Multivariate Tree Research Articles

Longitudinal assessment of health-related quality of life in patients with adult congenital heart disease undergoing cardiac surgery

ObjectiveThe study objective was to assess longitudinal postoperative health-related quality of life among patients with adult congenital heart disease facilitated by a novel electronic medical record–based patient-reported outcomes follow-up platform. MethodsFrom January 2022 to October 2023, 559 patients with adult congenital heart disease underwent cardiac surgery; 491 (88%) completed a 23-element health-related quality of life questionnaire covering 3 domains (physical, mental, and social) yielding 911 assessments. Automated questionnaires via electronic medical record were sent at 7 days preoperatively and postoperatively at 1, 3, 6, and 12 months. Nonlinear multiphase mixed effects models and boosting approach using multivariate trees were used to assess longitudinal trends and the relationship among patient characteristics, clinical variables, and health-related quality of life outcomes. ResultsMean age of patients was 53 years (range, 19-86), 238 (43%) were female, 109 (20%) were STAT category 3 or 4, postoperative mortality was 0, and stroke was 4 (0.7%). Diagnosis included hypertrophic obstructive cardiomyopathy (276, 50%), anomalous coronary artery (42, 7.5%), congenital aortic valve disease (42, 7.5%), bicuspid aortic valve (64, 12%), and aortic aneurysm (25, 4.5%). Although baseline health-related quality of life scores were below population norms, rapid postoperative increases were seen in physical, mental, and social scores, surpassing population norms between 2 and 6 months. Patients with higher baseline health-related quality of life had higher longitudinal scores. Female patients and those of Black race had higher Area Deprivation Index and lower postoperative physical health-related quality of life scores. ConclusionsPatients with adult congenital heart disease require lifelong medical surveillance and repeated interventions. Our innovative electronic medical record–embedded time-series tool assessing health-related quality of life after cardiac surgery shows improved patient-reported outcomes across mental, physical, and social domains that endure through at least the first postoperative year.

An Exploratory Approach of Clinically Useful Biomarkers of Cvid by Logistic Regression

Despite advancements in genetic and functional studies, the timely diagnosis of common variable immunodeficiency (CVID) remains a significant challenge. This exploratory study was designed to assess the diagnostic performance of a novel panel of biomarkers for CVID, incorporating the sum of κ+λ light chains, soluble B-cell maturation antigen (sBCMA) levels, switched memory B cells (smB) and the VISUAL score. Comparative analyses utilizing logistic regression were performed against established gold-standard tests, specifically antibody responses. Our research encompassed 88 subjects, comprising 27 CVID, 23 selective IgA deficiency (SIgAD), 20 secondary immunodeficiency (SID) patients and 18 healthy controls. We established the diagnostic accuracy of sBCMA and the sum κ+λ, achieving sensitivity (Se) and specificity (Spe) of 89% and 89%, and 90% and 99%, respectively. Importantly, sBCMA showed strong correlations with all evaluated biomarkers (sum κ+λ, smB cell and VISUAL), whereas the sum κ+λ was uniquely independent from smB cells or VISUAL, suggesting its additional diagnostic value. Through a multivariate tree decision model, specific antibody responses and the sum κ+λ emerged as independent, signature biomarkers for CVID, with the model showcasing an area under the curve (AUC) of 0.946, Se 0.85, and Spe 0.95. This tree-decision model promises to enhance diagnostic efficiency for CVID, underscoring the sum κ+λ as a superior CVID classifier and potential diagnostic criterion within the panel.

Unboxing Tree ensembles for interpretability: A hierarchical visualization tool and a multivariate optimal re-built tree

The interpretability of models has become a crucial issue in Machine Learning because of algorithmic decisions' growing impact on real-world applications. Tree ensemble methods, such as Random Forests or XgBoost, are powerful learning tools for classification tasks. However, while combining multiple trees may provide higher prediction quality than a single one, it sacrifices the interpretability property resulting in “black-box” models. In light of this, we aim to develop an interpretable representation of a tree-ensemble model that can provide valuable insights into its behavior. First, given a target tree-ensemble model, we develop a hierarchical visualization tool based on a heatmap representation of the forest's feature use, considering the frequency of a feature and the level at which it is selected as an indicator of importance. Next, we propose a mixed-integer linear programming (MILP) formulation for constructing a single optimal multivariate tree that accurately mimics the target model predictions. The goal is to provide an interpretable surrogate model based on oblique hyperplane splits, which uses only the most relevant features according to the defined forest's importance indicators. The MILP model includes a penalty on feature selection based on their frequency in the forest to further induce sparsity of the splits. The natural formulation has been strengthened to improve the computational performance of mixed-integer software. Computational experience is carried out on benchmark datasets from the UCI repository using a state-of-the-art off-the-shelf solver. Results show that the proposed model is effective in yielding a shallow interpretable tree approximating the tree-ensemble decision function.

A regression tree method for longitudinal and clustered data with multivariate responses

In this paper, we propose a tree-based method called Multivariate RE-EM tree, which combines the regression tree and the linear mixed effects model for modeling multivariate response longitudinal or clustered data. The Multivariate RE-EM tree method estimates a population-level single tree structure that is driven by the multiple responses simultaneously and object-level random effects for each response variable, where correlation between the response variables and between the associated random effects are each allowed. Through simulation studies, we verify the advantage of the Multivariate RE-EM tree over the use of multiple univariate RE-EM trees and the Multivariate Regression Tree. We apply the Multivariate RE-EM tree to analyze a real data set that contains multidimensional nonfinancial characteristics of poverty of different countries as responses, and various potential causes of poverty as predictors.

A randomized controlled clinical trial of premixed calcium silicate-based cements for pulpotomy in primary molars

ObjectivesThis study aimed to verify the non-inferiority of Endocem MTA Premixed and Well-Root PT, compared with ProRoot MTA in the pulpotomy of primary molars. In addition, we tried to determine the factors that affect the prognosis of pulpotomy in primary molars. MethodsThis randomized clinical trial enrolled 158 molars of 52 children; 153 teeth were finally included and divided into three groups: ProRoot MTA (n = 50), Endocem MTA Premixed (n = 53), and Well-Root PT (n = 50). Clinical and radiographic follow-up was performed at 3, 6, and 12 months postoperatively and at the last visit post-treatment. Data were analyzed using the Fisher's exact test, Cox regression analysis, and the Kaplan–Meier survival curve method. ResultsThe success rates in the ProRoot MTA, Endocem MTA Premixed, and Well-Root PT were 92, 84.9 and 82%, respectively. The cumulative survival rates did not differ significantly among the materials. Among the investigated variables, only ΔF and ΔF max significantly affected the success rates. In the multivariate survival tree model, significant unfavorable survival was observed when the ΔF value was -14.4 or less (hazard ratio, 7.56; P = 0.0295). ConclusionsConsidering the clinical effectiveness of Endocem MTA Premixed and Well-Root PT and the operational convenience as a premixed type, they can be used as advantageous materials in the pulpotomy of primary molars in pediatric patients. The QLF method is a useful diagnostic method that can establish treatment plans and determine the prognosis of pulpotomy based on the ΔF value in primary molars. Clinical significanceEndocem MTA Premixed and Well-Root PT can confer high success rates and are non-inferior to ProRoot MTA in pulpotomy for primary molars. We also showed that QLF technology can be applied to predict the success/failure and prognosis of pulpotomies in primary molars.

Predicting heterogeneous treatment effects of an Internet-based depression intervention for patients with chronic back pain: Secondary analysis of two randomized controlled trials

BackgroundDepression is highly prevalent among individuals with chronic back pain. Internet-based interventions can be effective in treating and preventing depression in this patient group, but it is unclear who benefits most from this intervention format. MethodIn an analysis of two randomized trials (N = 504), we explored ways to predict heterogeneous treatment effects of an Internet-based depression intervention for patients with chronic back pain. Univariate treatment-moderator interactions were explored in a first step. Multilevel model-based recursive partitioning was then applied to develop a decision tree model predicting individualized treatment benefits. ResultsThe average effect on depressive symptoms was d = −0.43 (95 % CI: −0.68 to –0.17; 9 weeks; PHQ-9). Using univariate models, only back pain medication intake was detected as an effect moderator, predicting higher effects. More complex interactions were found using recursive partitioning, resulting in a final decision tree with six terminal nodes. The model explained a large amount of variation (bootstrap-bias-corrected R2 = 45 %), with predicted subgroup-conditional effects ranging from di = 0.24 to −1.31. External validation in a pilot trial among patients on sick leave (N = 76; R2 = 33 %) pointed to the transportability of the model. ConclusionsThe studied intervention is effective in reducing depressive symptoms, but not among all chronic back pain patients. Predictions of the multivariate tree learning model suggest a pattern in which patients with moderate depression and relatively low pain self-efficacy benefit most, while no benefits arise when patients' self-efficacy is already high. If corroborated in further studies, the developed tree algorithm could serve as a practical decision-making tool.

Estimation of Vegetation Indices With Random Kernel Forests

Vegetation indexes help perform precision farming because they provide useful information regarding moisture, nutrient content, and crop health. Primary sources of those indexes are satellites and unmanned aerial vehicles equipped with expensive multispectral sensors. Reducing the price of obtaining such information would increase the availability of precision farming. Several studies have proposed deep neural network methods to estimate the indexes from RGB color images. However, these studies report relatively large errors for mature plants, when highly non-linear relationships between image RGB bands and vegetation indexes arise. One could apply multilayer random forest-based models (Deep Forests) to solve this problem, but they have limited discriminative power and ability on catching non-linear relationships between image features. The cornerstone of the Deep Forests is that at each layer they enrich original features with embeddings containing empiric class probabilities from previous layers, although these probabilities deliver limited information. In this paper, we propose methods, which combine ideas of Deep Forests, Random Forests of multivariate trees, and global pruning of Random Forests to tackle these problems. We applied oblique (linear) and kernel (non-linear) trees as basic classifiers of the Deep Forest to improve discriminative power. We also utilized a method to refine Random Forests with a global loss optimization. This method helps to generate more expressive embeddings at each layer of the Deep Forest, which significantly improves results of the data analysis. In the experiments, we compared those methods with AlexNet and ResNet-based neural networks on several image classification datasets as well as on the NDVI prediction task. The experiments on image classification show that the proposed Deep Forest-based methods provide competitive results on datasets with small and medium size of feature-set. The results of the NDVI prediction task indicate that these methods are robust to senescence of plants and outperform neural network-based solutions.

Green infrastructure can promote plant functional connectivity in a grassland species around fragmented semi‐natural grasslands in NW‐Europe

Species may benefit from green infrastructure, i.e. the network of natural and anthropogenic habitat remnants in human‐dominated landscapes, if it helps isolated populations in remaining habitat patches to be functionally connected. The importance of green infrastructure is therefore increasingly emphasized in conservation policy to counter biodiversity loss. However, there is limited evidence, particularly in plants, that green infrastructure promotes functional connectivity, i.e. supports the colonization of habitat patches across a landscape. We applied landscape genetics to test whether the green infrastructure supports structural and functional connectivity in the grassland perennial Galium verum, in 35 landscapes in Belgium, Germany and Sweden. We used multivariate genetic clustering techniques, nestedness analyses and conditional inference trees to examine landscape‐scale patterns in genetic diversity and structure of plant populations in the green infrastructure surrounding semi‐natural grasslands. Inferred functional connectivity explained genetic variation better than structural connectivity, yielding positive effects on genetic variation. The road verge network, a major structural component of the green infrastructure and its functional connectivity, most effectively explained genetic diversity and composition in G. verum. Galium verum ramets occupying the surrounding landscape proved to be genetic subsets of focal grassland populations, shaping a nested landscape population genetic structure with focal grasslands, particularly ancient ones, harbouring unique genetic diversity. This nested pattern weakened as road network density increased, suggesting road verge networks enable high landscape occupancy by increased habitat availability and facilitates gene flow into the surrounding landscape. Our study proposes that green infrastructure can promote functional connectivity, providing that a plant species can survive outside of core habitat patches. As this often excludes habitat specialist species, conservation practice and policy should primarily focus on ancient, managed semi‐natural grasslands. These grasslands both harbour unique genetic diversity and act as primary gene and propagule sources for the surrounding landscape, highlighting their conservation value.

A multivariate binary decision tree classifier based on shallow neural network

In this paper, a novel decision tree classifier based on shallow neural networks with piecewise and nonlinear transformation activation functions are presented. A shallow neural network is recursively employed into linear and non-linear multivariate binary decision tree methods which generates splitting nodes and classifier nodes. Firstly, a linear multivariate binary decision tree with a shallow neural network is proposed which employs a rectified linear unit function. Secondly, there is presented a new activation function with non-linear property which has good generalization ability in learning process of neural networks. The presented method shows high generalization ability for linear and non-linear multivariate binary decision tree models which are called a Neural Network Decision Tree (NNDT). The proposed models with high generalization ability ensure the classification accuracy and performance. A novel split criterion of generating the nodes which focuses more on majority objects of classes on the current node is presented and employed in the new NNDT models. Furthermore, a shallow neural network based NNDT models are converted into a hyperplane based linear and non-linear multivariate decision trees which has high speed in the processing classification decisions. Numerical experiments on publicly available datasets have showed that the presented NNDT methods outperform the existing decision tree algorithms and other classifier methods.

Techno-economic estimation of a non-cover box solar still with thermoelectric and antiseptic nanofluid using machine learning models

• Robust Machine Learning models were used to study the performance of PDCBSSTCDAN. • The energy effiicncy prediction with high accuracy was obtained by MARS technique. • The EPR model was the best result in exergy efficiency estimation of PDCBSSTCDAN. • The ML models could effectively detect the variations in effective variables of PDCBSSTCDAN. • The mathematical expressions of ML models could cover limitations of previous studies. With rapid rise of advancement in soft computing models, application of Machine Learning (ML) techniques has increasingly grown to successfully evaluate thermal characterizations of solar systems in the last decade. Compared with related literature, this research aimed to obtain accurate relationships based on the ML techniques for predicting the energy and exergy efficiencies of the parabolic dish concentrator box solar still fitted with thermoelectric condensing duct and antiseptic nanofluid (PDCBSSTCDAN) system. Effective variables that affect energy and exergy efficiencies are listed as the nanoparticle volume fraction, fan power, solar radiation, basin temperature, nanofluid temperature, ambient temperature, wind velocity, and productivity. By adding 0.05% and 0.1% by volume of Fe 3 O 4 @Ag nanoparticles to the basin water, the maximum production of distilled water has increased by 410 (ml/m 2 ) and 580 (ml/m 2 ), respectively, compared to the pure fluid. At the most optimal case, the cost of producing distilled water and the payback period are 0.0072 ($/L/m2) and 141 day, respectively. After having completed the development of ML techniques, empirical equations based on nature-inspired properties of ML models were obtained to estimate energy and exergy efficiencies with a reasonable degree of accuracy level. Results of ML models indicated that Evolutionary Polynomial Regression (EPR) technique yielded comparatively performance in the prediction of energy (Root Mean Square Error [RMSE] = 0.827) and exergy (Root Mean Square Error [RMSE] = 0.1078) efficiencies than Multivariate Adaptive Regression Analysis (MARS), Gene-Expression Programming (GEP), and M5Model Tree (MT). ML techniques could outperform the results of the previous investigations in terms of precision level and applicability of proposed empirical equations. Overall, the proposed equations can be conveniently utilized to perceive the physical characterizations of solar still systems.

Reciprocity and epistemicity: On the (proto)social and cross-cultural ‘value’ of information transmission

Reciprocity is a (proto)social mechanism that involves (im)politeness as a balance of positive and negative actions among individuals: doing something good to someone is expected to be reciprocated in kind (cf. Culpeper & Tantucci 2021). The same applies for negatively charged behaviour (Culpeper & Tantucci 2021). The present study advances the theory of reciprocity both empirically and theoretically, as it extends the model to contexts of information transmission, i.e. cases where some news is being communicated from one interlocutor to another. What we found is that the way people react to ‘being informed of something’ remarkably involves (im)politeness and is mediated by two maxims of epistemic reciprocity: Engagement E (be interested) maxim and Knowledge exchange Ke maxim (be interesting in return). Our case study is centred on Chinese telephone conversations among family members and shows that the costs and benefits realised by an information giver are matched by the information receiver when a propositional contribution to the current flow of information is produced in return. Conversely, when responses occur via bare backchanneling or absence of informative contribution to the on-going interaction, then reciprocity is not properly maintained, and perceptions of impoliteness are more likely to arise. Despite the context-dependent nature of our data, we will further argue that this finding has cross-cultural significance. Our methods triangulate between Likert-scale judgments, large scale corpus-based analysis and multivariate conditional inference tree modelling (Levshina 2015; Tantucci 2021).

Estimation of the compressive strength of green concretes containing rice husk ash: a comparison of different machine learning approaches

To mitigate the environmental issues related to the utilisation of ordinary portland cement (OPC) in concrete mixtures, attempts have been carried out to find alternative binders such as rice husk ash (RHA) as replacements for OPC. This study contributes to moving from the traditional laboratory-based methods for the determination of compressive strength (CS) towards machine learning-based approaches by developing three accurate models (i.e. artificial neural network (ANN), multivariate adaptive regression spline (MARS) and M5P model tree) for the estimation of the CS of concretes containing RHA. For this purpose, the models were developed employing 909 data records collected through technical literature. The results indicate that all three techniques provide reliable estimations of the CS for both training and testing datasets. However, the ANN-based model outperforms the other two models, while the MP5-based model is associated with the least accuracy and the maximum error values among all three techniques. The parametric study revealed that by increasing the contents of cement, coarse aggregate and age, and decreasing the contents of water, fine aggregate, RHA and superplasticizer, the CS of concrete increases while the sensitivity analysis demonstrated that the coarse aggregate content was the most influential parameter affecting the values of CS.

Perfil agronômico de cultivares de bananeiras na microrregião geográfica de Assis, São Paulo, Brasil

Abstract The characterization of banana cultivars is an important stage, which allows the identification of materials adapted to a particular region. The aim of this study was to evaluate the agronomic performance in the edaphoclimatic conditions of the geographic microregion of Assis, State of São Paulo, during the first three production cycles. The experiment was installed at São José Farm, Palmital, SP, where ten banana cultivars (Grande Naine, IAC 2001, FHIA 02, Bucaneiro, FHIA 17, Calypso, Ambrosia, Thap Maeo, BRS Princesa and Caipira) were evaluated during the three production cycles. The experimental design was in randomized blocks, with four replicates, each plot with 8.75 m2 and 5 plants per plot. The evaluated variables were plant height, pseudostem perimeter, number of leaves at flowering and harvesting, bunch mass, number of hands per bunch, fruit and pulp yield. Results were submitted to analysis of variance, means comparison tests and multivariate clustering or tree clustering analysis. ‘Grande Naine’ and ‘IAC 2001’ cultivars, as well as those of the Cavendish subgroup, are the most suitable for cultivation in the geographic microregion of Assis, SP, considering production performance in the evaluated production cycles.

Multidimensional Population Health Modeling: A Data-Driven Multivariate Statistical Learning Approach

Population health is multidimensional in nature, having complex relationships with the various health determinants. However, most previous studies investigate a single dimension of population health using linear models, failing to capture the nonlinearity in the data and interdependence of multiple dimensions in health outcomes. In this paper, we propose a data-driven multivariate statistical learning approach to simultaneously model various aspects of population health—characterizing the length and quality of life—as a function of health behaviors, clinical care, socioeconomic factors, physical environment, and demographics. We also propose a novel percentile-based variable selection for multivariate regression, without compromising the model’s generalization performance. We demonstrate the applicability of our proposed data-driven methodological framework using the New York State as a case study. Leveraging cross-validation techniques and statistical hypothesis tests, the results indicate that multivariate tree boosting method outperforms the traditionally-used univariate linear regression model and random forest in modeling multidimensional population health. The variable importance heat-map illustrates the relative influence of the key health determinants on the various dimensions of population health. Partial dependence plots are used to quantify the marginal effects and the nonlinear relationships between the health outcomes and health inputs. Our results show that teen birth rate is strongly associated with both length of life (e.g., child mortality) and quality of life (e.g., physically unhealthy days). Socioeconomic status is the key indicator to predict child and infant mortality. Our proposed framework can be used as a decision support tool for accurately assessing and predicting multivariate population health.

Genomic characterization of SARS-CoV-2 and its association with clinical outcomes: a 1-year longitudinal study of the pandemic in Colombia

ObjectivesThis study aimed to explore associations between the molecular characterization of severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and disease severity in ambulatory and hospitalized patients in two main Colombian epicentres during the first year of the coronavirus disease 2019 pandemic.MethodsIn total, 1000 patients with SARS-CoV-2 infection were included in this study. Clinical data were collected from 997 patients, and 678 whole-genome sequences were obtained by massively parallel sequencing. Bivariate, multi-variate, and classification and regression tree analyses were run between clinical and genomic variables.ResultsAge >88 years, and infection with lineages B.1.1, B.1.1.388, B.1.523 or B.1.621 for patients aged 71–88 years were associated with death [odds ratio (OR) 6.048036, 95% confidence interval (CI) 1.346567–32.92521; P=0.01718674]. The need for hospitalization was associated with higher age and comorbidities. The hospitalization rate increased significantly for patients aged 38–51 years infected with lineages A, B, B.1.1.388, B.1.1.434, B.1.153, B.1.36.10, B.1.411, B.1.471, B.1.558 or B.1.621 (OR 8.368427, 95% CI 2.573145–39.10672, P=0.00012). Associations between clades and clinical outcomes diverged from previously reported data.ConclusionsInfection with lineage B.1.621 increased the hospitalization and mortality rates. These findings, plus the rapidly increasing prevalence in Colombia and other countries, suggest that lineage B.1.621 should be considered as a ‘variant of interest’. If associated disease severity is confirmed, possible designation as a ‘variant of concern’ should be considered.

Assessment of the relationship between soil properties in an old tree line and its relation to tree density and tree trunk circumference

Soil organic carbon (SOC) is known as a vital ecosystem service, resulting from interactions of ecological processes. It is important for its contributions to food production, mitigation, and adaptation to climate change. In this study, we investigated the relationship between tree density and tree trunk circumference with the soil chemical properties in the small tree line area located in Józsefmajor, Hungary. The interrelation between different chemical soil properties also was measured. For this purpose, samples were taken in 24 plots (6 m×13m) from 0–10 soil depths. Tree density and tree trunk circumference in each plot were measured. The Near-Infrared spectroscopy technique (Wavelength Range: 1300–2600nm MEMS (micro-electromechanical systems) technology) was used to estimate the chemical properties of the soil. Pearson and Spearman correlation analysis was applied to study the interrelationships between two multivariate data sets, tree density and trunk circumference were compared with soil properties. The results showed a significant relationship between some soil chemical parameters, especially between soil organic carbon (SOC) and total N and also the cation exchange capacity (CEC) with SOC and total N. Besides, this study shows that the plots containing more trees and with a higher trunk circumference provide higher SOC and total N concentrations. Trunk circumference has a slightly stronger correlation with these two soil properties compared to those of tree density.

Use of Sentinel-2 Data to Improve Multivariate Tree Species Composition in a Forest Resource Inventory

Aerial-photo interpreted inventories of forest resources, including tree species composition, are valuable in forest resource management, but are expensive to create and can be relatively inaccurate. Because of differences among tree species in their spectral properties and seasonal phenologies, it might be possible to improve such forest resource inventory information (FRI) by using it in concert with multispectral satellite information from multiple time periods. We used Sentinel-2 information from nine spectral bands and 12 dates within a two-year period to model multivariate percent tree species composition in >51,000 forest stands in the FRI of south-central Ontario, Canada. Accuracy of random forest (RF) and convolutional neural network (CNN) predictions were tested using species-specific basal area information from 155 0.25-ha field plots. Additionally, we created models using the Sentinel-2 information in concert with the field data and compared the accuracy of these models and the FRI-based models by use of basal areas from a second (13.7-ha) field data set. Based on average R2 values across species in the two field data sets, the Sentinel-FRI models outperformed the FRI, showing 1.5- and 1.7-fold improvements relative to the FRI for RF and 2.1- and 2.2-fold improvements for CNN (mean R2: 0.141–0.169 (FRI); 0.217–0.295 (RF); 0.307–0.352 (CNN)). Models created with the field data performed even better: improvements relative to the FRI were 2.1-fold for RF and 2.8-fold for CNN (mean R2: 0.169 (FRI); 0.356 (RF); 0.469 (CNN)). As predicted, R2 values between FRI- and field-trained predictions were higher than R2 values with the FRI. Of the 21 tree species evaluated, 8 relatively rare species had poor models in all cases. Our multivariate approach allowed us to use more FRI stands in model creation than if we had been restricted to stands dominated by single species and allowed us to map species abundances at higher resolution. It might be possible to improve models further by use of tree stem maps and incorporation of the effects of canopy disturbances.

The compliance of French purchasing behaviors with a healthy and sustainable diet: a 1-yr follow-up of regular customers in hypermarkets

AbstractIn France, hypermarkets are the main shopping sites for food products. Therefore, the food-purchasing profiles of their regular customers may be a relevant indicator of the sustainability and health potentials of consumed diets. Knowing this information can be a step to address the issue of global health. The main objective of this study was to assess the sustainability and health potential of food-purchasing behaviors among regular adult customers, with or without children, of a leading French retailer. Secondarily, the cost of a sustainable food shopping cart was evaluated as regards the regular one, as calculated in this study. Purchasing receipts corresponding to 38,168 different food products were collected during one consecutive month for each four seasons in 2019 to assess compliance with a newly developed holistic indicator of food system sustainability, i.e., the 3V rule, recommending food consumption to be ‘Vegetal’/plant-based (≈15% animal calories/day), ‘Vrai’/real (max. 15% ultra-processed food calories/day, UPF) and ‘Varié’/varied. Participants were 708 regular buyers (aged ≥18 with different socio-economic profiles, with and without children) in 122 French hypermarkets. The plant rule was based on the animal and plant origin of food ingredients, including mixed products; the ‘real’ rule was evaluated with the Siga score according to the degree of processing to identify UPFs. The varied rule was defined based on a combination of food ‘categories × families’. The effect of children and season on the purchased animal and UPF calories and on the variety index was also evaluated. Multivariate and decision tree analyses were applied to compare consumers for their 3V rule profile similarities and differences, and to look for impacts of the presence or absence of children. Customers' purchases were far from the 3V rule, with a median of 41% animal and 61% UPF calories and a median variety index of 25% (compared to the consumer with the highest index set to 100%). There was no difference in purchased animal and UPF percentages neither according to seasons nor the presence of children. However, the presence of children was associated with a higher variety index (+33%, P < 0.05). Finally, the more the consumers purchased varied, the less they purchased UPFs. Compared to the average food basket, a 3V-based basket would cost 4.6% less. To make this basket accessible to everyone and to orientate consumer's purchasing behaviors toward more sustainable and healthier products, and hence food systems, hypermarkets should promote healthy eating and reassess their food offerings.

Pipe Break Rate Assessment While Considering Physical and Operational Factors: A Methodology based on Global Positioning System and Data-Driven Techniques

An accurate prediction of pipes failure rate plays a substantial role in the management of Water Distribution Networks (WDNs). In this study, a field study was conducted to register pipes break and relevant causes in the WDN of Yazd City, Iran. In this way, 851 water pipes were incepted and localized by the Global Positioning System (GPS) apparatus. Then, 1033 failure cases were reported in the eight zones of understudy WDN during March-December 2014. Pipes break rate (BRP) was calculated using the depth of pipe installation (hP), number of failures (NP), the pressure of water pipes in operation (P), and age of pipe (AP). After completing a pipe break database, robust Artificial Intelligence models, namely Multivariate Adaptive Regression Spline (MARS), Gene-Expression Programming (GEP), and M5 Model Tree were employed to extract precise formulation for the pipes break rate estimation. Results of the proposed relationships demonstrated that the MARS model with Coefficient of Correlation (R) of 0.981 and Root Mean Square Error (RMSE) of 0.544 provided more satisfying efficiency than the M5 model (R = 0.888 and RMSE = 1.096). Furthermore, statistical results indicated that MARS and GEP models had comparatively at the same accuracy level. Explicit equations by Artificial Intelligence (AI) models were satisfactorily comparable with those obtained by literature review in terms of various conditions: physical, operational, and environmental factors and complexity of AI models. Through a probabilistic framework for the pipes break rate, the results of first-order reliability analysis indicated that the MARS technique had a highly satisfying performance when MARS-extracted-equation was assigned as a limit state function.

Developing Multivariate Survival Trees with a Proportional Hazards Structure

In this paper, a tree-structured method is proposed to extend Classification and Regression Trees (CART) algorithm to multivariate survival data, assuming a proportional hazard structure in the whole tree. The method works on the marginal survivor distributions and uses a sandwich estimator of variance to account for the association between survival times. The Wald-test statistics is defined as the splitting rule and the survival trees are developed by maximizing between-node separation. The proposed method intends to classify patients into subgroups with distinctively different prognosis. However, unlike the conventional tree-growing algorithms which work on a subset of data at every partition, the proposed method deals with the whole data set and searches the global optimal split at each partition. The method is applied to a prostate cancer data and its performance is also evaluated by several simulation studies.