RESUMEN
Purpose: We applied machine learning to study associations between regional body fat distribution and diabetes mellitus in a population of community adults in order to investigate the predictive capability. We retrospectively analyzed a subset of data from the published Fasa cohort study using individual standard classifiers as well as ensemble learning algorithms. Methods: We measured segmental body composition using the Tanita Analyzer BC-418 MA (Tanita Corp, Japan). The following features were input to our machine learning model: fat-free mass, fat percentage, basal metabolic rate, total body water, right arm fat-free mass, right leg fat-free mass, trunk fat-free mass, trunk fat percentage, sex, age, right leg fat percentage, and right arm fat percentage. We performed classification into diabetes vs. no diabetes classes using linear support vector machine, decision tree, stochastic gradient descent, logistic regression, Gaussian naïve Bayes, k-nearest neighbors (k = 3 and k = 4), and multi-layer perceptron, as well as ensemble learning using random forest, gradient boosting, adaptive boosting, XGBoost, and ensemble voting classifiers with Top3 and Top4 algorithms. 4661 subjects (mean age 47.64 ± 9.37 years, range 35 to 70 years; 2155 male, 2506 female) were analyzed and stratified into 571 and 4090 subjects with and without a self-declared history of diabetes, respectively. Results: Age, fat mass, and fat percentages in the legs, arms, and trunk were positively associated with diabetes; fat-free mass in the legs, arms, and trunk, were negatively associated. Using XGBoost, our model attained the best excellent accuracy, precision, recall, and F1-score of 89.96%, 90.20%, 89.65%, and 89.91%, respectively. Conclusions: Our machine learning model showed that regional body fat compositions were predictive of diabetes status.
RESUMEN
Introduction: Simulation-based education (SBE) is an instructional approach that aims to accurately recreate real-life scenarios and engage learners in the practical application of lesson content. By replicating critical elements of clinical situations, SBE facilitates a deeper understanding and better preparation for managing such conditions in actual clinical practice. SBE offers promising prospects for improving medical education and patient care in various settings, such as outpatient clinics. Therefore, this scoping review aims to determine to what extent the most effective components and standards of the simulation have been considered in outpatient education. Methods: The present scoping review adheres to the guidelines outlined in the "Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) checklist" and the "Joanna Briggs Institute (JBI) Reviewers' Manual". This review focused on articles that specifically focused on the use of simulation in outpatient education. Google Scholar, PubMed, Scopus, Embase, and ERIC were searched for keywords related to simulation, ambulatory care, outpatient clinics, and medical education from January 1, 2001, to August 12, 2023. Results: The search indicated 513 articles, which were narrowed down by title and abstract relatedness. Twenty-nine articles entered the study's second phase, and after reviewing their full text, nine articles that explicitly reported simulation use in outpatient education remained. Based on the findings of eligible articles, the ten most frequent components of SBE that should be considered and followed discussed. These features were training facilitators, pre-briefing sessions, the type of simulation techniques, the site of simulation participation, the simulation duration, unit of participation, extent of direct participation, Simulation fidelity, feedback, and debriefing and reflection. Conclusion: SBE is a contemporary method of practical training for medical students that involves realistic modeling or simulation of clinical situations. It enhances learning effectiveness and provides a safe, educational atmosphere for teaching and learning. Designing simulations adhering to established standards and carefully considering essential components improves efficiency and effectiveness.
RESUMEN
INTRODUCTION: Designing, developing, and implementing a course without assessing and prioritizing instructional needs may result in inefficiency due to the disregard for the actual needs of the target population. The present study aimed to determine and prioritize medical students' instructional needs regarding Massive Open Online Courses (MOOCs) at Shiraz University of Medical Sciences. METHODS: This survey study was carried out in three stages (2020-2021) using the Delphi technique. Purposive and snowball sampling methods were used to select the instructors. The students were selected through simple random sampling. The first round of the Delphi technique involved a questionnaire consisting of one open-ended question, completed by 49 basic/clinical faculty members and 47 senior medical students. In the second round, a 5-point Likert scale-based questionnaire was used to prioritize the instructional needs. The reliability of the questionnaire was verified by Cronbach's alpha coefficient. In the third round, a focus group was used. A total of six expert faculty members and one senior medical student were invited to the focus group session to prioritize the needs. Data were analyzed using Friedman's non-parametric ranking test in SPSS version 26. RESULTS: Ten instructional needs priorities were extracted, including common pharmacotherapies (antibiotics and narcotics), prescriptions, physiology, anatomy, physical examination, electrocardiography interpretation, radiography, computed tomography scans, serum electrolyte disorders, and cardiovascular and internal (endocrine and metabolic) diseases. The chi-squared calculated value (715.584) indicated a significant difference in the importance of the questionnaire's questions (P < 0.001). These questions did not have equal value, and the importance, from the respondent's point of view and the observed distribution of ranks, was not the output of a random factor. CONCLUSIONS: The findings of this study can be used to design MOOCs, revise instructional programs, and adapt the curriculum to meet the needs of general practitioners, which will, in turn, help meet the medical needs of the general population.