Artificial Intelligence Applications in Type 2 Diabetes Mellitus Care: Focus on Machine Learning Methods / 대한의료정보학회지

OBJECTIVES: The incidence of type 2 diabetes mellitus has increased significantly in recent years. With the development of artificial intelligence applications in healthcare, they are used for diagnosis, therapeutic decision making, and outcome prediction, especially in type 2 diabetes mellitus. This study aimed to identify the artificial intelligence (AI) applications for type 2 diabetes mellitus care. METHODS: This is a review conducted in 2018. We searched the PubMed, Web of Science, and Embase scientific databases, based on a combination of related mesh terms. The article selection process was based on Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Finally, 31 articles were selected after inclusion and exclusion criteria were applied. Data gathering was done by using a data extraction form. Data were summarized and reported based on the study objectives. RESULTS: The main applications of AI for type 2 diabetes mellitus care were screening and diagnosis in different stages. Among all of the reviewed AI methods, machine learning methods with 71% (n = 22) were the most commonly applied techniques. Many applications were in multi method forms (23%). Among the machine learning algorithms applications, support vector machine (21%) and naive Bayesian (19%) were the most commonly used methods. The most important variables that were used in the selected studies were body mass index, fasting blood sugar, blood pressure, HbA1c, triglycerides, low-density lipoprotein, high-density lipoprotein, and demographic variables. CONCLUSIONS: It is recommended to select optimal algorithms by testing various techniques. Support vector machine and naive Bayesian might achieve better performance than other applications due to the type of variables and targets in diabetes-related outcomes classification.

Adult Stem Cells of Orofacial Origin: Current Knowledge and Limitation and Future Trend in Regenerative Medicine

Stem cell research is one of the most rapidly expanding field of medicine which provides significant opportunities for therapeutic and regenerative applications. Different types of stem cells have been isolated investigating their accessibility, control of the differentiation pathway and additional immunomodulatory properties. Bulk of the literature focus has been on the study and potential applications of adult stem cells (ASC) because of their low immunogenicity and reduced ethical considerations. This review paper summarizes the basic available literature on different types of ASC with special focus on stem cells from dental and orofacial origin. ASC have been isolated from different sources, however, isolation of ASC from orofacial tissues has provided a novel promising alternative. These cells offer a great potential in the future of therapeutic and regenerative medicine because of their remarkable availability at low cost while allowing minimally invasive isolation procedures. Furthermore, their immunomodulatory and anti-inflammatory potential is of particular interest. However, there are conflicting reports in the literature regarding their particular biology and full clinical potentials. Sound knowledge and higher control over proliferation and differentiation mechanisms are prerequisites for clinical applications of these cells. Therefore, further standardized basic and translational studies are required to increase the reproducibility and reduce the controversies of studies, which in turn facilitate comparison of related literature and enhance further development in the field.

effect of Ramadan fasting on thyroid hormones in 9-13 years old pre-menarche girls

Muslims fast from dawn to dusk during Ramadan. The effects of prolonged food deprivation on endocrine hormones have been studied in healthy adults but no previous study has investigated this effect on children. This study aimed to evaluate the feasible changes in serum level of thyroxin [T3], tetraiodothyronin [T4], thyroid stimulating hormone [TSH] and body composition in pre-menarche girls. This cohort study was performed through Ramadan 2012. We enrolled fifty-eight 9-13 years old girls [weight 34.20 +/- 7.96 kg, height 142.01 +/- 7.76 cm] in two groups from [31 and 27 in fasted and non-fasted groups, respectively] prior to Ramadan until afterwards. Weight and height of the subjects were measured using standard methods, and then Body Mass Index [BMI] was calculated. Body composition was measured using Bio Impedance Analyzer [BIA] method. Serum concentrations of T3, T4 and TSH hormones were measured by Radio Immunoassay [RIA]. Paired t-test was used to compare result of each group before and after Ramadan. Independent t-test was used to compare two groups together. Tanner intervention variable was controlled by generalized linear models intervening test. SPSS.11 software was used for data analysis. Ramadan fasting induces a significant decrease in BMI and weight on fasted group [P=0.005, P=0.044, respectively] while a significant increase was observed in non-fasted group [P<0.001]. Although, T3 decreased significantly by fasting [P<0.001], it remained in the normal range. Hence, T4 decreased and TSH increased slightly in both groups. According to our findings, despite a significant reduction of T3 in fasting group, variation in thyroid hormones level remained in the normal range during Ramadan fasting