Predictive modelling of student dropout risk: Practical insights from a South Korean distance university.

Distance education supports lifelong learning and empowers individuals in rapidly changing societal conditions, yet it encounters high dropout rates due to a range of individual and societal obstacles. This study addresses the challenge of creating a practical prediction model by analyzing extensive real-world time-point data from a well-established online university in Seoul. Covering 144,540 instances from 2018 to 2022, the study integrates diverse datasets to compare the accuracy of models based on longitudinal, semester-wise, and gender-specific datasets. The demographic, academic, and online metrics identified significant dropout indicators, including age (particularly when binned), residential area, specific occupations, GPA, and LMS log metrics, using a stepwise backward elimination process. The study revealed that, despite societal changes, recent data from the last four semesters can be effectively used for stable prediction training. Gender-based analysis showed different factors influencing dropout risk for males and females. The Light Gradient Boosting Machine (LGBM) algorithm excelled in prediction accuracy, with the ROC-AUC metric affirming its superiority. However, logistic regression also showed its competitive performance and offered in-depth interpretation. In South Korea's distinct educational setting, merging advanced algorithms like LGBM with the interpretive strength of logistic regression is key for effective student support strategies.

Dropout risk and effectiveness of retention strategies in the Memory Advancement by Intranasal Insulin in Type 2 Diabetes (MemAID) Clinical Trial.

BACKGROUND: Effective recruitment and retention strategies are essential in clinical trials. METHODS: The MemAID trial consisted of 12 visits during 24 weeks of intranasal insulin or placebo treatment and 24 weeks of post-treatment follow-up in older people with and without diabetes. Enhanced retention strategies were implemented mid study to address high drop-out rate. Baseline variables used in Cox regression models to identify dropout risk factors were: demographics and social characteristics, functional measures, metabolic and cardiovascular parameters, and medications. RESULTS: 244 participants were randomized; 13 (5.3%) were discontinued due to adverse events. From the remaining 231 randomized participants, 65 (28.1%) dropped out, and 166 (71.9%) did not. The Non-retention group included 95 participants not exposed to retention strategies, of which 43 (45.2%) dropped out. The Retention group included 136 participants exposed to enhanced retention strategies, of which 22 (16.2%) dropped out. Dropout risk factors included being unmarried, a longer diabetes duration, using oral antidiabetics as compared to not using, worse executive function and chronic pain. After adjusting for exposure to retention strategies, worse baseline executive function composite score (p = 0.001) and chronic pain diagnosis (p = 0.032) were independently associated with a greater risk of dropping out. The probability of dropping out decreased with longer exposure to retention strategies and the dropout rate per month decreased from 4.1% to 1.8% (p = 0.04) on retention strategies. CONCLUSIONS: Baseline characteristics allow prediction of dropping out from a clinical trial in older participants. Retention strategies has been effective at minimizing the impact of dropout-related risk factors. TRIAL REGISTRATION: Clinical trials.gov NCT2415556 3/23/2015 (www. CLINICALTRIALS: gov).

Adolescence dropout risk predictors: Family structure, mental health, and self-esteem.

This study investigated the predictive roles of family structure, mental health, and self-esteem in dropout risk among school-going adolescents in the Ibadan Municipality of Oyo State, Nigeria. A quantitative research design approach was adopted. A total of 287 school-going adolescents with consistent record of absenteeism were randomly selected from 14 schools in the Ibadan Municipality. A single adapted questionnaire divided into sections was used to collect data. The hypotheses raised were tested using the Pearson's product-moment correlation and multiple regression analysis. The study established that the relationship between dropout risk, lack of family structure (r = 0.491, n = 287, p < 0.05), mental health (r = 0.373, n = 287, p < 0.05), and self-esteem (r = 0.428, n = 287, p < 0.05) of the participants was significant. Furthermore, the joint influence of the predictive variables (family structure, mental health, and self-esteem) was also significant on dropout risk (R = 0.489, adjusted R2 of 0.398). The study concludes that dropout risk among school-going adolescents can be safeguarded with factors such as family structure, mental health, and self-esteem as guided against. Hence, the family structure, mental health, and self-esteem are very crucial if the upsurge of school dropout that is bedeviling the society will be reduced to bearable level or eradicated.

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

BACKGROUND: Despite 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. OBJECTIVES: The 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. DESIGN: Predictions 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. SETTINGS: College of Nursing in a private university in an urban Midwest city, USA. PARTICIPANTS: Seven 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. METHODS: Eight 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. RESULTS: Using 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. CONCLUSIONS: This 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.

Prospective longitudinal associations between household smoke exposure in early childhood and antisocial behavior at age 12.

Young children exert little control over household tobacco smoke exposure, which is considered a developmental neurotoxicant. Using the Quebec Longitudinal Study birth cohort, we examine prospective associations between early childhood smoke exposure and later antisocial behavior. Parents of 1035 children reported on the presence of household smokers at seven follow-ups from ages 1.5 to 7.5. At age 12, children self-reported on five aspects of early antisocial dispositions. After adjusting for confounders, every standard deviation increase in household smoke exposure was prospectively associated with a 19% standard deviation unit increase in conduct problems (ß=0.07; 95% confidence interval [CI] from 0.04 to 0.09), a 11% standard deviation unit increase in proactive aggression (ß=0.04; 95% CI from 0.01 to 0.07), a 13% standard deviation unit increase in reactive aggression (ß=0.07; 95% CI from 0.03 to 0.12), a 14% standard deviation unit increase in school indiscipline (ß=0.13; 95% CI from 0.05 to 0.20), and a 10% standard deviation unit increase in dropout risk (ß=0.07; 95% CI from 0.01 to 0.12). These long-term findings warrant fostering parental awareness of developmental risks by policy-makers/health practitioners. School curricula can equally integrate these ideas into their curriculum.

Early dropout predictive factors in obesity treatment.

Diet attrition and failure of long term treatment are very frequent in obese patients. This study aimed to identify pre-treatment variables determining dropout and to customise the characteristics of those most likely to abandon the program before treatment, thus making it possible to modify the therapy to increase compliance. A total of 146 outpatients were consecutively enrolled; 73 patients followed a prescriptive diet while 73 followed a novel brief group Cognitive Behavioural Treatment (CBT) in addition to prescriptive diet. The two interventions lasted for six months. Anthropometric, demographic, psychological parameters and feeding behaviour were assessed, the last two with the Italian instrument VCAO Ansisa; than, a semi-structured interview was performed on motivation to lose weight. To identify the baseline dropout risk factors among these parameters, univariate and multivariate logistic models were used. Comparison of the results in the two different treatments showed a higher attrition rate in CBT group, despite no statistically significant difference between the two treatment arms (P = 0.127). Dropout patients did not differ significantly from those who did not dropout with regards to sex, age, Body Mass Index (BMI), history of cycling, education, work and marriage. Regardless of weight loss, the most important factor that determines the dropout appears to be a high level of stress revealed by General Health Questionnaire-28 items (GHQ-28) score within VCAO test. The identification of hindering factors during the assessment is fundamental to reduce the dropout risk. For subjects at risk, it would be useful to dedicate a stress management program before beginning a dietary restriction.