ABSTRACT FROM AUTHOR]

Intensity modulation/direct detection (IM/DD) optical interconnect systems are susceptible to waveform distortion caused by complex nonlinearities. To reduce the effect of waveform distortion on signal transmission accuracy, in this paper, a random forest (RF) equalization algorithm based on decision tree (DT) integration is proposed for cost-sensitive IM/DD systems, which has the characteristics of nonlinear classification and regression. The performance of the RF equalizer is verified by simulation experiments on a 120 Gbps 8-level pulse amplitude modulation (PAM8) transmission system using an electro-absorption-modulated laser (EML). Simulation studies show that whether it is a back-to-back (B2B) transmission system or a 10 km optical fiber transmission system, the RF equalization scheme can achieve much better bit error rate (BER) performance than the traditional equalization scheme. In addition, in both transmission cases, the RF equalization scheme enables efficient classification of signals and is much less simpler than the artificial neural network (ANN) equalization scheme. [ABSTRACT FROM AUTHOR]

The smart wearable devices that can track the fitness activities are getting famous these days due to their easy-to-use features. The fitness trackers can work for an individual in a promising manner, provided that the user is well familiar with the device and is committed with the timelines. Several reports have provided evidence that these smart wearable devices have not showed promising results and in most of the cases, people have stopped using them, few weeks after the purchase. There are several reasons linked with this response. During this research, we have worked on the correlations of weight loss via smart device with the age, gender, body mass index (BMI) and ideal body weight (IBW), with the aid of gradient boosted decision trees (XGBoost) and support vector machine (SVM) learning tools. XGBoost and SVM are capable of dealing with complex datasets, with higher frequencies, and for data emerging from multiple sources. These machine learning tools use kernel functions for the clustering and other classification measures, and are thus better as compared to the logistic methods. Next, the time series forecasting tools are discussed with the Bayesian hyperparametric optimization. The time series of the weight loss monitoring of each individual, depicted in this manner, provided complex fractal patterns, with reduction in amplitude, with the passage of time. [ABSTRACT FROM AUTHOR]

Introduction: Well-trained staff is needed to interpret cardiopulmonary exercise tests (CPET). We aimed to examine the accuracy of machine learning–based algorithms to classify exercise limitations and their severity in clinical practice compared with expert consensus using patients presenting at a pulmonary clinic. Methods: This study included 200 historical CPET data sets (48.5% female) of patients older than 40 yr referred for CPET because of unexplained dyspnea, preoperative examination, and evaluation of therapy progress. Data sets were independently rated by experts according to the severity of pulmonary–vascular, mechanical–ventilatory, cardiocirculatory, and muscular limitations using a visual analog scale. Decision trees and random forests analyses were calculated. Results: Mean deviations between experts in the respective limitation categories ranged from 1.0 to 1.1 points (SD, 1.2) before consensus. Random forests identified parameters of particular importance for detecting specific constraints. Central parameters were nadir ventilatory efficiency for CO2, ventilatory efficiency slope for CO2 (pulmonary–vascular limitations); breathing reserve, forced expiratory volume in 1 s, and forced vital capacity (mechanical–ventilatory limitations); and peak oxygen uptake, O2 uptake/work rate slope, and % change of the latter (cardiocirculatory limitations). Thresholds differentiating between different limitation severities were reported. The accuracy of the most accurate decision tree of each category was comparable to expert ratings. Finally, a combined decision tree was created quantifying combined system limitations within one patient. Conclusions: Machine learning–based algorithms may be a viable option to facilitate the interpretation of CPET and identify exercise limitations. Our findings may further support clinical decision making and aid the development of standardized rating instruments. [ABSTRACT FROM AUTHOR]

Embedded system technologies are increasingly being incorporated into manufacturing, smart grid, industrial control systems, and transportation systems. However, the vast majority of today's embedded platforms lack the support of built-in security features which makes such systems highly vulnerable to a wide range of cyber-attacks. Specifically, they are vulnerable to malware injection code that targets the power distribution system of an ARM Cortex-M-based microcontroller chipset (ARM, Cambridge, UK). Through hardware exploitation of the clock-gating distribution system, an attacker is capable of disabling/activating various subsystems on the chip, compromising the reliability of the system during normal operation. This paper proposes the development of an Intrusion Detection System (IDS) capable of detecting clock-gating malware deployed on ARM Cortex-M-based embedded systems. To enhance the robustness and effectiveness of our approach, we fully implemented, tested, and compared six IDSs, each employing different methodologies. These include IDSs based on K-Nearest Classifier, Random Forest, Logistic Regression, Decision Tree, Naive Bayes, and Stochastic Gradient Descent. Each of these IDSs was designed to identify and categorize various variants of clock-gating malware deployed on the system. We have analyzed the performance of these IDSs in terms of detection accuracy against various types of clock-gating malware injection code. Power consumption data collected from the chipset during normal operation and malware code injection attacks were used for models' training and validation. Our simulation results showed that the proposed IDSs, particularly those based on K-Nearest Classifier and Logistic Regression, were capable of achieving high detection rates, with some reaching a detection rate of 0.99. These results underscore the effectiveness of our IDSs in protecting ARM Cortex-M-based embedded systems against clock-gating malware. [ABSTRACT FROM AUTHOR]

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the "interpretability spectrum". The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. It is found that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner. [ABSTRACT FROM AUTHOR]

Class noise is a common issue that affects the performance of classification techniques on real-world data sets. Class noise appears when a class variable in data sets has incorrect class labels. In the case of noisy data, the robustness of classification techniques against noise could be more important than the performance results on noise-free data sets. The decision tree method is one of the most popular techniques for classification tasks. The C4.5, CART, and random forest (RF) algorithms are considered to be three of the most used algorithms in decision trees. The aim of this paper is to reach conclusions on which decision tree algorithm is better to use for building decision trees in terms of its performance and robustness against class noise. In order to achieve this aim, we study and compare the performance of the models when applied to class variables with noise. The results obtained indicate that the RF algorithm is more robust to data sets with noisy class variable than other algorithms. [ABSTRACT FROM AUTHOR]

Learning from high dimensional data has been utilized in various applications such as computational biology, image classification, and finance. Most classical machine learning algorithms fail to give accurate predictions in high dimensional settings due to the enormous feature space. In this article, we present a novel ensemble of classification trees based on weighted random subspaces that aims to adjust the distribution of selection probabilities. In the proposed algorithm base classifiers are built on random feature subspaces in which the probability that influential features will be selected for the next subspace, is updated by incorporating grouping information based on previous classifiers through a weighting function. As an interpretation tool, we show that variable importance measures computed by the new method can identify influential features efficiently. We provide theoretical reasoning for the different elements of the proposed method, and we evaluate the usefulness of the new method based on simulation studies and real data analysis. [ABSTRACT FROM AUTHOR]

Ensemble methods are supervised learning algorithms that provide highly accurate solutions by training many models. Random forest is probably the most widely used in regression and classification problems. It builds decision trees on different samples and takes their majority vote for classification and average in case of regression. However, such an algorithm suffers from a lack of explainability and thus does not allow users to understand how particular decisions are made. To improve on that, we propose a new way of interpreting an ensemble tree structure. Starting from a random forest model, our approach is able to explain graphically the relationship structure between the response variable and predictors. The proposed method appears to be useful in all real-world cases where model interpretation for predictive purposes is crucial. The proposal is evaluated by means of real data sets. [ABSTRACT FROM AUTHOR]

Since there has been concern about food security, accurate prediction of wheat yield prior to harvest is a key component. Random Forest (RF) has been used in many classification and regression applications, such as yield estimation, and the performance of RF has improved by tuning its hyperparameters. In this paper, different changes are made to traditional RF for yield estimation, and the performance of RF is evaluated. Accordingly, RFs constructed using various weak learners, as well as a combined RF consisting of different weak learners are assessed by growing weak Gaussian Process Regression (GPR), Decision Tree (DT), Neural Network (NN), and Stepwise Regression (SW) models in the forest. The input data to DTs are also partitioned into leaves in N (e.g., two) dimensional feature space by using clustering in each parent node. In addition, a subset of the training set is randomly sampled with replacement for training a learner in the forest, instead of randomly sampling the whole training set in traditional RF. Using clustering in DTs added flexibility while utilizing NN as a weak learner yielded the most favorable outcomes in our research. The number of input training samples (Itree) to each tree was also identified as a new hyperparameter to the forest, and the prediction results were more influenced by the Itree compared to the known hyperparameters, such as the number of trees in the forest (ntree) and the number of features for each tree (mtry). [ABSTRACT FROM AUTHOR]

Spam emails pose a substantial cybersecurity danger, necessitating accurate classification to reduce unwanted messages and mitigate risks. This study focuses on enhancing spam email classification accuracy using stacking ensemble machine learning techniques. We trained and tested five classifiers: logistic regression, decision tree, K-nearest neighbors (KNN), Gaussian naive Bayes and AdaBoost. To address overfitting, two distinct datasets of spam emails were aggregated and balanced. Evaluating individual classifiers based on recall, precision and F1 score metrics revealed AdaBoost as the top performer. Considering evolving spam technology and new message types challenging traditional approaches, we propose a stacking method. By combining predictions from multiple base models, the stacking method aims to improve classification accuracy. The results demonstrate superior performance of the stacking method with the highest accuracy (98.8%), recall (98.8%) and F1 score (98.9%) among tested methods. Additional experiments validated our approach by varying dataset sizes and testing different classifier combinations. Our study presents an innovative combination of classifiers that significantly improves accuracy, contributing to the growing body of research on stacking techniques. Moreover, we compare classifier performances using a unique combination of two datasets, highlighting the potential of ensemble techniques, specifically stacking, in enhancing spam email classification accuracy. The implications extend beyond spam classification systems, offering insights applicable to other classification tasks. Continued research on emerging spam techniques is vital to ensure long-term effectiveness. [ABSTRACT FROM AUTHOR]

In this work, we present a blockchain-based secure and flexible distributed privacy-preserving online model that helps in sharing key features of datasets across multiple organizations without violating the privacy of data. In our model, all members are encouraged to participate, discouraged to write fake data. Learning is carried out without sharing of raw data, and data sharing is immutable that improves prediction results of the data held by each member of an industry. We also propose a new consensus algorithm—Proof of Share for adding a valid transaction to the blockchain, thus preventing non participating members from reading any of the data shared by the peer and discouraging fake writes. We evaluated our model on 3, 5, and 10 members setup by applying decision tree, logistic regression, Gaussian naive Bayes, and support vector machine classifiers. The maximum increase of 26.9231 % was observed in accuracy where results of a member's data were taken as baseline. F β (β = 0.5) score increased by 0.4533 and F 1 score by 0.0800. The proposed model to the best of our knowledge is the only one that encourages all members to participate, rather than being passive listeners and discourages a member from forging results thus rendering it suitable for utilization in domains like health care, finance, education, etc. where data are unevenly split and secrecy of data and peers is required. [ABSTRACT FROM AUTHOR]

This paper analyzes the efficiency of various machine learning models (artificial neural networks, random forest, decision tree, AdaBoost and XGBoost) against the evolution of VBA-based (Visual Basic for Applications) malware over a large period of time (1995–2021). The file set used in our research is comprehensive—approximately 1.9 million files (out of which 944,595 are malicious and the rest are benign)—which allowed to gain insights on the resilience of various machine learning models against the diversity and the evolution of file features that reflect obfuscation techniques in VBA-based malware. In studying detection of VBA-based malware, we focus on characteristics of both the classifiers—proactivity (short-term detection efficiency against future malware), endurance (long-term detection robustness)—and of the detection-wise relevant file features—feature perishability (dynamics of feature relevance). We also describe in some detail—as a prerequisite of the study—various obfuscation techniques used by the malware under investigation during the last decade. [ABSTRACT FROM AUTHOR]

Extreme response style (ERS), the tendency of participants to select extreme item categories regardless of the item content, has frequently been found to decrease the validity of Likert-type questionnaire results. For this reason, various item response theory (IRT) models have been proposed to model ERS and correct for it. Comparisons of these models are however rare in the literature, especially in the context of cross-cultural comparisons, where ERS is even more relevant due to cultural differences between groups. To remedy this issue, the current article examines two frequently used IRT models that can be estimated using standard software: a multidimensional nominal response model (MNRM) and a IRTree model. Studying conceptual differences between these models reveals that they differ substantially in their conceptualization of ERS. These differences result in different category probabilities between the models. To evaluate the impact of these differences in a multigroup context, a simulation study is conducted. Our results show that when the groups differ in their average ERS, the IRTree model and MNRM can drastically differ in their conclusions about the size and presence of differences in the substantive trait between these groups. An empirical example is given and implications for the future use of both models and the conceptualization of ERS are discussed. [ABSTRACT FROM AUTHOR]

One of the most common attacks is man‐in‐the‐middle (MitM) which, due to its complex behaviour, is difficult to detect by traditional cyber‐attack detection systems. MitM attacks on internet of things systems take advantage of special features of the protocols and cause system disruptions, making them invisible to legitimate elements. In this work, an intrusion detection system (IDS), where intelligent models can be deployed, is the approach to detect this type of attack considering network alterations. Therefore, this paper presents a novel method to develop the intelligent model used by the IDS, being this method based on a hybrid process. The first stage of the process implements a feature extraction method, while the second one applies different supervised classification techniques, both over a message queuing telemetry transport (MQTT) dataset compiled by authors in previous works. The contribution shows excellent performance for any compared classification methods. Likewise, the best results are obtained using the method with the highest computational cost. Thanks to this, a functional IDS will be able to prevent MQTT attacks. [ABSTRACT FROM AUTHOR]

Improving health literacy through health information dissemination is one of the most economical and effective mechanisms for improving population health. This process needs to fully accommodate the thematic suitability of health information supply and demand and reduce the impact of information overload and supply–demand mismatch on the enthusiasm of health information acquisition. We propose a health information topic modeling analysis framework that integrates deep learning methods and clustering techniques to model the supply‐side and demand‐side topics of health information and to quantify the thematic alignment of supply and demand. To validate the effectiveness of the framework, we have conducted an empirical analysis on a dataset with 90,418 pieces of textual data from two prominent social networking platforms. The results show that the supply of health information in general has not yet met the demand, the demand for health information has not yet been met to a considerable extent, especially for disease‐related topics, and there is clear inconsistency between the supply and demand sides for the same health topics. Public health policy‐making departments and content producers can adjust their information selection and dissemination strategies according to the distribution of identified health topics, thereby improving the effectiveness of public health information dissemination. [ABSTRACT FROM AUTHOR]

Background: Patient safety incidents lead to performance difficulties for nurses when providing nursing practice. This affects work-life balance and causes second and third-victimization. This study predicts factors affecting clinical nurses' work-life balance due to patient safety incidents using classification and regression tree analysis techniques. Methods: This study was a secondary analysis of data from a cohort research project, which used a descriptive survey for data collection. Participants comprised 372 nurses. Data were collected using SurveyMonkey, a mobile-based survey software solution, from January to September 2021. Data included the general characteristics of clinical nurses, second damage, second damage support, third damage, and work-life balance. The specific variables included in the analysis chosen through rigorous Lasso analysis form the foundation for predicting work-life balance. Variables with low explanatory power were excluded, thereafter, the variables selected by Lasso were analyzed with a classification and regression tree model to predict work-life balance. Results: A regression tree was applied to predict work-life balance using seven variables—education level, marital status, position, physical distress, second-victim support, turnover intentions, and absenteeism (selected through Lasso analysis). After pruning, at tree size four, when turnover intentions were < 4.250, physical distress < 2.875, and second-victim support < 2.345, the predicted work-life balance was 3.972. However, when turnover intentions were < 4.250, physical distress < 2.875, and second-victim support ≥ 2.345, then the predicted work-life balance was 2.760. Conclusions: This study's insights offer crucial groundwork for crafting targeted workforce risk management strategies and fostering a conducive organizational culture to mitigate nursing occupational stress, potentially curbing the recurrence of patient safety incidents and improving nursing practice while enhancing patient outcomes. Future research should explore second and third victim experiences across various healthcare settings globally to understand their impact on WLB and patient safety outcomes. [ABSTRACT FROM AUTHOR]

PURPOSE: In artificial intelligence–based modeling, working with a limited number of patient groups is challenging. This retrospective study aimed to evaluate whether applying synthetic data generation methods to the clinical data of small patient groups can enhance the performance of prediction models. MATERIALS AND METHODS: A data set collected by the Cancer Registry Library Project from the Yonsei Cancer Center (YCC), Severance Hospital, between January 2008 and October 2020 was reviewed. Patients with colorectal cancer younger than 50 years who started their initial treatment at YCC were included. A Bayesian network–based synthesizing model was used to generate a synthetic data set, combined with the differential privacy (DP) method. RESULTS: A synthetic population of 5,005 was generated from a data set of 1,253 patients with 93 clinical features. The Hellinger distance and correlation difference metric were below 0.3 and 0.5, respectively, indicating no statistical difference. The overall survival by disease stage did not differ between the synthetic and original populations. Training with the synthetic data and validating with the original data showed the highest performances of 0.850, 0.836, and 0.790 for the Decision Tree, Random Forest, and XGBoost models, respectively. Comparison of synthetic data sets with different epsilon parameters from the original data sets showed improved performance >0.1%. For extremely small data sets, models using synthetic data outperformed those using only original data sets. The reidentification risk measures demonstrated that the epsilons between 0.1 and 100 fell below the baseline, indicating a preserved privacy state. CONCLUSION: The synthetic data generation approach enhances predictive modeling performance by maintaining statistical and clinical integrity, and simultaneously reduces privacy risks through the application of DP techniques. Synthetic oncology data with differential privacy enhance survival status prediction AI, ensuring data privacy. [ABSTRACT FROM AUTHOR]