Son YJ, et al. Healthc Inform Res. 2010 Dec;16(4):253-259. http://dx.doi.org/10.4258/hir.2010.16.4.253

Korean student nurses may be exposed to stress caused by their future employment (employment stress). The aim of this study was to investigate the effects of a Laughter Program on psychological stress, by assessing salivary cortisol and the subjective happiness of student nurses in order to relieve employment stress. A quasi-experimental, non-equivalent, control-group, and pre-test/post-test was conducted in 4th year student nurses (n = 48) from 2 universities in Korea at a time when participants' final exams and job searches were simultaneously occurring. Physiological stress (salivary cortisol), and psychological stress measured using modified Cornell Medical Index questionnaire and the Subjective Happiness Scale were used to determine the effects of the program. The results of the study showed that the Laughter Program was effective in relieving employment stress and increasing the subjective well-being of student nurses. Psychological stress (p < 0.001), salivary cortisol levels (p < 0.001), and subjective happiness (p < 0.001) were statistically significantly improved after the intervention compared with before the Laughter Program. This study is an effective evidence-based intervention to reduce student nurses employment stress and improve subjective happiness.

As studies analyzing the networks and relational structures of research topics in academic fields emerge, studies that apply methods of network and relationship analysis, such as social network analysis (SNA), are drawing more attention. The purpose of this study is to explore the interaction of medical education subjects in the framework of complex systems theory using SNA and to analyze the trends in medical education. The authors extracted keywords using Medical Subject Headings terms from 9,379 research articles (162,866 keywords) published in 1963–2015 in PubMed. They generated an occurrence frequency matrix, calculated relatedness using Weighted Jaccard Similarity, and analyzed and visualized the networks with Gephi software. Newly emerging topics by period units were identified as historical trends, and 20 global-level topic clusters were obtained through network analysis. A time-series analysis led to the definition of five historical periods: the waking phase (1963–1975), the birth phase (1976–1990), the growth phase (1991–1996), the maturity phase (1997–2005), and the expansion phase (2006–2015). The study analyzed the trends in medical education research using SNA and analyzed their meaning using complex systems theory. During the 53-year period studied, medical education research has been subdivided and has expanded, improved, and changed along with shifts in society’s needs. By analyzing the trends in medical education using the conceptual framework of complex systems theory, the research team determined that medical education is forming a sense of the voluntary order within the field of medicine by interacting with social studies, philosophy, etc., and establishing legitimacy and originality.

Moon M, et al. Healthc Inform Res. 2017 Jan;23(1):43-52. https://doi.org/10.4258/hir.2017.23.1.43

Background: A machine learning (ML) system is able to construct algorithms to continue improving predictions and generate automated knowledge through data-driven predictors or decisions. Objective: The purpose of this study was to compare six ML methods (random forest (RF), logistics regression, linear support vector machine (SVM), polynomial SVM, radial SVM, and sigmoid SVM) of predicting falls in nursing homes (NHs). Methods: We applied three representative six-ML algorithms to the preprocessed dataset to develop a prediction model (N = 60). We used an accuracy measure to evaluate prediction models. Results: RF was the most accurate model (0.883), followed by the logistic regression model, SVM linear, and polynomial SVM (0.867). Conclusions: RF was a powerful algorithm to discern predictors of falls in NHs. For effective fall management, researchers should consider organizational characteristics as well as personal factors. Recommendations for Future Research: To confirm the superiority of ML in NH research, future studies are required to discern additional potential factors using newly introduced ML methods.