Applying data mining techniques to extract hidden patterns about breast cancer survival in an Iranian cohort study

Background: breast cancer survival has been analyzed by many standard data mining algorithms. A group of these algorithms belonged to the decision tree category. Ability of the decision tree algorithms in terms of visualizing and formulating of hidden patterns among study variables were main reasons to apply an algorithm from the decision tree category in the current study that has not studied already

Methods: the classification and regression trees [CART] was applied to a breast cancer database contained information on569 patients in 2007-2010. The measurement of Gini impurity used for categorical target variables was utilized. The classification error that is a function of tree size was measured by 10-fold cross-validation experiments. The performance of created model was evaluated by the criteria as accuracy, sensitivity and specificity

Results: the CART model produced a decision tree with 17 nodes, 9 of which were associated with a set of rules. The rules were meaningful clinically. They showed in the if-then format that Stage was the most important variable for predicting breast cancer survival. The scores of accuracy, sensitivity and specificity were: 80.3%, 93.5% and 53%, respectively

Conclusions: the current study model as the first one created by the CART was able to extract useful hidden rules from a relatively small size dataset

Problems and obstacles in implementation of picture archiving and communication system [PACS] in urmia imam khomeini hospital

Picture Archiving and Communication System [PACS] provides the possibility of electronic transfer and storage of medical images in different units of treatment and educational centers. The aim of this study was to determine the problems and obstacles related to implementation of PACS in Urmia Imam Khomeini hospital. In this descriptive study, 88 physicians, nurses, radiographers, health information managers and executive managers in Urmia Imam Khomeini hospital were assessed. The sample size was accordance to the size of population; so, the census method was used for sampling. Data collection was performed by two questionnaires. The validity and reliability of the questionnaires were confirmed by content validity and test-retest method respectively. The four areas composed of human resources, management, organizational and technological factors which evaluated with those questionnaires. The data analysis was conducted based on the descriptive analysis. Results in four areas showed that the knowledge of employees and managers with the concept of PACS was 43.1% and 83.3% respectively. The findings also indicated that the interest of employees and managers to implementing such a system were 80% and 66.7% respectively. Based on the opinions of both managers and employees, it was found that the lack of awareness of hospital executive managers was the most important obstacle in the implementation of the PACS. Considering the progress in the medical informatics domain and applications of health information systems, it is necessary that the executive managers apply such systems in hospitals