Regression Tree Approach Research Articles

Marijuana Use among College Students after the COVID-19 Pandemic: A Classification and Regression Tree Approach

Marijuana Use among College Students after the COVID-19 Pandemic: A Classification and Regression Tree Approach

Investigation of mechanical properties of high-performance concrete via multi-method of regression tree approach

Concrete's workability and durability are influenced by its mechanical properties, including Tensile and Compressive strength. High-performance concrete exhibits non-linear relationships between its compressive and tensile strength characteristics and the proportions of its constituent materials, such as water, aggregate, cement, and admixtures. The investigation of the relations between the constituents of concrete and its mechanical properties has posed a challenging issue. This paper seeks to develop a range of single, hybrid, and ensemble models to resolve the problem of accurately estimating the mechanical properties of concrete according to its constituent components as input variables. In this regard, various frameworks incorporating a machine learning technique called decision tree and four metaheuristic optimization algorithms were utilized in model development to emulate the values of tensile and compressive strength. The findings indicated that the decision tree-dynamic arithmetic optimization algorithm hybrid model produced results with an correlation of determination of 0.9919 in compressive strength and 0.9933 in tensile strength, which were on average 1–3 % higher than that of the decision tree-dandelion optimizer algorithm, decision tree-arithmetic optimization algorithm, and decision tree-coot optimization algorithm, indicating superior optimization performance of dynamic arithmetic optimization algorithm. Additionally, the powerful prediction capability of the decision tree + dynamic arithmetic optimization algorithm + dandelion optimizer algorithm + coot optimization algorithm + arithmetic optimization algorithm ensemble model was noticeable with R2 of 0.9882 and 0.9936 in compressive and tensile strength estimation reliable to be used for various data produced in the future. In general, the utilization of coupling techniques to generate hybrid and ensemble models can enhance the accuracy of predictions while reducing the time and costs associated with experimental procedures.

The influence of climatic and human-induced factors on the spatial distribution of invasive plant species richness across the Loess Plateau

Biological invasion poses a critical global issue, leading to substantial detrimental impacts on biodiversity, the environment, and the economy. The objective of the study is to offer a thorough understanding of how both climatic and human-induced elements impact the geographic richness of invasive plant species across the Loess Plateau. We evaluate the distribution of invasive plant species at the county level across the Loess Plateau by examining herbarium records from China. We incorporate 16 climatic and anthropogenic variables to depict the local environmental settings. Furthermore, we apply a classification and regression tree approach to investigate the correlation between the richness of invasive plant species and the identified factors. Our study demonstrates that a total of 401 invasive plant species are identified, which are spread across 249 genera and 61 families. Among these, the Asteraceae family stands out as the most prevalent, trailed by Poaceae and Fabaceae. The spatial distribution of invasive plant species richness reveals a notable trend, with the highest frequencies found in the southeastern parts of the region and the lowest in the northwestern areas. It is noteworthy that regions with higher levels of economic advancement tend to harbor a more significant abundance of invasive plant species. The richness of invasive plant species on the Loess Plateau is predominantly shaped by a combination of climatic and human variables, such as annual precipitation, gross domestic product, maximum temperature of warmest month, and minimum temperature of coldest month. To fully comprehend the ecological and biological mechanisms underlying the diversity of invasive plant species on the Loess Plateau, a pioneering conceptual framework has been established. Our study suggests that achieving a harmonious equilibrium among development, conservation, and invasion mitigation is essential for recognizing emerging risks associated with habitat alterations, climate change, and socio-economic advancements in arid regions.

Machine learning prediction of hypertension and diabetes in twin pregnancies using characteristics at prenatal care entry: a nationwide study.

To develop a prediction model for hypertensive disorders in pregnancy (HDP) and gestational diabetes (GDM) in twin pregnancies utilizing characteristics at the prenatal care entry level. Cross-sectional study using the US national live birth data between 2016 and 2021. The association of all prenatal candidate variables with HDP and GDM was tested with uni- and multi-variable logistic regression analyses. Prediction models were built with generalized linear models using the logit link function and classification and regression tree approach (XGboost) machine learning (ML) algorithm. Performance was assessed with repeated 2-fold cross-validation and performance metrics we considered were area under the curve (AUC). P value <0.001 was considered statistically significant. A total of 707,198 twin pregnancies were included in the HDP analysis and 723,882 twin pregnancies for the GDM analysis. The incidence of HDP and GDM significantly increased from 12.2% in 2016 to 15.4% in 2021 and from 8.1% in 2016 to 10.7% in 2021, respectively. Factors that increase the risk of HDP in twin gestations are maternal age <20, age≥35, infertility, prepregnancy DM, non-Hispanic Black population, obesity, and those with Medicaid insurance (p<0.001). Factors that more than doubled the risk are obesity class II and III (p<0.001). Factors that increase the risk of GDM in twin gestations are age <25, age≥30, history of infertility, prepregnancy hypertension, non-Hispanic Asian population, non-US nativity, and obesity (p<0.001). Factors that more than doubled the risk are maternal age ≥ 30 years, non-Hispanic Asian, and class I, II, and III maternal obesity ( p<0.001). For both HDP and GDM, the performance of the ML and logistic regression model was mostly similar with negligible difference in terms of all tested performance domains. The AUC of the final ML model for HDP and GDM were 0.62±0.004, and 0.67±0.004, respectively. The incidence of HDP and GDM in twin gestations is increasing. The predictive accuracy of the machine learning model for both HDP and GDM in twin gestations is similar to that of the logistic regression model. Both models had modest performance, well-calibrated, and neither had a poor fit. This article is protected by copyright. All rights reserved.

Gradient boosted regression as a tool to reveal key drivers of temporal dynamics in a synthetic yeast community.

Microbial communities are vital to our lives, yet their ecological functioning and dynamics remain poorly understood. This understanding is crucial for assessing threats to these systems and leveraging their biotechnological applications. Given that temporal dynamics are linked to community functioning, this study investigated the drivers of community succession in the wine yeast community. We experimentally generated population dynamics data and used it to create an interpretable model with a gradient-boosted regression tree approach. The model was trained on temporal data of viable species populations in various combinations, including pairs, triplets, and quadruplets, and was evaluated for predictive accuracy and input feature importance. Key findings revealed that the inoculation dosage of non-Saccharomyces species significantly influences their performance in mixed cultures, while Saccharomyces cerevisiae consistently dominates regardless of initial abundance. Additionally, we observed multispecies interactions where the dynamics of Wickerhamomyces anomalus were influenced by Torulaspora delbrueckii in pairwise cultures, but this interaction was altered by the inclusion of S. cerevisiae. This study provides insights into yeast community succession and offers valuable machine learning-based analysis techniques applicable to other microbial communities, opening new avenues for harnessing microbial communities.

Retraction Note: Classification of nucleotide sequences for quality assessment using logistic regression and decision tree approaches

Retraction Note: Classification of nucleotide sequences for quality assessment using logistic regression and decision tree approaches

Data-driven approach for air pollutant concentrations forecasting: A window-based multi-output GBRT approach

Air pollutant concentrations forecasting is essential for detrimental public exposure prevention, air quality enhancement, and effective environmental policy shaping. Recently, air pollutant concentrations forecasting based on machine learning has been considerably advanced with the development of data-driven approaches. However, multi-source data constraints and architectural complexity in machine learning approaches limit the use of machine learning in actual scenarios. Herein we present a window-based multi-output gradient boosting regression tree (WM-GBRT) approach to predict air pollutant concentrations for the next 48 h at each monitoring station, considering air pollutant monitoring data, meteorological monitoring data, NECP-GFS data, and GEOS-CF data. The key innovation of our approach lies in the flexible input window configuration and the implementation of an multi-step independent strategy. The experiments were conducted in China and compared to existing data-driven baselines, we show that our approach achieved the superior performance in forecasting concentrations of six air pollutants, with a considerable improvement of 6.94 % (PM2.5), 12.3 % (PM10), 3.84 % (O3), 30.6 % (SO2), 9.84 % (NO2), and 93.9 % (CO) when compared to the second-best baselines. This simple yet efficient approach can be easily applied, providing a reliable technical method for predicting air pollutant concentrations.

Dissecting Alzheimer's Disease Risk in Asian American Elders: A Classification and Regression Tree Approach.

Alzheimer's disease (AD) poses a growing public health challenge, particularly with an aging population. While extensive research has explored the relationships between AD, socio-demographic factors, and cardiovascular risk factors, a notable gap exists in understanding these connections within the Asian American elderly population. This study aims to address this gap by employing the Classification and Regression Tree (CART) approach to investigate the intricate interplay of socio-demographic variables, cardiovascular risk factors, sleep patterns, prior antidepressant use, and AD among Asian American elders. Data from the 2017 Uniform Data Set, provided by the National Alzheimer's Coordinating Center, were analyzed, focusing on a sample of Asian American elders (n = 4,343). The analysis utilized the Classification and Regression Tree (CART) approach. CART analysis identified critical factors, including levels of independence, specific age thresholds (73.5 and 84.5 years), apnea, antidepressant use, and body mass index, as significantly associated with AD risk. These findings have far-reaching implications for future research, particularly in examining the roles of gender, cultural nuances, socio-demographic factors, and cardiovascular risk elements in AD within the Asian American elderly population. Such insights can inform tailored interventions, improved healthcare access, and culturally sensitive policies to address the complex challenges posed by AD in this community.

Stratum-specific health outcome estimation in Pakistan using double goal CART.

Post-stratification is applied when the subpopulation membership is observed only for sampled values and the goal is to estimate stratum-specific parameters which leads the survey statisticians towards primary goals i.e., classification of non-sampled units into different strata and prediction of the values of the study variables. Regression models, on one side, optimize the prediction of the study variable's non-sampled values while the classification algorithms, on the other side, look for the classification of non-sampled cases into different strata. Hence, it is crucial to deal with these two goals simultaneously for the estimation of stratum-specific parameters. This study introduces the idea of a double-objective classification and regression trees (CARTs) approach for estimating stratum-specific parameters. Theoretical properties of the total estimator are derived. An application on the estimation of health outcomes in different domains is given to delineate the practical significance as well as the efficiency of the proposed CART-based method. The proposed estimator of population total performs better than the existing stratum-specific estimator in terms of relative efficiency for all choices of parameters. As an ensemble model, the random forest CART outperforms the other competing tree-based models and homogenous population model without using any auxiliary variable.

Decision Tree for 305-Day Milk Yield in Cross-bred Cattle

Cows' Lactation Milk Yield (LMY) is a crucial factor in animal breeding operations. Investigating the influence of potential environmental factors on lactation milk yield is of paramount importance and in order to identify the various factors influencing lactation milk yield, dairy cattle records were analysed using the regression tree approach. Age, Parity (P), Lactation Length (LL), and Calving Season (CS) were taken into account as explanatory variables while 305-day Milk Yield (MY) as a dependent variable. Decision tree study revealed that Lactation Length, followed by Parity, Age, and Calving Season, had the greatest impact on the 305-d milk output of cross-bred cows. The regression trees use the tree to represent the recursive part. Each terminal node or leaf of the tree represents a cell of the section and has just added a simple pattern applied to it in this cell. It was evident from nodes (branches) in regression tree, that cows with parities of 1 and 4 (node 11) produced less milk than cows with parities of 2, 3, 5, 6, 7 and 8 (node 10). More milk was produced by cows older than 4.3 years and whose calving seasons were spring and summer (node 40). With the use of the regression tree method, we were able to extract sub-homogenous groups based on the explanatory variables from records of cross-bred cattle and determine the combinations of environmental conditions that produced the maximum 305-d milk yield.

Understanding transmission risk and predicting environmental suitability for Mayaro Virus in Central and South America.

Mayaro virus (MAYV) is a mosquito-borne Alphavirus that is widespread in South America. MAYV infection often presents with non-specific febrile symptoms but may progress to debilitating chronic arthritis or arthralgia. Despite the pandemic threat of MAYV, its true distribution remains unknown. The objective of this study was to clarify the geographic distribution of MAYV using an established risk mapping framework. This consisted of generating evidence consensus scores for MAYV presence, modeling the potential distribution of MAYV in select countries across Central and South America, and estimating the population residing in areas suitable for MAYV transmission. We compiled a georeferenced compendium of MAYV occurrence in humans, animals, and arthropods. Based on an established evidence consensus framework, we integrated multiple information sources to assess the total evidence supporting ongoing transmission of MAYV within each country in our study region. We then developed high resolution maps of the disease's estimated distribution using a boosted regression tree approach. Models were developed using nine climatic and environmental covariates that are related to the MAYV transmission cycle. Using the output of our boosted regression tree models, we estimated the total population living in regions suitable for MAYV transmission. The evidence consensus scores revealed high or very high evidence of MAYV transmission in several countries including Brazil (especially the states of Mato Grosso and Goiás), Venezuela, Peru, Trinidad and Tobago, and French Guiana. According to the boosted regression tree models, a substantial region of South America is suitable for MAYV transmission, including north and central Brazil, French Guiana, and Suriname. Some regions (e.g., Guyana) with only moderate evidence of known transmission were identified as highly suitable for MAYV. We estimate that approximately 58.9 million people (95% CI: 21.4-100.4) in Central and South America live in areas that may be suitable for MAYV transmission, including 46.2 million people (95% CI: 17.6-68.9) in Brazil. Our results may assist in prioritizing high-risk areas for vector control, human disease surveillance and ecological studies.

Interaction of Biomechanical, Anthropometric, and Demographic Factors Associated with Patellofemoral Pain in Rearfoot Strike Runners: A Classification and Regression Tree Approach

BackgroundPatellofemoral pain (PFP) is among the most common injuries in runners. While multiple risk factors for patellofemoral pain have been investigated, the interactions of variables contributing to this condition have not been explored. This study aimed to classify runners with patellofemoral pain using a combination of factors including biomechanical, anthropometric, and demographic factors through a Classification and Regression Tree analysis.ResultsThirty-eight runners with PFP and 38 healthy controls (CON) were selected with mean (standard deviation) age 33 (16) years old and body mass index 22.3 (2.6) kg/m2. Each ran at self-selected speed, but no between-group difference was identified (PFP = 2.54 (0.2) m/s x CON = 2.55 (0.1) m/s, P = .660). Runners with patellofemoral pain had different patterns of interactions involving braking ground reaction force impulse, contact time, vertical average loading rate, and age. The classification and regression tree model classified 84.2% of runners with patellofemoral pain, and 78.9% of healthy controls. The prevalence ratios ranged from 0.06 (95% confidence interval: 0.02–0.23) to 9.86 (95% confidence interval: 1.16–83.34). The strongest model identified runners with patellofemoral pain as having higher braking ground reaction force impulse, lower contact times, higher vertical average loading rate, and older age. The receiver operating characteristic curve demonstrated high accuracy at 0.83 (95% confidence interval: 0.74–0.93; standard error: 0.04; P < .001).ConclusionsThe classification and regression tree model identified an influence of multiple factors associated with patellofemoral pain in runners. Future studies may clarify whether addressing modifiable biomechanical factors may address this form of injury.

Exploring key social capital indicators for disaster preparedness in rural disaster-prone areas: a boosted regression tree approach

Exploring key social capital indicators for disaster preparedness in rural disaster-prone areas: a boosted regression tree approach

Classification and regression tree approach for the prediction of the seasonal apparel market: focused on weather factors

PurposeClimate change-induced weather changes are severe and frequent, making it difficult to predict apparel sales. The primary goal of this study was to assess consumers' responses to winter apparel searches when external stimuli, such as weather, calendars and promotions arise and to develop a decision-making tool that allows apparel retailers to establish sales strategies according to external stimuli.Design/methodology/approachThe theoretical framework of this study was the effect of external stimuli, such as calendar, promotion and weather, on seasonal apparel search in a consumer's decision-making process. Using weather observation data and Google Trends over the past 12 years, from 2008 to 2020, consumers' responses to external stimuli were analyzed using a classification and regression tree to gain consumer insights into the decision process. The relative importance of the factors in the model was determined, a tree model was developed and the model was tested.FindingsWinter apparel searches increased when the average, maximum and minimum temperatures, windchill, and the previous day's windchill decreased. The month of the year varies depending on weather factors, and promotional sales events do not increase search activities for seasonal apparel. However, sales events during the higher-than-normal temperature season triggered search activity for seasonal apparel.Originality/valueConsumer responses to external stimuli were analyzed through classification and regression trees to discover consumer insights into the decision-making process to improve stock management because climate change-induced weather changes are unpredictable.

GP-BART: A novel Bayesian additive regression trees approach using Gaussian processes

The Bayesian additive regression trees (BART) model is an ensemble method extensively and successfully used in regression tasks due to its consistently strong predictive performance and its ability to quantify uncertainty. BART combines “weak” tree models through a set of shrinkage priors, whereby each tree explains a small portion of the variability in the data. However, the lack of smoothness and the absence of an explicit covariance structure over the observations in standard BART can yield poor performance in cases where such assumptions would be necessary. The Gaussian processes Bayesian additive regression trees (GP-BART) model is an extension of BART which addresses this limitation by assuming Gaussian process (GP) priors for the predictions of each terminal node among all trees. The model's effectiveness is demonstrated through applications to simulated and real-world data, surpassing the performance of traditional modelling approaches in various scenarios.

Machine learning models for occurrence form prediction of heavy metals in tailings

ABSTRACT Modern mining and metal ore smelting produce vast tailings, increasing heavy metal pollution. The study of heavy metal occurrence forms is a promising way to remediate contaminated tailings while minimizing environmental damage. However, laboratory measurements of heavy metal occurrence forms are complex and time-consuming, so a fast and accurate identification method is urgently needed. This study used gradient boosting regression tree (GBRT) approaches to predict heavy metal occurrence forms in tailings, with tailings mineralogy information and heavy metal properties as input variables and the percentages of seven occurrence forms as output variables. The optimum GBRT model achieved excellent performance, with R values greater than 0.92 recorded on the testing set for all seven occurrence forms. The feature importance analysis showed that electronegativity was the most critical variable across all occurrence forms, with an average feature importance of 0.442, followed closely by atomic number, which had an average feature importance of 0.211. Overall, this study proposes a reliable and efficient GBRT prediction model for heavy metal occurrence forms, providing new insights into the effects of tailings mineralogy on heavy metal occurrence forms. This approach can be applied to contamination analysis and the safe and efficient use of heavy metals.

Interpretable machine learning models for hospital readmission prediction: a two-step extracted regression tree approach

BackgroundAdvanced machine learning models have received wide attention in assisting medical decision making due to the greater accuracy they can achieve. However, their limited interpretability imposes barriers for practitioners to adopt them. Recent advancements in interpretable machine learning tools allow us to look inside the black box of advanced prediction methods to extract interpretable models while maintaining similar prediction accuracy, but few studies have investigated the specific hospital readmission prediction problem with this spirit.MethodsOur goal is to develop a machine-learning (ML) algorithm that can predict 30- and 90- day hospital readmissions as accurately as black box algorithms while providing medically interpretable insights into readmission risk factors. Leveraging a state-of-art interpretable ML model, we use a two-step Extracted Regression Tree approach to achieve this goal. In the first step, we train a black box prediction algorithm. In the second step, we extract a regression tree from the output of the black box algorithm that allows direct interpretation of medically relevant risk factors. We use data from a large teaching hospital in Asia to learn the ML model and verify our two-step approach.ResultsThe two-step method can obtain similar prediction performance as the best black box model, such as Neural Networks, measured by three metrics: accuracy, the Area Under the Curve (AUC) and the Area Under the Precision-Recall Curve (AUPRC), while maintaining interpretability. Further, to examine whether the prediction results match the known medical insights (i.e., the model is truly interpretable and produces reasonable results), we show that key readmission risk factors extracted by the two-step approach are consistent with those found in the medical literature.ConclusionsThe proposed two-step approach yields meaningful prediction results that are both accurate and interpretable. This study suggests a viable means to improve the trust of machine learning based models in clinical practice for predicting readmissions through the two-step approach.

How to better balance academic achievement and learning anxiety from time on homework? A multilevel and classification and regression tree analyses.

Using education survey data from 153, 317 Grade 4 students and 150, 040 Grade 8 students in China, this study examined the relationship between time on homework and academic achievement and learning anxiety with hierarchical linear modeling (HLM) and classification and regression tree (CART) approaches. With a classification of time spent on homework into four related variables, this study found that, firstly, time spent on in-school homework during weekdays had positive effects on students' achievement for both grades, and the positive effect was stronger for Grade 8 students than Grade 4 students. Moreover, a maximum of 1 h was recommended for Grade 4 students. Secondly, time spent on out-of-school homework on weekdays was negatively correlated with students' academic achievement and positively with learning anxieties. It had greater detrimental effect on Grade 8 than Grade 4. Thirdly, Grade 8 students were encouraged to have more out-of-school homework on weekend with more than 2.8 h on average recommended. It was expected to complement extant studies and provide the practical findings for teachers, practitioners and school policy makers in making any homework assignment planning or conducting interventions.

Determinants of Farm Household Socio-Economic Vulnerability Induced by Climate Change in Maharashtra: Regression Tree Approach

Climate change is a serious threat to the agrarian economy of Maharashtra due to persistent droughts, floods, irregular rainfall, etc. The present study was conducted during 2020–21 in three districts of Maharashtra (Parbhani, Sindhudurg and Ahmednagar) based on the extent of socio-economic vulnerability. The regression tree approach predicted the likelihood of socio-economic vulnerability in 180 randomly selected farm households. Findings indicated that improvement in visits of veterinary doctors, animals registered for feed camp, less consumption expenditure on food, and insuring farm animals resulted in a low vulnerability category. On the contrary, low access to electricity, low rainfall, and a higher number of unemployed members in a household resulted in a high level of socio-economic vulnerability. The study suggested focused policy efforts to improve the current socio-economic status of farm households by understanding the importance of closely associated variables affecting the degree of vulnerability to cope with climate change.

Spatial Heterogeneity in the Nonlinear Impact of Built Environment on Commuting Time of Active Users: A Gradient Boosting Regression Tree Approach

Many studies provided evidence regarding the influence of built environment (BE) on commuting time. However, few studies have considered the spatial heterogeneity of such impacts. Using data from Nanjing, China, this study employs two-step clustering and gradient boosted regression trees (GBRT) to segment the neighborhoods into different types and investigate the effects of BE characteristics on the commuting time of active users. The results show a strong effect of BE characteristics on commuting time, involving active modes. The importance of BE characteristics varies among neighborhood types. For active commuters in the internal region of Nanjing, commuting time is affected mostly by the land use mix at the work end. The lowest impact of BE in internal regions is associated with metro station density. For active commuters in external region of the city, the relative importance of intersection density at the home end is the largest (as high as 5.76%). Moreover, other significant differences are found in the associations between BE characteristics and active commuting time in the two regions.