Data-driven system to predict academic grades and dropout.
Ontology highlight
ABSTRACT:
SUBMITTER: Rovira S
PROVIDER: S-EPMC5308611 | biostudies-literature | 2017
REPOSITORIES: biostudies-literature
Publications
Data-driven system to predict academic grades and dropout.
Rovira Sergi S Puertas Eloi E Igual Laura L
PloS one 20170214 2
Nowadays, the role of a tutor is more important than ever to prevent students dropout and improve their academic performance. This work proposes a data-driven system to extract relevant information hidden in the student academic data and, thus, help tutors to offer their pupils a more proactive personal guidance. In particular, our system, based on machine learning techniques, makes predictions of dropout intention and courses grades of students, as well as personalized course recommendations. M ...[more]
Similar Datasets
Project description:The present study addressed concerns over the high risk of university students' academic failure. It examined how perceived academic control and academic emotions predict undergraduate students' academic success, conceptualized as both low dropout intention and high achievement (indicated by GPA). A cross-sectional survey was administered to 883 undergraduate students across all disciplines of a German STEM orientated university. The study additionally compared freshman students (N = 597) vs. second-year students (N = 286). Using structural equation modeling, for the overall sample of undergraduate students we found that perceived academic control positively predicted enjoyment and achievement, as well as negatively predicted boredom and anxiety. The prediction of dropout intention by perceived academic control was fully mediated via anxiety. When taking perceived academic control into account, we found no specific impact of enjoyment or boredom on the intention to dropout and no specific impact of all three academic emotions on achievement. The multi-group analysis showed, however, that perceived academic control, enjoyment, and boredom among second-year students had a direct relationship with dropout intention. A major contribution of the present study was demonstrating the important roles of perceived academic control and anxiety in undergraduate students' academic success. Concerning corresponding institutional support and future research, the results suggested distinguishing incoming from advanced undergraduate students.
| S-EPMC5339277 | biostudies-literature
Project description:OBJECTIVE An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. To date, research has focused on developing risk prediction models for CDI that work well across institutions. However, this one-size-fits-all approach ignores important hospital-specific factors. We focus on a generalizable method for building facility-specific models. We demonstrate the applicability of the approach using electronic health records (EHR) from the University of Michigan Hospitals (UM) and the Massachusetts General Hospital (MGH). METHODS We utilized EHR data from 191,014 adult admissions to UM and 65,718 adult admissions to MGH. We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 4,836 features from patients at UM and 1,837 from patients at MGH. We used L2 regularized logistic regression to learn the models, and we measured the discriminative performance of the models on held-out data from each hospital. RESULTS Using the UM and MGH test data, the models achieved area under the receiver operating characteristic curve (AUROC) values of 0.82 (95% confidence interval [CI], 0.80-0.84) and 0.75 ( 95% CI, 0.73-0.78), respectively. Some predictive factors were shared between the 2 models, but many of the top predictive factors differed between facilities. CONCLUSION A data-driven approach to building models for estimating daily patient risk for CDI was used to build institution-specific models at 2 large hospitals with different patient populations and EHR systems. In contrast to traditional approaches that focus on developing models that apply across hospitals, our generalizable approach yields risk-stratification models tailored to an institution. These hospital-specific models allow for earlier and more accurate identification of high-risk patients and better targeting of infection prevention strategies. Infect Control Hosp Epidemiol 2018;39:425-433.
| S-EPMC6421072 | biostudies-literature
Project description:Many data-driven patient risk stratification models have not been evaluated prospectively. We performed and compared the prospective and retrospective evaluations of 2 Clostridioides difficile infection (CDI) risk-prediction models at 2 large academic health centers, and we discuss the models' robustness to data-set shifts.
| S-EPMC10024639 | biostudies-literature
Project description:Many insurance companies have considerable prebariatric surgery requirements despite a lack of evidence for improved clinical outcomes. The hypothesis of this study is that insurance-specific requirements will be associated with a decreased progression to surgery and increased delay in time to surgery.Retrospective data collection was performed for patients undergoing bariatric surgery evaluation from 2010-2015. Patients who underwent surgery (SGY; n = 827; mean body mass index [BMI] 49.1) were compared with those who did not (no-SGY; n = 648; mean BMI: 49.4). Univariate and multivariate analysis were performed to identify specific co-morbidity and insurance specific predictors of surgical dropout and time to surgery.A total of 1475 patients using 12 major insurance payors were included. Univariate analysis found insurance requirements associated with surgical drop out included longer median diet duration (no-SGY = 6 mo; SGY = 3 mo; P<.001); primary care physician letter of necessity (P<.0001); laboratory testing (P = .019); and evaluation by cardiology (P<.001), pulmonology (P<.0001), or psychiatry (P = .0003). Using logistic regression to control for co-morbidities, longer diet requirement (odds ratio [OR] .88, P<.0001), primary care physician letter (OR .33, P<.0001), cardiology evaluation (OR .22, P = .038), and advanced laboratory testing (OR 5.75, P = .019) independently predicted surgery dropout. Additionally, surgical patients had an average interval between initial visit and surgery of 5.8±4.6 months with significant weight gain (2.1 kg, P<.0001).Many prebariatric surgery insurance requirements were associated with lack of patient progression to surgery in this study. In addition, delays in surgery were associated with preoperative weight gain. Although prospective and multicenter studies are needed, these findings have major policy implications suggesting insurance requirements may need to be reconsidered to improve medical care.
| S-EPMC5469712 | biostudies-literature
Project description:BackgroundMissing data are a notable problem in Alzheimer's disease clinical trials. One cause of missing data is participant dropout. The Research Attitudes Questionnaire is a 7-item instrument that measures an individual's attitudes toward biomedical research, with higher scores indicating more favorable attitudes. The objective of this study was to describe the performance of the Research Attitudes Questionnaire over time and to examine whether Research Attitudes Questionnaire scores predict study dropout and other participant behaviors that affect trial integrity.MethodsThe Research Attitudes Questionnaire was collected at baseline and weeks 26 and 52 from each member of 119 participant/study partner dyads enrolled in a Phase 2, randomized, double-blind, placebo-controlled mild-to-moderate Alzheimer's disease clinical trial. Within-subject longitudinal analyses examined change in Research Attitudes Questionnaire scores over time in each population. Logistic regression analyses that controlled for trial arm and clustering in trial sites were used to assess whether baseline Research Attitudes Questionnaire scores predicted trial completion, study medication compliance, and enrollment in optional substudies.ResultsParticipants and study partners endorsed statistically similar ratings on the Research Attitudes Questionnaire that were stable over time. Participants with baseline Research Attitudes Questionnaire scores above 28.5 were 4.7 (95% confidence interval = 1.01 to 21.95) times as likely to complete the trial compared to those with lower scores. Applying the same cutoff, baseline study partner Research Attitudes Questionnaire scores were similarly able to predict study completion (odds ratio = 4.2, 95% confidence interval = 1.71 to 10.32). Using a score cutoff of 27.5, higher participant Research Attitudes Questionnaire scores predicted study medication compliance (odds ratio = 5.85, 95% confidence interval = 1.34 to 25.54). No relationship was observed between Research Attitudes Questionnaire score and participation in optional substudies.ConclusionThis brief instrument that measures research attitudes may identify participants at risk for behaviors that cause missing data.
| S-EPMC8009810 | biostudies-literature
Project description:In this study we modelled possible causes and consequences of student burnout and engagement on academic efficacy and dropout intention in university students. Further we asked, can student engagement protect against the effects of burnout? In total 4,061 university students from Portugal, Brazil, Mozambique, the United Kingdom, the United States of America, Finland, Serbia, and Macao SAR, Taiwan participated in this study. With the data collected we analyzed the influence of Social Support, Coping Strategies, and school/course related variables on student engagement and burnout using structural equation modeling. We also analyzed the effect of student engagement, student burnout, and their interaction, on Academic Performance and Dropout Intention. We found that both student engagement and burnout are good predictors of subjective academic performance and dropout intention. However, student burnout suppresses the effect of student engagement on these variables. This result has strong implications for practitioners and administrators. To prevent student dropout, it is not enough to promote student engagement-additionally, and importantly, levels of student burnout must be kept low. Other variables such as social support and coping strategies are also relevant predictors of student engagement and burnout and should be considered when implementing preventive actions, self-help and guided intervention programs for college students.
| S-EPMC7595383 | biostudies-literature
Project description:Fewer women than men pursue careers in science, technology, engineering and mathematics (STEM), despite girls outperforming boys at school in the relevant subjects. According to the 'variability hypothesis', this over-representation of males is driven by gender differences in variance; greater male variability leads to greater numbers of men who exceed the performance threshold. Here, we use recent meta-analytic advances to compare gender differences in academic grades from over 1.6 million students. In line with previous studies we find strong evidence for lower variation among girls than boys, and of higher average grades for girls. However, the gender differences in both mean and variance of grades are smaller in STEM than non-STEM subjects, suggesting that greater variability is insufficient to explain male over-representation in STEM. Simulations of these differences suggest the top 10% of a class contains equal numbers of girls and boys in STEM, but more girls in non-STEM subjects.
| S-EPMC6156605 | biostudies-literature
Project description:BackgroundThe development of high-throughput sequencing and analysis has accelerated multi-omics studies of thousands of microbial species, metagenomes, and infectious disease pathogens. Omics studies are enabling genotype-phenotype association studies which identify genetic determinants of pathogen virulence and drug resistance, as well as phylogenetic studies designed to track the origin and spread of disease outbreaks. These omics studies are complex and often employ multiple assay technologies including genomics, metagenomics, transcriptomics, proteomics, and metabolomics. To maximize the impact of omics studies, it is essential that data be accompanied by detailed contextual metadata (e.g., specimen, spatial-temporal, phenotypic characteristics) in clear, organized, and consistent formats. Over the years, many metadata standards developed by various metadata standards initiatives have arisen; the Genomic Standards Consortium's minimal information standards (MIxS), the GSCID/BRC Project and Sample Application Standard. Some tools exist for tracking metadata, but they do not provide event based capabilities to configure, collect, validate, and distribute metadata. To address this gap in the scientific community, an event based data-driven application, OMeta, was created that allows users to quickly configure, collect, validate, distribute, and integrate metadata.ResultsA data-driven web application, OMeta, has been developed for use by researchers consisting of a browser-based interface, a command-line interface (CLI), and server-side components that provide an intuitive platform for configuring, capturing, viewing, and sharing metadata. Project and sample metadata can be set based on existing standards or based on projects goals. Recorded information includes details on the biological samples, procedures, protocols, and experimental technologies, etc. This information can be organized based on events, including sample collection, sample quantification, sequencing assay, and analysis results. OMeta enables configuration in various presentation types: checkbox, file, drop-box, ontology, and fields can be configured to use the National Center for Biomedical Ontology (NCBO), a biomedical ontology server. Furthermore, OMeta maintains a complete audit trail of all changes made by users and allows metadata export in comma separated value (CSV) format for convenient deposition of data into public databases.ConclusionsWe present, OMeta, a web-based software application that is built on data-driven principles for configuring and customizing data standards, capturing, curating, and sharing metadata.
| S-EPMC6322262 | biostudies-literature
Project description:Prediction of patient-centered outcomes in hospitals is useful for performance benchmarking, resource allocation, and guidance regarding active treatment and withdrawal of care. Yet, their use by clinicians is limited by the complexity of available tools and amount of data required. We propose to use Disjunctive Normal Forms as a novel approach to predict hospital and 90-day mortality from instance-based patient data, comprising demographic, genetic, and physiologic information in a large cohort of patients admitted with severe community acquired pneumonia. We develop two algorithms to efficiently learn Disjunctive Normal Forms, which yield easy-to-interpret rules that explicitly map data to the outcome of interest. Disjunctive Normal Forms achieve higher prediction performance quality compared to a set of state-of-the-art machine learning models, and unveils insights unavailable with standard methods. Disjunctive Normal Forms constitute an intuitive set of prediction rules that could be easily implemented to predict outcomes and guide criteria-based clinical decision making and clinical trial execution, and thus of greater practical usefulness than currently available prediction tools. The Java implementation of the tool JavaDNF will be publicly available.
| S-EPMC3974677 | biostudies-literature
Project description:Academic self-concept (ASC) is comprised of individual perceptions of one's own academic ability. In a cross-sectional quasi-representative sample of 3,779 German elementary school children in grades 1 to 4, we investigated (a) the structure of ASC, (b) ASC profile formation, an aspect of differentiation that is reflected in lower correlations between domain-specific ASCs with increasing grade level, (c) the impact of (internal) dimensional comparisons of one's own ability in different school subjects for profile formation of ASC, and (d) the role played by differences in school grades between subjects for these dimensional comparisons. The nested Marsh/Shavelson model, with general ASC at the apex and math, writing, and reading ASC as specific factors nested under general ASC fitted the data at all grade levels. A first-order factor model with math, writing, reading, and general ASCs as correlated factors provided a good fit, too. ASC profile formation became apparent during the first two to three years of school. Dimensional comparisons across subjects contributed to ASC profile formation. School grades enhanced these comparisons, especially when achievement profiles were uneven. In part, findings depended on the assumed structural model of ASCs. Implications for further research are discussed with special regard to factors influencing and moderating dimensional comparisons.
| S-EPMC5436832 | biostudies-other