Categories Of Predictors Research Articles

Objective sleep monitoring at home in older adults: A scoping review.

Inadequate sleep in older adults is linked to health issues such as frailty, cognitive impairment and cardiovascular disorders. Maintaining regular sleep patterns is important for healthy aging, making effective sleep monitoring essential. While polysomnography is the gold-standard for diagnosing sleep disorders, its regular use in home settings is limited. Alternative objective monitoring methods in the home can offer insights into natural sleep patterns and factors affecting them without the limitations of polysomnography. This scoping review aims to examine current technologies, sensors and sleep parameters used for home-based sleep monitoring in older adults. It also aims to explore various predictors and outcomes associated with sleep to understand the factors of sleep monitoring at home. We identified 54 relevant articles using PubMed, Scopus, Web of Science and an AI tool (Research Rabbit), with 48 studies using wearable technologies and eight studies using non-wearable technologies. Further, six types of sensors were utilized. The most common technology employed was actigraphy wearables, while ballistocardiography and electroencephalography were less common. The most frequent objective parameters of sleep measured were total sleep time, wakeup after sleep onset and sleep efficiency, with only six studies evaluating sleep architecture in terms of sleep stages. Additionally, six categories of predictors and outcomes associated with sleep were analysed, including Health-related, Environmental, Interventional, Behavioural, Time and Place, and Social associations. These associations correlate with total sleep time, wakeup after sleep onset and sleep efficiency, and include in-bed behaviours, exterior housing conditions, aerobic exercise, living place, relationship status, and seasonal thermal environments.

English

Pedotransfer function (PTFs) is widely developed using machine learning algorithms (MLA) and non-linear regression (NLR). Saturated hydraulic conductivity (Ks) is obviously used to regulate water movement in the soil. The objective of the work is to evaluate the accuracy of MLA to predict Ks. Moreover, is to determine the best class of predictors that can be used to predict Ks with little estimation error. Saturated hydraulic conductivity was measured by direct method using the constant head method. In addition, Ks was predicted using PTFs developed by machine learning algorithms including Random Forest Algorithm (RFA), and Gradient Boosting Algorithm (GBA) models with three categories of soil physical predictors. Furthermore, PTFs developed by RFA, and GBA were compared with PTFs developed by NLR models using the same three categories of soil physical predictors. The three categories of soil physical predictors were the following: category-1 refers to sand, silt, and clay “SSC”; category-2 refers to category-1, in addition to bulk density “SSC+BD”; and category-3 refers to category-2, in addition to organic matter “SSC+BD+OM”. The results of error analysis observed that PTFs developed by RFA were more accurate than GBA and NLR models, respectively, for Ks prediction with the three categories of soil physical predictors. Moreover, the category-3 which takes into account sand, silt, clay, bulk density, and organic matter was the best category used to predict Ks using RFA, and NLR models. PTFs developed by machine learning algorithms including RFA, and GBA models can be utilized to predict Ks with little calculation error. However, RFA was greater than GBA for calculating Ks. The efficiency of RFA was associated with the number of soil variables predictors and building classification and regression trees which is more robust than decision trees such as GBA to optimize Ks prediction.

Procurement Planning Process and Organization Performance in the Energy Sector in Kenya: A Case Study of Geothermal Development Company

The aim was to examine procurement planning processes on organization performance at Geothermal Development Company, and establish the influence of supplier selection, need identification on organization performance at the Geothermal Development Company. The study's fundamental anchor theory was goal-setting theory, which is backed by institutional theory and a resource-based view. Utilizing stratified random sampling, using a descriptive research methodology, 232 people were selected as the sample size out of 550. Questionnaires were used in the process of gathering data. Ten randomly chosen employees from the target population participated in the pilot project. SPSS version 27 and basic statistics were used to analyze the quantitative data. Tables were used in the data presentation. Inferential statistics, regression analysis and correlation, were utilized to show the relationships between the variables. The regression is based on the organization's performance and procurement planning process as predictors. The findings demonstrate a positive correlation with R = 0.684 and R2 = 0.573, meaning that changes in each of the predictor categories could account for 57.3% of the variance in the organization’s performance, the variances of the elements not included in this analysis account for the remaining 42.7%. Study recommends that GDC management recognize that procurement planning practices are not static and needs should be determined, tendering procedures should be established, budgets should be estimated, and user departments should be involved. In order to ensure that procurements are successful, GDC management should make sure that appropriate procedures are put in place during planning, with input from procurement staff and the user department, and that progress reports are escalated for required action. Further investigation into other variables is required to account for the remaining change in purchase planning procedures. based on the findings of this investigation, the conclusion, and the advice that came after. This additional research should aim to corroborate the findings of the current study and offer fresh data.

The definition of predictor and outcome variables in mortality prediction models: a scoping review and quality of reporting study

Mortality prediction models are promising tools for guiding clinical decision-making and resource allocation in intensive care units (ICUs). Clearly specified predictor and outcome variables are necessary to enable external validation and safe clinical application of prediction models. The objective of this study was to identify the predictor and outcome variables used in different mortality prediction models in the ICU and investigate their reporting. For this scoping review, MEDLINE, EMBASE, Web of Science, and the Cochrane Central Register of Controlled Trials (CENTRAL) were searched. Studies developed within a general ICU population reporting on prediction models with mortality as a primary or secondary outcome were eligible. The selection criteria were adopted from a review by Keuning et al. Predictor and outcome variables, variable characteristics (defined as units, definitions, moments of measurement and methods of measurement), and publication details (defined as first author, year of publication and title) were extracted from the included studies. Predictor and outcome variable categories were demographics, chronic disease, care logistics, acute diagnosis, clinical examination and physiological derangement, laboratory assessment, additional diagnostics, support and therapy, risk scores, and (mortality) outcomes. A total of 56 mortality prediction models containing 204 unique predictor and outcome variables were included. The predictor variables most frequently included in the models were age (40 times), admission type (27 times), and mechanical ventilation (21 times). We observed that single variables were measured with different units, according to different definitions, at a different moment, and with a different method of measurement in different studies. The reporting of the unit was mostly complete (98% overall, 95% in the laboratory assessment category), whereas the definition of the variable (74% overall, 63% in the chronic disease category) and method of measurement (70% overall, 34% in the demographics category) were most often lacking. Accurate and transparent reporting of predictor and outcome variables is paramount to enhance reproducibility, model performance in different contexts, and validity. Since unclarity about the required input data may introduce bias and thereby affect model performance, this study advocates that prognostic ICU models can be improved by transparent and clear reporting of predictor and outcome variables and their characteristics.

Career Adaptability Across Southeast Asia: A Systematic Review

Southeast Asia has recently seen a number of developments and transformations that requires one to adjust to as the region’s skill requirements are evolving. For some these new changes brings new opportunities, however, for some greater levels of career adaptability is need to manage these new developments and transformations. The necessity of systematically reviewing articles on career adaptability in Southeast Asian nations is made apparent by this particular instance. A systematic review of career adaptability in Southeast Asia was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. About 22 eligible studies were identified. The findings indicated that the most prevalent groups in career adaptability studies were students, followed by working adults. Antecedents such as role modeling and cultural intelligence were identified. Four categories of predictors were identified such as personal, educational, career behavior, and environmental factor. Two categories were identified for the outcomes of career adaptability, namely, personal and career outcomes. Findings revealed that career adaptability offers several beneficial outcomes such as improved employability skills and life satisfaction. Discussion includes conditions faced in Southeast Asian countries and cultural differences. The dearth of studies within multicultural settings calls for further research in exploring career adaptability, as this broaden cultural understanding and awareness of educational and career behaviors pertaining to one’s career adaptability. This study offers important practical implications and recommendations for career counseling practices and policymakers in Southeast Asia that would potentially benefit students and working adults.

First Years Away From Home: Predictors of Engagement in a Self-Directed Prevention Handbook for Caregivers of Transitioning College Students

Caregiver and teen engagement in prevention programs is critical for positive outcomes, but barriers may reduce participation for those who may benefit most. Self-directed programs can reduce some barriers, but little research exists on predictors of engagement in these programs, especially those aimed at college-age youth and their caregivers. This paper describes engagement in a self-administered, paper handbook-based preventive intervention for students leaving home for their first year of college. Data are from the First Years Away from Home randomized controlled trial study. We measured four engagement outcomes: caregiver-reported initiation, caregiver- and student-reported dose, and caregiver-reported student engagement. Aim 1 was to describe caregiver and student engagement in the intervention; Aim 2 was to examine four categories of engagement predictors measured at baseline: sociodemographic, student, and caregiver factors, and caregiver–student relationship quality. Caregivers and students reported engaging with intervention materials, with 80% of caregivers and 77% of students reporting some handbook use. Most caregivers reported students as moderately to highly engaged. Some positive predictors of engagement outcomes included a positive caregiver–student relationship, greater student well-being, and caregiver disapproval of substance use. However, some were less engaged: risk factors for lower engagement included minoritized ethnicity status, student substance use, first-generation college student status, and students with poorer well-being and less positive relationships with their caregiver. Future work should examine ways to better engage families of students who may be entering college with higher levels of risk when creating and implementing interventions aimed at this developmental period.

Investigating the relative role of dispersal and demographic traits in predictive phylogeography

Many studies suggest that aside from environmental variables, such as topography and climate, species‐specific ecological traits are relevant to explain the geographic distribution of intraspecific genetic lineages. Here, we investigated whether and to what extent incorporating such traits systematically improves the accuracy of random forest models in predicting genetic differentiation among pairs of localities. We leveraged available ecological datasets for birds and tested the inclusion of two categories of ecological traits: dispersal‐related traits (i.e. morphology and foraging ecology) and demographic traits (such as species survival rate and generation length). We estimated genetic differentiation from published mitochondrial DNA sequences for 28 species of birds (1578 total genetic samples, 391 localities) in the Atlantic Forest of South America. Aside from the aforementioned ecological traits, we included geographic, topographic and climatic distances between localities as environmental predictors. We then created models using all available data to evaluate model uncertainty both across space and across the different categories of predictors. Finally, we investigated model uncertainty in predicting genetic differentiation individually for each species (a common challenge in conservation biology). Our results show that while environmental conditions are the most important predictors of genetic differentiation, model accuracy largely increases with the addition of ecological traits. Additionally, the inclusion of dispersal traits improves model accuracy to a larger extent than the inclusion of demographic traits. Similar results are observed in models for individual species, although model accuracy is highly variable. We conclude that ecological traits improve predictive models of genetic differentiation, refining our ability to predict phylogeographic patterns from existing data. Additionally, demographic traits may not be as informative as previously hypothesized. Finally, prediction of genetic differentiation for species with conservation concerns may require further careful assessment of the environmental and ecological variation within the species range.

Developing flood mapping procedure through optimized machine learning techniques. Case study: Prahova river basin, Romania

Study regionPrahova river basin located in the central-southern region of Romania. Study focusThis study aims to assess the susceptibility to flooding by using state-of-the-art machine learning and optimization procedures. To achieve this goal, we employed ten flood-related variables as independent variables in our machine learning models. These variables include slope angle, convergence index, distance from the river, elevation, plan curvature, hydrological soil group, lithology, topographic wetness index, rainfall, and land use. We used 158 flood locations as dependent variables in the training of four hybrid models: Deep Learning Neural Network-Statistical Index (DLNN-SI), Particle Swarm Optimization-Deep Learning Neural Network-Statistical Index (PSO-DLNN-SI), Support Vector Machine-Statistical Index (SVM-SI), and Particle Swarm Optimization-Support Vector Machine-Statistical Index (PSO-SVM-SI). Utilizing the Statistical Index method, we calculated coefficients for each flood predictor class or category. New hydrological insights for the regionThe PSO-DLNN-SI model demonstrated the best performance, achieving an AUC-ROC curve of 0.952. It's worth noting that the application of the PSO algorithm significantly enhanced the model's performance. Additionally, it's crucial to highlight that approximately 25 % of the study region exhibits a high to very high susceptibility to flood events. Taking into account the very precise results of the models applied in the present study, we can state that from a hydrological point of view, the current research contributes to a better understanding of the intensity with which floods can affect the different areas of the Prahova river basin.

Risk Factors for Non-Adherence to Medication for Liver Transplant Patients: An Umbrella Review.

Background/Objectives: Liver Transplantation (LT) is the second most common solid organ transplantation. Medication adherence on LT patients is key to avoiding graft failure, mortality, and important quality of life losses. The aim of this study is to identify risk-factors for non-adherence to treatment of liver transplant patients according to reliable published evidence. Methods: An umbrella review within the context of adherence to immunosuppressant medication of LT patients, was conducted. The review was performed in accordance with the principles of the preferred reporting items for systematic reviews and meta-analysis (PRISMA) guidelines. Results: A total of 11 articles were finally included for the review. Non-adherence factors were identified and allocated using the WHO classification of factors for non-adherence. Each of these groups contains a subset of factors that have been shown to influence adherence to medication, directly or indirectly, according to literature findings. Conclusions: The results of the review indicate that sociodemographic factors, factors related to the patient, factors related to the treatment, condition-related and health system-related factors are good categories of predictors for both adherence and non-adherence to immunosuppressive medication in LT patients. This list of factors may help physicians in the treating and recognizing of patients with a potential risk of non-adherence and it could help in the designing of new tools to better understand non-adherence after LT and targeted interventions to promote adherence of LT patients.

The Australian Traumatic Brain Injury Initiative: Systematic Review and Consensus Process to Determine the Predictive Value of Pre-existing Health Conditions for People with Moderate-Severe Traumatic Brain Injury.

The first aim of the Australian Traumatic Brain Injury Initiative (AUS-TBI) encompasses development of a set of measures that comprehensively predict outcomes for people with moderate-severe TBI across Australia. This process engaged diverse stakeholders and information sources across six areas: social, health, and clinical factors; biological markers; treatments; and longer-term outcomes. Here, we report the systematic review of pre-existing health conditions as predictors of outcome for people with moderate-severe TBI. Standardized searches were implemented across databases until March 31, 2022. English-language reports of studies evaluating association between pre-existing health conditions and clinical outcome in at least 10 patients with moderate-severe TBI were included. A predefined algorithm was used to assign a judgement of predictive value to each observed association. The list of identified pre-existing health conditions was then discussed with key stakeholders during a consensus meeting to determine the feasibility of incorporating them into standard care. The searches retrieved 22,217 records, of which 47 articles were included. The process led to identification of 88 unique health predictors (homologized to 21 predictor categories) of 55 outcomes (homologized to 19 outcome categories). Only pre-existing health conditions with high and moderate predictive values were discussed during the consensus meeting. Following the consensus meeting, 5 out of 11 were included (migraine, mental health conditions, ≥4 pre-existing health conditions, osteoporosis, and body mass index [BMI]) as common data elements in the AUS-TBI data dictionary. Upon further discussion, 3 additional pre-existing health conditions were included. These are pre-existing heart disease, frailty score, and previous incidence of TBI.

Time to recovery and its predictors following traumatic injuries among injured victims in Dessie Comprehensive Specialized Hospital, North East of Ethiopia, 2022: a retrospective follow-up study.

Injuries are an extremely important public health problem worldwide. Despite being largely preventable and despite government efforts, injuries continue to be a major public health issue. Thus, the study tends to evaluate the time to recovery and its predictors for traumatic injuries. A hospital-based retrospective follow-up study was used. A total of 329 medical charts were actually reviewed. Traumatic injury victims from January 1, 2018-December 31, 2022 were included, and a simple random sampling technique was utilized. The data was gathered by reviewing medical charts. Data was coded and entered into Epi-Data Manager version 4.6.0.4 statistical software and further analyzed using STATA version 17. Descriptive statistics were performed to see the frequency distribution of variables. A Kaplan-Meier survival estimate and log rank test were performed to plot the overall survival curve and compare the difference in recovery among predictor categories, respectively. A model fitness test was done by using the Cox-Snell residual test and Harrell's C concordance statistic. Finally, a Cox proportional hazard model was fitted to determine the effect of predictors on recovery time from traumatic injuries. The median time to recovery of traumatic injuries was 5 days (IQR: 3-10days), with an overall incidence density of 8.77 per 100 person-days of observation. In the multivariable cox proportional regression model, variables such as being male (AHR: 0.384, 95%CI: 0.190-0.776, P-value: 0.008), the Glasgow coma scale of 13-15 (AHR: 2.563, 95%CI: 1.070-6.139, P-value: 0.035), intentional injury (AHR: 1.934, 95%CI: 1.03-3.632, P-value: 0.040), mild traumatic brain injury (AHR: 2.708, 95%CI: 1.095-6.698, P-value: 0.031), and moderate traumatic brain injury (AHR: 2.253, 95%CI: (1.033-4.911, P-value: 0.041) were statistically significant variables. The median recovery time for traumatically injured respondents was 5 days. Independent predictors such as the Glasgow coma scale, time taken for surgical management, intent of injury, and traumatic brain injury were statistically significant with time to recovery from trauma.

Socio-Economic Predictors of Migration Intentions: Systematic Analysis

Population migration to other cities and countries can significantly impact demographics and fiscal policy, subsequently leading to the weakening of the economy in sending regions. Despite numerous studies demonstrating the significant influence of social and economic factors on the formation of migration intentions, new data in this field continues to emerge, which has not yet been systematically organized. This study aims to systematize and detail the socio-economic predictors of migration intentions through a theoretical review of research, including the latest works. Based on the analyzed literature, five categories of socio-economic predictors of migration intentions were identified: demographic, economic, socio-psychological, political, and cultural. This research contributes to a more detailed understanding of socio-economic predictors of migration intentions, enabling more precise decision-making in the development of government policies aimed at managing migration flows.

Decision Curve Analysis of In-Hospital Mortality Prediction Models: The Relative Value of Pre- and Intraoperative Data For Decision-Making.

Clinical prediction modeling plays a pivotal part in modern clinical care, particularly in predicting the risk of in-hospital mortality. Recent modeling efforts have focused on leveraging intraoperative data sources to improve model performance. However, the individual and collective benefit of pre- and intraoperative data for clinical decision-making remains unknown. We hypothesized that pre- and intraoperative predictors contribute equally to the net benefit in a decision curve analysis (DCA) of in-hospital mortality prediction models that include pre- and intraoperative predictors. Data from the VitalDB database featuring a subcohort of 6043 patients were used. A total of 141 predictors for in-hospital mortality were grouped into preoperative (demographics, intervention characteristics, and laboratory measurements) and intraoperative (laboratory and monitor data, drugs, and fluids) data. Prediction models using either preoperative, intraoperative, or all data were developed with multiple methods (logistic regression, neural network, random forest, gradient boosting machine, and a stacked learner). Predictive performance was evaluated by the area under the receiver-operating characteristic curve (AUROC) and under the precision-recall curve (AUPRC). Clinical utility was examined with a DCA in the predefined risk preference range (denoted by so-called treatment threshold probabilities) between 0% and 20%. AUROC performance of the prediction models ranged from 0.53 to 0.78. AUPRC values ranged from 0.02 to 0.25 (compared to the incidence of 0.09 in our dataset) and high AUPRC values resulted from prediction models based on preoperative laboratory values. A DCA of pre- and intraoperative prediction models highlighted that preoperative data provide the largest overall benefit for decision-making, whereas intraoperative values provide only limited benefit for decision-making compared to preoperative data. While preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for low treatment thresholds up to 5% to 10%, preoperative laboratory measurements become the dominant source for decision support for higher thresholds. When it comes to predicting in-hospital mortality and subsequent decision-making, preoperative demographics, comorbidities, and surgery-related data provide the largest benefit for clinicians with risk-averse preferences, whereas preoperative laboratory values provide the largest benefit for decision-makers with more moderate risk preferences. Our decision-analytic investigation of different predictor categories moves beyond the question of whether certain predictors provide a benefit in traditional performance metrics (eg, AUROC). It offers a nuanced perspective on for whom these predictors might be beneficial in clinical decision-making. Follow-up studies requiring larger datasets and dedicated deep-learning models to handle continuous intraoperative data are essential to examine the robustness of our results.

Understanding Contemporary Career Success: A Critical Review

This article provides a critical review of developments in the literature on career success. We review work from both the organizational psychology (OP) and organizational behavior (OB) disciplines, highlighting the different perspectives, strengths, and weaknesses of each area, and attempt to reconcile these perspectives on career success to suggest productive new research directions. First, the article reflects on conceptualizations of objective and subjective career success and their relative value to the field. We then discuss several categories of career success predictors drawn from economic, sociological, and social-psychological perspectives used in OP and OB. These include human capital, internal and external labor markets, sponsorship and social capital, stable and malleable individual differences, and career self-management behaviors. We provide research suggestions within each of those sections as well as an integrative research agenda built around several emerging issues and theoretical perspectives, encouraging future research on the implications of sustainable careers, career shocks, marginalized group experiences, and alternative employment arrangements for career success.

Spatial model of Dengue Hemorrhagic Fever (DHF) risk: scoping review

BackgroundCreating a spatial model of dengue fever risk is challenging duet to many interrelated factors that could affect dengue. Therefore, it is crucial to understand how these critical factors interact and to create reliable predictive models that can be used to mitigate and control the spread of dengue.MethodsThis scoping review aims to provide a comprehensive overview of the important predictors, and spatial modelling tools capable of producing Dengue Haemorrhagic Fever (DHF) risk maps. We conducted a methodical exploration utilizing diverse sources, i.e., PubMed, Scopus, Science Direct, and Google Scholar. The following data were extracted from articles published between January 2011 to August 2022: country, region, administrative level, type of scale, spatial model, dengue data use, and categories of predictors. Applying the eligibility criteria, 45 out of 1,349 articles were selected.ResultsA variety of models and techniques were used to identify DHF risk areas with an arrangement of various multiple-criteria decision-making, statistical, and machine learning technique. We found that there was no pattern of predictor use associated with particular approaches. Instead, a wide range of predictors was used to create the DHF risk maps. These predictors may include climatology factors (e.g., temperature, rainfall, humidity), epidemiological factors (population, demographics, socio-economic, previous DHF cases), environmental factors (land-use, elevation), and relevant factors.ConclusionsDHF risk spatial models are useful tools for detecting high-risk locations and driving proactive public health initiatives. Relying on geographical and environmental elements, these models ignored the impact of human behaviour and social dynamics. To improve the prediction accuracy, there is a need for a more comprehensive approach to understand DHF transmission dynamics.

Who “phubs”? A systematic meta-analytic review of phubbing predictors

Phubbing (i.e., snubbing someone in face-to-face interactions by focusing on one's phone instead of those present) has increased enormously in recent years and has become a widespread usage phenomenon that is associated with negative consequences, for instance for relationships and friendships. To better understand the predictors of phubbing behavior, the present paper provides a systematic overview of the growing research field. Based on a meta-analytic review of 79 studies and 526 effect sizes, we identified 10 higher-level predictor categories of phubbing behavior: sociodemographics, personality, technology-related norms & experiences, technical equipment, (smart)phone & Internet use, problematic use, well-being, psychopathology, and resilience as well as risk factors. The results of the three-level meta-analysis models indicated that the strongest predictors were problematic use patterns.

Examining the Potential of Sentinel Imagery and Ensemble Algorithms for Estimating Aboveground Biomass in a Tropical Dry Forest

Accurate estimations of aboveground biomass (AGB) in tropical forests are crucial for maintaining carbon stocks and ensuring effective forest management. By combining remote sensing (RS) data with ensemble algorithms, reliable AGB estimates in forests can be obtained. In this context, the freely available Sentinel-1 (S-1 SAR) and Sentinel 2 multispectral imagery (S-2 MSI) data have a significant role in enhancing accurate AGB estimations at a lower cost, which is relevant for the tropical dry forest (TDF) regions where AGB estimation is uncertain or there is a lack of comprehensive exploration. This study aims to address this gap by presenting a cost-effective and reliable AGB estimation approach in the TDF region of Colombia. For this purpose, we modeled and compared the performance of two ensemble algorithms, random forest (RF) and extreme gradient boosting (XGBoost), to estimate AGB using three predictor categories (polarizations/textures, spectral bands/vegetation indices, and a combination of both). We then examined the modeling potential of S-1 SAR and S-2 MSI imagery in predicting forest AGB and subsequently identified the most suitable variables. To construct AGB models’ field data, we employed a clustered distributed sampling approach involving 100 subsample plots, each with an area of 400 m2. Stepwise multiple linear regression was applied to identify suitable predictors from the original satellite bands, vegetation indices, and texture metrics. To produce a map of AGB, predicted AGB values were calculated for every pixel within a specific satellite subscene using the most effective ensemble algorithm. Our study findings show that the RF model, which employed combined predictor sets, displayed superior performance when evaluated against the independent validation set. The RF model successfully estimated AGB with a high degree of accuracy, achieving an R2 value of 0.78 and an RMSE value of 42.25 Mg/ha−1. In contrast, the XGBoost model performed less accurately, obtaining an R2 value of only 0.60 and an RMSE value of 48.41 Mg/ha−1. The results also indicate that S-2 vegetation indices data were more appropriate for this purpose than S-1 texture data. Despite this, S-1 cross-polarized textures were necessary during the dry season for the combined datasets. The top predictive variables for S-2 images were cab and cw, as well as red-edge bands during the wet season. As for S-1 images, texture D_VH _Hom during the dry season was the most important variable for explaining performance. Overall, the proposed approach of using freely available Sentinel data seems to improve the accuracy of AGB estimation in heterogeneous forest cover and, as such, they should be recommended as a data source for forest AGB assessment.

Prediction of Dilatory Behavior in eLearning: A Comparison of Multiple Machine Learning Models

Procrastination, the irrational delay of tasks, is a common occurrence in online learning. Potential negative consequences include higher risk of drop-outs, increased stress, and reduced mood. Due to the rise of learning management systems and learning analytics, indicators of such behavior can be detected, enabling predictions of future procrastination and other dilatory behavior. However, research focusing on such predictions is scarce. Moreover, studies involving different types of predictors and comparisons between the predictive performance of various methods are virtually non-existent. In this study, we aim to fill these research gaps by analyzing the performance of multiple machine learning algorithms when predicting the delayed or timely submission of online assignments in a higher education setting with two categories of predictors: subjective, questionnaire-based variables and objective, log-data based indicators extracted from a learning management system. The results show that models with objective predictors consistently outperform models with subjective predictors, and a combination of both variable types perform slightly better with an accuracy of 70%. For each of these three options, a different approach prevailed (Gradient Boosting Machines for the subjective, Bayesian multilevel models for the objective, and Random Forest for the combined predictors). We conclude that careful attention should be paid to the selection of predictors and algorithms before implementing such models in learning management systems.

Which pupils have access to CLIL? Investigating the schools’ choice for English-based CLIL programmes in Belgium

Despite its non-elitist goals, there is growing concern over the potentially elitist nature of content and language integrated learning (CLIL) programmes in English. Previous European studies have reported more advantaged pupils’ profiles in these programmes compared to regular programmes. It is unclear from the literature however which pupils have access to CLIL programmes based on the choices made at the school level. In order to remedy this gap in the current literature, the present quantitative study analysed all 948 secondary schools in the Flemish Community of Belgium based on three main categories of predictors: home language, socio-economic status (SES) and school size. Resulting of a stepwise logistic regression analysis, only SES and school size appear to be strong predictors of the presence of an English CLIL programme. In a region where low-SES pupils have an average of three-year delay in development in comparison to their high-SES peers (Franck and Nicaise 2018), the identification (and transformation) of these kinds of selective mechanisms is crucial to reaching educational equity. We relate these mechanisms to some specific characteristics of CLIL in the Flemish Community of Belgium, which may also apply, to some extent, to other educational contexts in Europe.

Validated Pretreatment Prediction Models for Response to Neoadjuvant Therapy in Patients with Rectal Cancer: A Systematic Review and Critical Appraisal.

Pretreatment response prediction is crucial to select those patients with rectal cancer who will benefit from organ preservation strategies following (intensified) neoadjuvant therapy and to avoid unnecessary toxicity in those who will not. The combination of individual predictors in multivariable prediction models might improve predictive accuracy. The aim of this systematic review was to summarize and critically appraise validated pretreatment prediction models (other than radiomics-based models or image-based deep learning models) for response to neoadjuvant therapy in patients with rectal cancer and provide evidence-based recommendations for future research. MEDLINE via Ovid, Embase.com, and Scopus were searched for eligible studies published up to November 2022. A total of 5006 studies were screened and 16 were included for data extraction and risk of bias assessment using Prediction model Risk Of Bias Assessment Tool (PROBAST). All selected models were unique and grouped into five predictor categories: clinical, combined, genetics, metabolites, and pathology. Studies generally included patients with intermediate or advanced tumor stages who were treated with neoadjuvant chemoradiotherapy. Evaluated outcomes were pathological complete response and pathological tumor response. All studies were considered to have a high risk of bias and none of the models were externally validated in an independent study. Discriminative performances, estimated with the area under the curve (AUC), ranged per predictor category from 0.60 to 0.70 (clinical), 0.78 to 0.81 (combined), 0.66 to 0.91 (genetics), 0.54 to 0.80 (metabolites), and 0.71 to 0.91 (pathology). Model calibration outcomes were reported in five studies. Two collagen feature-based models showed the best predictive performance (AUCs 0.83-0.91 and good calibration). In conclusion, some pretreatment models for response prediction in rectal cancer show encouraging predictive potential but, given the high risk of bias in these studies, their value should be evaluated in future, well-designed studies.