Decision Tree Methodology Research Articles

Comparison between statistical and machine learning methods to detect the hematological indices with the greatest influence on elevated serum levels of low-density lipoprotein cholesterol

IntroductionElevated levels of low-density lipoprotein-cholesterol (LDL-C) is a significant risk factor for the development of cardiovascular diseases (CVD)s. Furthermore, studies have revealed an association between indices of the complete blood count (CBC) and dyslipidemia. We aimed to investigate the relationship between CBC parameters and serum levels of LDL. MethodIn a prospective study involving 9704 participants aged 35–65 years, comprehensive screening was conducted to estimate LDL-C levels and CBC indicators. The association between these biomarkers and high LDL-C (LDL-C≥130 mg/dL (3.25 mmol/L)) was investigated using various analytical methods, including Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Neural Network (NN), and Support Vector Machine (SVM) methodologies. ResultThe present study found that age, hemoglobin (HGB), hematocrit (HCT), platelet count (PLT), lymphocyte (LYM), PLT-LYM ratio (PLR), PLT-High-Density Lipoprotein (HDL) ratio (PHR), HGB-LYM ratio (HLR), red blood cell count (RBC), Neutrophil-HDL ratio (NHR), and PLT-RBC ratio (PRR) were all statistically significant between the two groups (p<0.05). Another important finding was that red cell distribution width (RDW) was a significant predictor for higher LDL levels in women. Furthermore, in men, RDW-PLT ratio (RPR) and PHR were the most important indicators for assessing the elevated LDL levels. ConclusionThe study found that sex increases LDL-C odds in females by 52.9 %, while age and HCT increase it by 4.1 % and 5.5 %, respectively. RPR and PHR were the most influential variables for both genders. Elevated RPR and PHR were negatively correlated with increased LDL levels in men, and RDW levels was a statistically significant factor for women. Moreover, RDW was a significant factor in women for high levels of HDL-C.The study revealed that females have higher LDL-C levels (16 % compared to 14 % of males), with significant differences across variables like age, HGB, HCT, PLT, RLR, PHR, RBC, LYM, NHR, RPR, and key factors like RDW and SII.

Rethinking the prognosis model of differentiated thyroid carcinoma.

The prediction efficiency of long-term cancer-specific survival (CSS) in guiding the treatment of differentiated thyroid carcinoma (DTC) patients is still unsatisfactory. We need to refine the system so that it more accurately correlates with survival. This is a retrospective study using the Surveillance, Epidemiology, and End Results (SEER) database, and included patients who underwent surgical treatment and were diagnosed with DTC from 2004 to 2020. Patients were divided into a training cohort (2004-2015) and validation cohort (2016-2020). Decision tree methodology was used to build the model in the training cohort. The newly identified groups were verified in the validation cohort. DTC patient totals of 52,917 and 48,896 were included in the training and validation cohorts, respectively. Decision tree classification of DTC patients consisted of five categorical variables, which in order of importance were as follows: M categories, age, extrathyroidal extension, tumor size, and N categories. Then, we identified five TNM groups with similar within-group CSS. More patients were classified as stage I, and the number of stage IV patients decreased significantly. The new system had a higher proportion of variance explained (PVE) (5.04%) and lower Akaike information criterion (AIC) (18,331.906) than the 8th TNM staging system (a PVE of 4.11% and AIC of 18,692.282). In the validation cohort, the new system also showed better discrimination for survival. The new system for DTC appeared to be more accurate in distinguishing stages according to the risk of mortality and provided more accurate risk stratifications and potential treatment selections.

Implementation of Decision Tree Method to Predict Customer Interest in Internet Data Packages

The use of smartphones is on the rise, making internet packages vital in everyday life. In Indonesia, mobile operators offer a variety of data packages to meet customer needs. Understanding preferences is important to making the right decisions when providing products that meet customer needs. However, not all packages are suitable for all customers. Telkomsel is one of the providers that can deliver consistent signals and a wide range of data packages, but it still has a relatively high price. The study uses decision tree methodology to analyze citizens' preferences about Telkomsel services, comparing the relative cost of data packages with other services. This research will use surveys with samples from different communities to determine the representativeness of the results and provide strategic recommendations for Telkomsel to improve customer satisfaction. The research methods employed in this study included data collection, preprocessing, data division, model design, prediction results, and result evaluation. The results showed accuracy levels of 98.7%, precision of 100%, recall of 98.7%, specificity of 100%, and an F1-score of 99.3%. This study demonstrates the effectiveness of the decision tree model in predicting customer interest in Telkomsel services. Despite some limitations, the findings provide valuable insights that Telkomsel can use to develop more effective marketing strategies.

Predictive modeling of spring-back in pre-punched sheet roll forming using machine learning

This study outlines an experimental and computational endeavor aimed at developing a machine learning model to estimate spring-back values utilizing the decision tree methodology. A design of experiment approach was employed to collect a dataset, and based on the experimental results, a precise model was constructed to predict spring-back values. The model considered parameters such as thickness, diameter of circle hole, distance between the center hole and flange edge, and hole spacing. Various hyper parameters, including max depth and minimum samples for split, were explored, with configurations such as (30,5), (20,8), and (10,2) being evaluated to identify the optimal model for spring-back prediction. Analysis of the results demonstrated that the decision tree models accurately estimated spring-back values in cold roll forming of pre-punched sheets based on the input parameters. The coefficient of determination in the test section for decision tree models with parameters (30,5), (20,8), and (10,2) was found to be 0.90, 0.98, and 0.96, respectively. Additionally, the percentage of absolute error in the test section for the same decision tree models was calculated as 8.84%, 6.18%, and 7.6%, respectively.

Effect of street trees shade on perceived thermal comfort in a south temperate climate: The sidewalks of Montevideo (Uruguay)

The use of vegetation in cities is one of the most promising strategies for urban climate change adaptation and mitigation. Tree shade influences heat storage from surfaces reducing long wave radiation emission which directly affects people. People 's heat perception depends more on insolation and the temperature of surrounding objects than on air temperature itself. There is a need for analyzes that include the combined effects of physical and human variables on thermal comfort, as well as location-based studies to address its climatic and social conditions. In order to compare the effect of the trees on microenvironmental temperature and perceived thermal comfort, we measured physical parameters and performed structured interviews on three downtown streets of Montevideo, Uruguay, which had sections with and without trees on four dates during the summer. Generally, people surveyed under both treatments stated they did not feel fully comfortable due to summer heat, but the proportion of people who stated feeling in thermal comfort under tree shade was more than double than the unshaded sections.The seasonal ARIMA analysis supported that the tree shade reduced the microenvironmental temperature by its effect on radiant temperature. By using a statistical decision tree methodology that combines all the variables in the same analysis, we found a greater impact of physical variables than personal variables on people's thermal comfort and thermal preferences. We also identified gender as a significant variable that affects people's thermal preferences, where 46.4 % of females preferred a slightly colder environment.

Reliable arrival time picking of acoustic emission using ensemble machine learning models

This study presents an innovative method for accurately picking the first-wave arrival time in acoustic emission (AE) localization, particularly effective in environments with low or variable signal-to-noise ratios (SNR). Utilizing an ensemble learning model, it synergizes multiple automatic arrival time estimation algorithms to enhance both consistency and robustness. The model, rooted in decision tree methodologies, integrates a variety of techniques, including Akaike information criterion (AIC), improved AIC, Hinkley, energy ratios, and wavelet transformation-based binary map. Its efficacy is demonstrated through testing on 549 manually annotated AE datasets, where the model’s predictions were benchmarked against manual picks, showcasing superior accuracy and robustness in AE event source localization. Evaluations of the model’s performance across various ensemble machine learning models highlighted its ability to significantly diminish localization errors, achieving an average absolute error of less than 1.5 mm. The study also delved into the impact of base pickers and the size of the training dataset on the model’s predictions. Findings indicated consistent performance across different decision tree models, with the accuracy of base pickers and training set size playing a significant role in outcomes. This research culminates in a decision tree-based ensemble machine learning solution that effectively estimates AE first-wave arrival times with high accuracy and robustness, even amidst fluctuating SNR conditions. Its adaptability and interpretability greatly reduce source localization errors in practical AE monitoring, effectively overcoming challenges associated with imprecise arrival time picking.

DETERMINANTS AND CLASSIFICATIONS OF ONLINE SHOPPING CONSUMERS’ PURCHASE INTENTION IN INDONESIA

Online shopping is still growing significantly, which is an upward trend for e-commerce platforms. It has grown in popularity among consumers for a number of reasons, driving Indonesian consumer behavior. This study aims to identify determinants and classifications of Indonesian online shopping consumers’ purchase intention using the decision tree methodology. The notion underpinning this study is the phenomena of online shopping as a consumer behavior transition in Indonesia which has increased gradually over the last decades. The data was collected using a structured questionnaire and 820 respondents participated in this study. Then, the data was analyzed using C5.0 and CART 5.0 algorithms. The results show that the most influential determinants of the frequency of online shopping include the consumers’ occupation, choice of e-commerce platforms, product origin, and product quality. The influence of several factors on customers' intentions to engage in shopping online can be determined, including job status, e-commerce platform, product sources, and product quality.JEL: L81, L86, Q5.

Student well-being and mathematical literacy performance in PISA 2018: a machine-learning approach

One of the goals of the educational system is to promote the well-being of students due to its associated on their academic performance. This research aims to shed light on the main role of well-being variables (introduced by PISA 2018 for the first time, as far as our knowledge) in the mathematical competence throughout of the PISA 2018 evaluation with a sample of 35,943 Spanish students. Students ranged in age from 15 to 16 years old (SD = 0.288). Supervised learning techniques such as decision tree methodology, random forest, and a linear hierarchical model have been used throughout this study. The criterion variable was competency performance in mathematics, while the independent variables consisted of a total of 83 items extracted from the student well-being questionnaire. These predictors are grouped into five domains: physical, psychological, material, cognitive and social. We have proved that well-being plays an important role in mathematical understanding in PISA 2018. Specifically, social well-being is the most important variable in our study. To conclude, we observe that social well-being, contextualised in terms of the relationships that the students maintain with their teachers, peers and families, plays a detrimental role in mathematics achievement.

Unveiling IoT Customer Behaviour: Segmentation and Insights for Enhanced IoT-CRM Strategies: A Real Case Study.

In today's competitive landscape, achieving customer-centricity is paramount for the sustainable growth and success of organisations. This research is dedicated to understanding customer preferences in the context of the Internet of things (IoT) and employs a two-part modeling approach tailored to this digital era. In the first phase, we leverage the power of the self-organizing map (SOM) algorithm to segment IoT customers based on their connected device usage patterns. This segmentation approach reveals three distinct customer clusters, with the second cluster demonstrating the highest propensity for IoT device adoption and usage. In the second phase, we introduce a robust decision tree methodology designed to prioritize various factors influencing customer satisfaction in the IoT ecosystem. We employ the classification and regression tree (CART) technique to analyze 17 key questions that assess the significance of factors impacting IoT device purchase decisions. By aligning these factors with the identified IoT customer clusters, we gain profound insights into customer behaviour and preferences in the rapidly evolving world of connected devices. This comprehensive analysis delves into the factors contributing to customer retention in the IoT space, with a strong emphasis on crafting logical marketing strategies, enhancing customer satisfaction, and fostering customer loyalty in the digital realm. Our research methodology involves surveys and questionnaires distributed to 207 IoT users, categorizing them into three distinct IoT customer groups. Leveraging analytical statistical methods, regression analysis, and IoT-specific tools and software, this study rigorously evaluates the factors influencing IoT device purchases. Importantly, this approach not only effectively clusters the IoT customer relationship management (IoT-CRM) dataset but also provides valuable visualisations that are essential for understanding the complex dynamics of the IoT customer landscape. Our findings underscore the critical role of logical marketing strategies, customer satisfaction, and customer loyalty in enhancing customer retention in the IoT era. This research offers a significant contribution to businesses seeking to optimize their IoT-CRM strategies and capitalize on the opportunities presented by the IoT ecosystem.

Adapting the Planetary Health Diet Index for children and adolescents

BackgroundTools for measuring adherence to sustainable healthy diets among children and adolescents are lacking.ObjectiveTo advance methods for measuring adherence to sustainable healthy diets among children and adolescents by adapting an existing index, compare scores obtained using the original and adapted versions of the index in a sample of Chilean children, and describe the adapted index association with diet characteristics.MethodsThe Planetary Health Diet Index (PHDI) was adapted to better reflect children's and adolescents’ nutritional requirements. The adapted index (PHDI-C) comprises 16 components with a maximum score of 150 points. PHDI-C was piloted among a sample of 958 Chilean children (3–6 years) using dietary data collected in 2016 through single 24-h recalls. A decision tree and food disaggregation methodology were developed to guide the calculation of scores. Scores obtained using the original and adapted versions of the index were compared. Linear regression models adjusted by child’s gender and age were fitted to explore associations between total PHDI-C score, dietary recall characteristics and nutritional composition of children’s diets.ResultsPHDI accounted for 75.7% of children’s total caloric intake, whereas PHDI-C accounted for 99.6%. PHDI & PHCI-C scores were low among this sample of children; however, mean total score was lower when using PHDI compared to PHDI-C [40.7(12.1) vs 50.1(14.6)]. Children’s scores were very low for nuts & peanuts, legumes, dark green vegetables, whole cereals, tubers & potatoes, and added sugars components across both indices, but were higher for dairy products and eggs & white meats components when using the PHDI-C due to adjustments made to ensure nutritional adequacy. Mean total PHDI-C score was significantly lower on weekends and special occasions, and significantly higher when children reported having a special diet (e.g., vegetarian). Total PHDI-C score was negatively associated with total sugars, saturated fats, trans fats, and animal-based protein intake, and positively associated with total protein, plant-based protein, total carbohydrates, and total fibre intake.ConclusionsThis study provides a replicable method for measuring adherence to sustainable healthy diets among children and adolescents that can be used to monitor trends and measure the effectiveness of actions targeting improving children’s diets.

Marathi text summarization through NLP and deep learning mechanism

&lt;p&gt;Every day, an ever-increasing amount of people gain access to the internet platform. This has proven to be efficient in creating cost-effective internet platform deployments and applications. The growth in the amount of people using the platform has resulted in a rise in the quantity of information accessible on the internet in the form of news, media, and other forms of communication. This causes evaluating and comprehending a significant amount of textual information a very challenging task. For the objective of generating textual summaries for Marathi texts, an effective and trustworthy approach is required. Through the use of machine learning methods, a successful strategy for extracting summary for the Marathi text has been generated for this objective. To obtain the Marathi text summary, the proposed method uses feature extraction as well as deep belief networks and decision tree methodologies. The experimentation was carried out on the performance of the Term Frequency-Inverse Document Frequency (TF-IDF) in the stopword elimination procedure, along with the evaluation of the summarization outcome which achieves a Mean Absolute Error (MAE) of 2.8 for the stopword removal approach through TF-IDF technique and a precision of 95.49% with an accuracy of 92.76%.&lt;/p&gt;

An Empirical Investigation of the Reasons of Financial Needs and Preference of Islamic Banking Customers in Türkiye

Many interest-free financial organs are operating in a similar system all over the world, especially in Muslim countries. Islamic banks are banks that operate in the financial sector, support the real economy, and offer banking services. Islamic banks collect funds from savers, make them available in industry and trade sectors according to interest-free financing ethics and share profit or loss with savers. Alternative financing systems are one of the issues discussed in recent years to reduce the problems arising from the traditional banking system, which has become controversial especially with the recent crises. One of these alternatives is Islamic finance practices. As in all the world, the rising market share in Türkiye is increasing interest in the bank. This study aims to guide banks in product development by using data mining techniques in Islamic banking in terms of being a service enterprise. For this purpose, a face-to-face survey was conducted with 212 customers registered at 5 branches of an Islamic bank. In the study in which decision tree methodology is conducted, the satisfaction, needs, and expectations of the bank are determined according to the different characteristics of the customers (socio-economic factors, financial and Islamic literacy levels etc.). From this point of view, product and policy development suggestions were brought to Islamic banks according to customer characteristics.

A new echocardiographic index to select patients for PFO suture-mediated percutaneous closure.

To identify a simple echocardiographic predictor of procedural success to select patient for percutaneous suture-mediated patent fossa ovalis (PFO) closure. Percutaneous suture-mediated PFO closure has been shown as a safe and advantageous alternative to device-based PFO closure, yet its overall success is slightly lower in unselected patients. Preprocedural transesophageal echocardiogram (TEE) of 302 patients (113 men, 45 ± 12 years) who underwent percutaneous suture-mediated PFO closure were reviewed. At echocardiographic follow-up (3-6 months), residual right-to-left shunt(RLS) ≥2 was found in 60 (19.9%) patients. At multivariable analysis, only two anatomical variables measured at preprocedural TEE were found as independent predictors of residual RLS ≥ 2 at follow-up: PFO maximum width(odds ratio[OR] 1.89, 95% confidence interval [CI] 1.16-3.40, p = 0.02) and PFO minimal septa overlapping (OR 0.58, 95% CI 0.35-0.88, p = 0.02). An index based on the ratio of PFO maximum width to PFO minimum septal overlapping (W/SO) proved to be the most powerful predictor of RLS ≥ 2 at follow-up (OR 48.1, 95% CI 9.3-352.2, p < 0.01). The ROC curve for the W/SO ratio was found to have an AUC of 0.84 (95% CI 0.75-0.93) and a cut-off value of 0.61 yielding a sensitivity of 80% and specificity of 78% with a negative predictive value of 94%. A decision tree methodology's AUC was 0.75 (95% CI 0.67-0.83). The results of this study indicate that the ratio between the maximum amplitude of the PFO and the minimum overlap of the septa is the best predictive index of a favorable result by using one stitch only.

The influence of Slovak consumer lifestyle on purchasing behaviour in the consumption of organic food

PurposeHealth is an essential issue in the motivation to eat organic food. The aim of the study is to investigate the relationship if people who have a positive view of a healthy lifestyle (want to live healthy) have an influence on the tendency to buy organic food.Design/methodology/approachThe analysis of secondary data dealing with the issue was supplemented by primary data. In order to meet the main aim, a preliminary objective was set which was to determine the influence of socio-demographic factors on the recommended lifestyle. Specifically, the largest statistically significant difference in influence on healthy lifestyle was gender, followed by education and age. The survey was conducted in the period of January–May 2019 on a sample of 1,373 respondents from Slovakia.FindingsThe data was evaluated by means of selected specific statistical methods (Kruskal–Wallis test, Man-Whitney test and Decision tree methodology). The results of the research verified that the lifestyle of Slovak consumers has an influence on the consumption of organic products and that people who practise healthy eating buy organic food more often. Our research has shown that lifestyle is increasingly influencing consumer purchasing behaviour.Originality/valueThe results showed that today's healthy lifestyle increases the demand for healthy food among potential consumers. Furthermore, the presented results of our research in Slovakia could establish some basis for conducting similar research in other European countries.

Statistical analysis of various splitting criteria for decision trees

Decision trees are frequently used to overcome classification problems in the fields of data mining and machine learning, owing to their many perks, including their clear and simple architecture, excellent quality, and resilience. Various decision tree algorithms are developed using a variety of attribute selection criteria, following the top-down partitioning strategy. However, their effectiveness is influenced by the choice of the splitting method. Therefore, in this work, six decision tree algorithms that are based on six different attribute evaluation metrics are gathered in order to compare their performances. The choice of the decision trees that will be compared is done based on four different categories of the splitting criteria that are criteria based on information theory, criteria based on distance, statistical-based criteria, and other splitting criteria. These approaches include iterative dichotomizer 3 (first category), C[Formula: see text] (first category), classification and regression trees (second category), Pearson’s correlation coefficient based decision tree (third category), dispersion ratio (third category), and feature weight based decision tree algorithm (last category). On eleven data sets, the six procedures are assessed in terms of classification accuracy, tree depth, leaf nodes, and tree construction time. Furthermore, the Friedman and post hoc Nemenyi tests are used to examine the results that were obtained. The results of these two tests indicate that the iterative dichotomizer 3 and classification and regression trees decision tree methods perform better than the other decision tree methodologies.

Factors Determining Child Custody in Taiwan after Patriarchy's Decline: Decision Tree Analysis on Family Court Decisions

AbstractThe doctrine of ‘best interests of the child’ has guided courts in determining post-divorce child custody cases in Taiwan since 1996 amendments to the Civil Code. Amended Article 1055-1 requires judges to consider factors such as ‘the age, sex, and wishes of the child’ and ‘the age, occupation, character, health condition, economic condition, and lifestyle of the parents.’ However, previous studies have not clarified which factors judges consider primary. This article collects Taiwanese family court decisions from 2012 to 2017, involving 1,126 children whose parents were both Taiwanese and who both sought to acquire custody, in which Taiwanese district courts granted sole custody to the husband or wife. The article employs decision tree methodology, a commonly used machine learning technology. The article concludes that the three most significant factors considered by Taiwanese judges are first, which parent is the child's current primary caregiver, followed by the wishes of the child and the judge's assessment of parent-child interaction. This result runs counter to widely held beliefs that parental gender and parents’ occupations and economic resources are still prime factors in judges’ contemplation. Decision tree learning, we suggest, can assist parents’ and lawyers’ case evaluations and speed up extrajudicial custody determination arrangements.

Biomarkers estimating baseline mortality risk for neonatal sepsis: nPERSEVERE: neonate-specific sepsis biomarker risk model.

Prognostic biomarker research neonatal sepsis is lacking. We assessed the utility of a validated pediatric prognostic tool called PERSEVERE II that uses decision tree methodology to predict mortality at discharge in neonates who experienced sepsis. Prospective study in a dual-center cohort of neonates with sepsis admitted between June 2020 and December 2021. Biomarker analysis was done on serum samples obtained at the time of evaluation for the event. In a cohort of 59 neonates with a mortality rate of 15.3%, PERSEVERE II was 67% sensitive and 59% specific for mortality, p 0.27. Amongst PERSEVERE II biomarkers, IL-8 showed good prognostic performance for mortality prediction with a cutoff of 300 pg/mL (sensitivity 100%, specificity 65%, negative predictive value 100%, AUC 0.87, p 0.0003). We derived a new decision tree that is neonate specific (nPERSEVERE) with improved performance compared to IL-8 (sensitivity 100%, specificity 86%, negative predictive value 100%, AUC 0.95, p < 0.0001). IL-8 and nPERSEVERE demonstrated good prognostic performance in a small cohort of neonates with sepsis. Moving toward precision medicine in sepsis, our study proposes an important tool for clinical trial prognostic enrichment that needs to be validated in larger studies. Prognostic and predictive biomarker research is lacking in the newborn intensive care unit. Biomarkers can be used at the time of evaluation for neonatal sepsis (blood culture acquisition) to identify neonates with high baseline mortality risk. Stratification is an important step toward precision medicine in neonatal sepsis.

Risk Stratification of Diffuse Large B-Cell Lymphoma Based on Cell Surface Markers Using Flow Cytometry

Background: Diffuse large B-cell lymphoma (DLBCL) is the most common subtype of malignant lymphoma. Approximately 80% of patients with DLBCL can achieve remission with chemotherapy. However, the prognosis of relapsed and refractory patients is poor. The International Prognostic Index (IPI) is the most widely used prognostic score for non-Hodgkin lymphoma, but it cannot accurately identify a high-risk population for DLBCL. Although gene expression profiles and genomic classifications are other useful tools for predicting outcomes, they are rarely performed in clinical practice. Some antigens, such as CD5 and CD43, have been reported to negatively predict the outcome of DLBCL, while expression of CD10 may have a better prognosis. Most previous studies have been based on immunohistochemistry, in which discordant judgment may occur. Using multicolor flow cytometry, the expression of antigens on lymphoma cells can undoubtedly be documented and surface markers and their combinations may be able to predict prognosis. The present study aimed to develop a new predictive model based on cell surface markers expressed on DLBCL cells. Methods: Baseline cell surface markers data of the newly diagnosed DLBCL patients enrolled in the present study were analyzed by flow cytometry. The expressions of CD5, CD10, CD19, CD20, CD21, CD22, CD23, CD25, CD38, CD40, CD43, CD44, CD200, and HLA-DR, which are routinely analyzed at our hospital, were obtained for all patients. As the primary endpoint was to determine the 2-year progression-free survival rate (PFS), we applied a decision tree methodology to define which of the abovementioned markers were significant clinical predictors of PFS and established a new cell surface marker-based prognostic score. Based on this analysis, we stratified the patients into good, intermediate, and poor prognosis groups. Survival outcomes for the three groups were estimated using the Kaplan-Meier method and the hazard ratio (HR) and 95% confidence interval (CI) from multivariate Cox regression, considering IPI as a covariate. In addition, the sensitivity and specificity of the new score combined with the IPI score was compared to that of the IPI score alone using the area under the curve (AUC) of receiver operating characteristic (ROC) curves. Results: A total of 139 patients with DLBCL were included. The median age at diagnosis was 71 years (range 33-97), and 53% of the patients were male. Regarding IPI scores, 28 patients were in the low-risk group, 28 in the low-intermediate-risk group, 37 in the high-intermediate-risk group, and 46 in the high-risk group. The decision tree method indicated CD5, CD10, CD21, CD43, and HLA-DR as significant predictive variables for 2-year PFS (Figure 1A). The good (51 patients), intermediate (33 patients), and poor (55 patients) prognosis groups identified based on the new score showed a 2-year PFS of 84.5% (95%CI: 70.2-92.3%), 56.3% (95%CI: 37.6-71.4%), and 40.4% (95%CI: 27.0-53.4%), respectively (Figure 1B). The adjusted HR for 2-year PFS was 3.17 (95%CI: 1.27-7.87, P = 0.013) in the intermediate prognosis group and 4.51 (95%CI: 1.97-10.3, P < 0.001) in the poor prognosis group, when compared to the good prognosis group. The ROC analysis showed that adding the new score to the IPI score significantly improved the predictive accuracy of the 2-year PFS from an AUC of 0.688 to 0.767 (P = 0.020). Conclusion: The new cell surface marker-based risk score for DLBCL patients established here is more useful for predicting the 2-year PFS than the IPI score alone. Further external validation is required to increase the prognostic accuracy of this new score. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Stream Processing for Performance Analysis of Identifying Dropout Students utilizing Different Decision Tree Based Methods

A person's ability to lead a stable, affluent life is made possible through education. In the same way, a country's development may be influenced by the proportion of its population with a higher level of education. This number does, however, decline because of early schooling dropouts. Furthermore, a nation's resources are diminished if a student cannot continue because of a dropout. Although the number of dropouts is constantly falling, it is still very challenging for educational institutions to identify these individuals. An educational institution's first priority is to improve student Performance; therefore, it makes sure that every student graduates on time. Nevertheless, a significant barrier that has a negative effect on this goal is student dropout. Understanding the causes of dropouts is necessary to finding a solution. The causes differ from one student to another; some are connected to the student's workload and mental fortitude. Various ways using Decision Tree (DT) methodologies have been suggested and studied in this study.

Food security and agricultural challenges in West-African rural communities: a machine learning analysis

ABSTRACT This article investigated household-level food security for Ghana, Liberia, and Senegal. Different agroclimatic, ecological, social, and farming conditions in West Africa were represented. Using data-driven Random Forest and Chi-Square Automatic Interaction Detection (CHAID) decision tree methodology, this study classified 644 Ghanaian, 323 Liberian, and 510 Senegalese households for comparison and interpretation on food security. The predictors growing Liberian and Senegalese decision trees imply community support, diverse selling channels outside villages, resolving the dispute over farmland, and increasing community-level investment for food availability and access demonstrate household food security. Predictor importance on food security for Ghana highlighted the role of independent producers and food suppliers toward stability. Household food security or insecurity was distinguished by location-specific and gender-led households in Liberia and Senegal. Practically, the results presented a need to step-up agricultural education and extension based on an empirical field survey and its interpretations. The results can add considerations to the role of farming households as independent and individual suppliers and consumers to long-standing dimensions of food security, i.e., food availability, access, and stability.