Early Identification Of At-risk Students Research Articles

A Flipped Class to Support the Success of At-Risk Students

Early identification of at-risk students for timely intervention is critical to prevent non-completion of study programs. This article proposes a flipped class framework to support the academic success of at-risk students in an undergraduate Calculus course. It comprises three main components of setting, conduct, and monitoring. A flipped support class was implemented as periodic sessions throughout the learning semester over six consecutive semesters for the selected total of 560 at-risk students. At-risk students who attended the flipped support class reported a higher passing percentage than those who did not, in each of the six semesters. A strong mathematics foundation contributed to the likelihood of passing the course; however, it can be further increased by attending more hours of the flipped support class.

Improving Student Retention in Institutions of Higher Education through Machine Learning: A Sustainable Approach

Effective student retention in higher education represents a critical challenge to institutional stability and educational quality. This study addresses this challenge by integrating machine learning and artificial intelligence techniques in the context of sustainability education. To achieve this, data are collected from a representative cohort of students undergoing extensive cleaning and pre-processing. Additionally, a pre-trained neural network model is implemented, adjusting key parameters. The model evaluation was based on relevant metrics and error analysis, demonstrating that integrating machine learning and artificial intelligence allows early identification of at-risk students and the provision of personalized interventions. This study addresses contemporary student retention challenges in three critical areas: the transition to online education, student mental health and well-being, and equity and diversity in access to higher education. These challenges are addressed through specific strategies based on data analysis and machine learning, thus contributing to overcoming them in the context of higher education. Additionally, this study prioritizes ethical concerns when applying these technologies, ensuring integrity and equity in decision-making related to student retention. Together, this work presents an innovative approach that uses machine learning and artificial intelligence to improve student retention within the framework of educational sustainability, highlighting its transformative potential in higher education.

Strengthening School Management with Digital Education Technology to Improve the Quality of Educational Output

Digital educational technologies enhance teaching methodologies through multimedia resources, interactive simulations and real-time assessment tools. Teachers can leverage adaptive learning algorithms to adapt learning to the individual needs of students, driving engagement, understanding, and academic success. Moreover, data-driven decision-making is facilitated by digital educational technologies. Educators gain valuable insights into student performance through sophisticated analytics, enabling them to identify areas for improvement and implement targeted interventions. This approach supports early identification of at-risk students and ensures that a comprehensive support system is in place. In addition, digital education technologies promote collaboration and communication between various stakeholders, including teachers, students, parents and administrators. This enables real-time feedback, collaboration between parents and teachers, and remote learning opportunities, creating a participatory and dynamic educational environment. In conclusion, embracing digital education technology has great potential to strengthen school management and meet the demands of 21st century quality education. By automating administrative tasks, improving teaching methodologies, enabling data-driven decision-making and promoting collaboration, educational institutions can adapt to evolving challenges and deliver high-quality educational outcomes. Embracing these technological advances is important for preparing students for the demands of the digital age and ensuring a successful future.

Can Simulation Predict NCLEX-RNⓇ Success?

Undergraduate nursing programs frequently utilize computer-based predictor exams to identify whether students have high or low chances in achieving licensure. This study examines the relationship between undergraduate nursing student simulation performance and NCLEX-RNⓇ success. Data from a baccalaureate graduating class of 58 nursing students who completed multiple, high-fidelity simulation experiences 12-20 months prior to NCLEX-RNⓇ testing was assessed. In an Obstetric clinical course, students completed five simulations and were evaluated using the Creighton Competency Evaluation InstrumentⓇ. Logistic regression was completed to identify significant relationships between student simulation performance and NCLEX-RNⓇ outcomes. Three of the five simulation experiences were statistically significant (p < .05) in predicting NCLEX-RNⓇ success. The results of this study indicate that simulation performance may be another method of predicting NCLEX-RNⓇ success. Implementation of this finding may provide means for early identification of at-risk students, allowing for targeted remediation interventions to best prepare them for later success on licensure examination.

Challenging the Core Assumption of Chronic Absenteeism: Are Excused and Unexcused Absences Equally Useful in Determining Academic Risk Status?

In response to the Every Student Succeeds Act (ESSA) (2015), 36 U.S. states have adopted chronic absenteeism as an indicator of school quality and student success. It is also being increasingly utilized within schools to identify students at risk for future educational problems, as research consistently shows that early absences are related to later achievement issues. By leveraging readily available attendance records, schools can identify students at risk of poor outcomes early in their educational lives and provide them with supports before challenges worsen. Despite its pervasive use, major theoretical assumptions underlying this indicator have never been validated. The current study represents the first empirical test of the most basic assumption of chronic absenteeism—that all absences from school are equally useful in providing diagnostic information to determine future risk status. To test the diagnostic utility of different absence types across the early elementary grades, this study employed ROC analyses with administrative data from a large, urban school district. Findings indicate that only unexcused absences provide diagnostic accuracy in determining future achievement status in the early elementary grades, whereas excused absences provide no diagnostic accuracy and actually dampen the ability of unexcused absences to determine students’ achievement risk status when used in conjunction with them. These results have implications for researchers, policymakers, and practitioners and necessitate additional empirical studies that test the underlying assumptions of chronic absenteeism to ensure that it is being used both effectively and ethically in the early identification of at-risk students.

Sustainable Math Education of Female Students during a Pandemic: Online versus Face-to-Face Instruction

The present study was driven by the assumption that a key feature of sustainable education is its ability to preserve standards of quality even amid unforeseen, potentially disruptive events. It asked whether students’ academic success in math general education courses differed between synchronous online (during the COVID-19 pandemic) and face-to-face (before the pandemic), under the ancillary assumption that computational competency, a pillar of sustainable education, shapes enduring success in a variety of professional fields. As the early identification of at-risk students and ensuing remedial interventions can bring about academic success, the study also investigated the predictive validity of students’ initial performance in online and face-to-face math courses. Two general education courses (introductory calculus and statistics), taught by the same instructor, were selected. Class grades did not differ between instructional modes, thereby providing no evidence for the widespread concern that the switch to the online mode had damaged learning. Yet, during the semester, test and homework performance were differentially sensitive to modes of instruction. Furthermore, both test and homework performance during the first half of the semester predicted class grades in online courses, whereas only test performance predicted class grades in face-to-face courses. These results suggest that sustainable math education in times of crisis is feasible and that educators’ consideration of the differential predictive value of test and homework performance may aid its attainment.

Predicting nursing baccalaureate program graduates using machine learning models: A quantitative research study

BackgroundDespite powerful efforts to maximize nursing school enrollment, schools and colleges of nursing are faced with high rates of attrition and low rates of completion. Early identification of at-risk students and the factors associated with graduation outcomes are the main foci for the studies that have addressed attrition and completion rates in nursing programs. Machine learning has been shown to perform better in prediction tasks than traditional statistical methods. ObjectivesThe purpose of this study was to identify adequate models that predict, early in a students career, if an undergraduate nursing student will graduate within six college years. In addition, factors related to successful graduation were to be identified using several of the algorithms. DesignPredictions were made at five time points: the beginning of the first, second, third, fourth years, and the end of the sixth year. Fourteen scenarios were built for each machine learning algorithm through the combinations of different variable sections and time points. SettingsCollege of Nursing in a private university in an urban Midwest city, USA. ParticipantsSeven hundred and seventy-three full time, first time, and degree-seeking students who enrolled from 2004 through 2012 in a traditional 4-year baccalaureate nursing program. MethodsEight popular machine learning algorithms were chosen for model construction and comparison. In addition, a stacked ensemble method was introduced in the study to boost the accuracy and reduce the variance of prediction. ResultsUsing one year of college academic performance, the graduation outcome can be correctly predicted for over 80% of the students. The prediction accuracy can reach 90% after the second college year and 99% after the third year. Among all the variables, cumulative grade points average (GPA) and nursing course GPA are the most influential factors for predicting graduation. ConclusionsThis study provides a potential mode of data-based tracking system for nursing students during their entire baccalaureate program. This tracking system can serve a large number of students automatically to provide customized evaluation on the dropout risk students and enhance the ability of a school or college to more strategically design school-based prevention and interventional services.

Dropping out from Higher Education in Germany an Empirical Evaluation of Determinants for Bachelor Students

AbstractWithdrawing from university is a complex decision-making process, during which several conditions and problems from different areas of life and study accumulate and affect each other. This study is based on the National Educational Panel Study (NEPS), which includes a wide range of information on study course and students’ characteristics, and aims at providing an encompassing analysis of determinants influencing students’ dropout decision. Determinants can be categorized into demographic and family background, the financial situation of students, their prior education, institutional determinants, as well as motivation and satisfaction with study. Both, a bivariate analysis, as well as a logistic regression model with LASSO regularization identify many important determinants already known before or at the beginning of the study, such as prior education and satisfaction related variables, allowing early identification of at-risk students and the implementation of prevention programs.

Implementing Interprofessional Education: Initial results from the first interprofessional fellowship in integrative health and medicine

High attrition rate in first year health science courses including allied health is a common problem in the higher education sector. This systematic review aims to explore the tools used by educators in identifying first year, at-risk students studying health science courses within higher education. The review identifies the tools and investigates their effectiveness in identifying at-risk students.A mixed-methods systematic review of original research was undertaken exploring the tools used or developed for identification of the at-risk health science students in their first year of study. Following databases were searched: Academic OneFile, CINAHL PLUS, ERIC, ScienceDirect and Google Scholar.Collectively, the included studies (n = 13) revealed that a combination of both academic and non-academic factors are most effective in identifying at-risk students. All 13 identified studies developed tools based on one or more of the following three categories: those examining the personal background, academic preparedness and the student perceptions of their own abilities and readiness.With students enrolling into health science courses coming from various diverse academic and personal backgrounds, the tools identified in this systematic review could enhance early identification of at-risk students, thereby enabling educational institutions to take timely educational interventions to support them.

NCLEX-RN® in Every Laboratory and Simulation: Technology Can Help

Undergraduate nursing programs frequently utilize computer-based predictor exams to identify whether students have high or low chances in achieving licensure. This study examines the relationship between undergraduate nursing student simulation performance and NCLEX-RNⓇ success. Data from a baccalaureate graduating class of 58 nursing students who completed multiple, high-fidelity simulation experiences 12-20 months prior to NCLEX-RNⓇ testing was assessed. In an Obstetric clinical course, students completed five simulations and were evaluated using the Creighton Competency Evaluation InstrumentⓇ. Logistic regression was completed to identify significant relationships between student simulation performance and NCLEX-RNⓇ outcomes. Three of the five simulation experiences were statistically significant (p < .05) in predicting NCLEX-RNⓇ success. The results of this study indicate that simulation performance may be another method of predicting NCLEX-RNⓇ success. Implementation of this finding may provide means for early identification of at-risk students, allowing for targeted remediation interventions to best prepare them for later success on licensure examination.

Centralized student performance prediction in large courses based on low-cost variables in an institutional context

An increasing number of higher education institutions have deployed learning management systems (LMSs) to support learning and teaching processes. Accordingly, data-driven research has been conducted to understand the impact of student participation within these systems on student outcomes. However, most research has focused on small samples or has used variables that are expensive to measure, which limits its generalizability. This article presents a prediction model based on low-cost variables and a sophisticated algorithm, to predict early which students attending large classes (with more than 50 enrollments) who are at risk of failing a course. Therefore, it will enable instructors and educational managers to carry out early interventions to prevent course failure. The results overperform other approaches in terms of accuracy, cost, and generalization. Moreover, LMS usage information improved the model by up to 12.28% in terms of root-mean-square error, enabling better early identification of at-risk students.

Effectiveness of a Retention Program to Improve Performance During the First Semester of a Doctor of Physical Therapy Program.

To meet the expanding need for physical therapists universities are under increasing pressure to enroll, educate, and train physical therapists. Poor academic performance can result in student dismissal from a physical therapy program. The purpose of this study is to determine if implementation of a retention program would improve student academic performance in the foundational science curriculum in a physical therapy program. A prospective observational cohort design was used. The retention program centered on three approaches: 1. Early identification of at-risk students. 2. Supplemental instruction in Human Anatomy. 3. Offering peer tutoring for the foundational science courses. A significant association existed between the implementation of the retention program and the reduction of dismissals from the Fall Semester of 2012 to the fall 2013 semesters. Implementation of a retention program had a beneficial effect on decreasing student dismissals in a physical therapy program.

The role of teaching presence and student participation in Spanish blended courses

ABSTRACTThis chapter describes a study of a blended language course that combines face-to-face (F2F) instructional time with an online component. The purpose of the study is to understand how teachers and students exploit the complementarity of the two delivery formats to improve the learning experience. The study first examines how the presence of an online component affects the F2F portion of the course by comparing it to a corresponding section of the same course taught entirely F2F. The findings of this first part of the study show major differences between the two delivery formats regarding teaching strategies and teaching presence. The second part of the study uses LMS data to analyze student participation in the online component of the blended course. Data were gathered to measure active participation, passive participation and continuity. The results show that online behaviors distinguish less successful students from more successful ones, and that there is a strong correlation between low levels of online participation and low grades in the course. Continuity proved to be the strongest predictor variable for success in the course. The results have important implications for course design and the use of learning analytics for the early identification of at-risk students.

A Novel Approach to Assessing Professionalism in Preclinical Medical Students Using Multisource Feedback Through Paired Self- and Peer Evaluations

ABSTRACTPhenomenon: Professionalism is integral to the role of the physician. Most professionalism assessments in medical training are delayed until clinical rotations where multisource feedback is available. This leaves a gap in student assessment portfolios and potentially delays professional development. Approach: A total of 246 second-year medical students (2013–2015) completed self- and peer assessments of professional behaviors in 2 courses following a series of Team-Based Learning exercises. Correlation and regression analyses were used to examine the alignment or misalignment in the relationship between the 2 types of assessments. Four subgroups were formed based on observed patterns of initial self- and peer assessment alignment or misalignment, and subgroup membership stability over time was assessed. A missing data analysis examined differences between average peer assessment scores as a function of selective nonparticipation. Findings: Spearman correlation demonstrated moderate to strong correlation between self-assessments completed alone (no simultaneous peer assessment) and self-assessments completed at the time of peer assessments (ρ = .59, p < .0001) but weak correlation between the two self-assessments and peer assessments (alone: ρ = .13, p < .013; at time of peer: ρ = .21, p < .0001). Generalized estimating equation models revealed that self-assessments done alone (p < .0001) were a significant predictor of self-assessments done at the time of peer. Course was also a significant predictor (p = .01) of self-assessment scores done at the time of peer. Peer assessment score was not a significant predictor. Bhapkar's test revealed subgroup membership based on the relationship between self- and peer ratings was relatively stable across Time 1 and Time 2 assessments (χ2 = 0.83, p = .84) for all but one subgroup; members of the subgroup with initially high self-assessment and low peer assessment were significantly more likely to move to a new classification at the second measurement. A missing data analysis revealed that students who completed all self-assessments had significantly higher average peer assessment ratings compared to students who completed one or no self-assessments with a difference of –0.32, 95% confidence interval [–0.48, –0.15]. Insights: Multiple measurements of simultaneous self- and peer assessment identified a subgroup of students who consistently rated themselves higher on professionalism attributes relative to the low ratings given by their peers. This subgroup of preclinical students, along with those who elected to not complete self-assessments, may be at risk for professionalism concerns. Use of this multisource feedback tool to measure perceptual stability of professionalism behaviors is a new approach that may assist with early identification of at-risk students during preclinical years.

Multiple Mini-Interview Performance Predicts Academic Difficulty in the PharmD Curriculum

Objective. To identify admissions variable prognostics for academic difficulty in the PharmD curriculum to use for admissions determinations and early identification of at-risk students. Methods. Retrospective multivariate analysis of 2008-2012 admission data were linked with academic records to identify students with academic difficulty (ie, those with Ds, Fs, delayed progression). The influence of prepharmacy grade point average (GPA), composite Pharmacy College Admission Test (PCAT) score, multiple-mini interview (MMI) score, age, credit hours, state residence, and prior degree on academic difficulty was estimated using multivariate logistic regression. Results. Students' (n=587) prepharmacy GPA, composite PCAT score, mean MMI score, and age were 3.6, 72.0, 5.5, 22.8 (SD=4.14 years), respectively. Students having a GPA <3.25, PCAT score <60th percentile, or MMI score <4.5, were approximately 12-, 7-, and 3-times more likely, respectively, to experience academic difficulty than those with a GPA ≥ 3.75, PCAT score >90, or MMI score of 5-6. Conclusion. Using GPA, PCAT, and MMI performance can predict academic difficulty and assist in the early identification of academically at-risk PharmD students.

Closing the Loop between Access and Success: Early Identification of At-risk Students and Monitoring as Key Strategies Used by a South African University

Closing the Loop between Access and Success: Early Identification of At-risk Students and Monitoring as Key Strategies Used by a South African University

Closing the Loop between Access and Success: Early Identification of At-risk Students and Monitoring as Key Strategies Used by a South African University

Sosibo, Z.; and Katiya, M.; (2015). Closing the Loop between Access and Success: Early Identification of At-risk Students and Monitoring as Key Strategies Used by a South African University. International Journal of Educational Sciences 01/2015; 8(2):271-279.

Leveraging Technology to Improve Developmental Mathematics Course Completion: Evaluation of a Large-Scale Intervention

This study hypothesizes that course passing rates in remedial mathematics classes can be improved through early identification of at-risk students using a department-wide midterm, followed by a mandated set of online intervention assignments incorporating immediate and elaborate feedback for all students identified as at-risk by their midterm score. A sample of over 20,000 students was used to evaluate the intervention, which was implemented department-wide over several semesters in all developmental mathematics courses at a large diverse urban community college. The intervention was assessed by evaluating course passing rates (a proxy for passing rates on standardized exit examinations) and student time spent in the intervention lab. Students from semesters prior to the intervention were used as a control, with fall semesters compared to fall semesters and spring to spring, to control for possible variation in student enrollment. Highly statistically significant differences were found between student passing rates pre- versus post-intervention, with passing rates improving by as much as 50%. The size of this study and the diversity of the student population involved suggests that results are likely widely applicable to other institutions across the country. In particular, the interventions tested were chosen specifically because they can reasonably be implemented even across relatively large and diffuse departments with limited resources.

Pre-college Matriculation Risk Profiles and Alcohol Consumption Patterns During the First Semesters of College

Excessive alcohol consumption represents a significant concern on U.S. college campuses, and there is a need to identify students who may be at risk for engaging in risky alcohol use. The current study examined how variables measured prior to college matriculation, specifically alcohol-related decision-making variables drawn from the Theory of Reasoned Action (i.e., alcohol expectancies, attitudes, and normative beliefs), were associated with patterns of alcohol use prior to and throughout the first semesters of college. Participants were 392 undergraduate students (56% female) from a large Northeastern U.S. university. Decision-making variables were assessed prior to college matriculation, and alcohol use was measured with five assessments before and throughout freshman and sophomore semesters. Latent profile analysis was used to identify types of students with distinct patterns of decision-making variables. These decision-making profiles were subsequently linked to distinct patterns of alcohol use using latent transition analysis. Four distinct decision-making profiles were found and were labeled "Anti-Drinking," "Unfavorable," "Mixed," and "Risky." Five drinking patterns were observed and included participants who reported consistently low, moderate, or high rates of alcohol use. Two patterns described low or non-drinking at the pre-college baseline with drinking escalation during the measurement period. Students' likelihood of following the various drinking patterns varied according to their decision-making. Findings suggest the early identification of at-risk students may be improved by assessing decision-making variables in addition to alcohol use. The findings also have implications for the design of early identification assessments to identify at-risk college students and for the targeting of alcohol prevention efforts to students based on their alcohol-related attitudes and beliefs.

Standardized Mastery Content Assessments for Predicting NCLEX-RN Outcomes

Nurse educators need predictors of failure for early intervention. This study investigated the predictability of fundamentals, mental health, and pharmacology standardized assessment scores to identify the risk of baccalaureate students' failure on the NCLEX-RN. Using logistic regression the pharmacology assessment score was predictive with 73.7% accuracy. Use of the pharmacology assessment can assist in early identification of at-risk students in efforts to better prepare for the NCLEX-RN examination.