Cytochrome P450 2C19 (CYP2C19) is a clinically important enzyme involved in the metabolism of therapeutic drugs, including (S)-mephenytoin, omeprazole, proguanil, and diazepam. Individuals are characterized as either extensive metabolizers (EM) or poor metabolizers (PM) on the basis of CYP2C19 enzyme activity. The PM phenotype occurs in 2 -5% of Caucasians, but in 18 -23% of Asians. To clarify the association between CYP2C19 polymorphisms and gastric cancer in Koreans, we investigated CYP2C19 genotypes (CYP2C19*1, *2, and *3) in 109 patients with gastric cancer and 211 controls. Normal (CYP2C19*1) and defective alleles were detected with polymerase chain reaction/restriction enzyme analysis. CYP2C19 has three hereditary genotypes: homozygous EM, with high enzymatic activity; heterozygous EM, with moderate enzymatic activity; and PM, with no enzyme activity. We found that CYP2C19 heterozygous EM is more closely associated with gastric cancer than is homozygous EM. Because the CYP2C19 genotype varies in Koreans, a genotyping test is desirable to prevent gastropathy recurrence in patients before their doses of omeprazole are reduced during maintenance therapy.

When observing behaviors of special-needs students, on average, typical behaviors of common propensity are observed along with unspecific behaviors. Unlike behaviors that are generally known, information regarding unspecific behaviors is insufficient. For an education or guidance regarding the unspecific behaviors, collection and management of data regarding the unspecific behaviors of special-needs students are needed. In this paper, a consultation management model based on behavior classification of special-needs students using machine learning is proposed. It is a model that provides data to a user by collecting, classifying and managing the behavior data by letting the machine learn the data regarding the unspecific behaviors of special-needs students that are not typical and well known. Since it requires data regarding various behaviors of special-needs students, the data set shall be organized using the behavior pattern data of special-needs students that currently exists, and the data shall be learned by the proposed model. Web-based machine learning model that collects behaviors of special-needs students in real-time is proposed in order to collect the behavior pattern data regarding the unspecific behaviors of special-needs students. The data can be input using the proposed model, and the user can use it through web-browser. The data can be easily input and revised using the proposed model in any environment that the internet can be accessed. The utilization of data analysis result can be enhanced through the use of data list and tools such as a graph through a web-browser, and the accuracy can be enhanced by learning the result that has been acquired by comparing it with previous data by connecting to the database. The test has been performed by arbitrarily applying unspecific behaviors that are not stored in the database, and the forecast model has accurately classified and grouped the input data. Also, it has been verified that it is possible to accurately distinguish and classify the behaviors through the feature data of the behaviors even if there are some errors in the input process. In future, the research of real-time data collection and tailored education index data: the common items need to be organized as a data by recording a class time of special schools or special classes and analyzing the behavior patterns of multiple special-needs students in real-time.

No abstract