ABSTRACT
Emergency departments have a basic role in saving the human life in any accidents. Developing an information system with an accurate documentation facilitates evaluating emergencies activities and providing quality care. The main objective of this study was to determine the rate of complete documentation and compliance of legal aspects in documentation of Emergency's Medical Records in teaching hospitals of Zabol University of Medical Sciences. In this descriptive-analytical research, 500 Emergency's Medical Records were selected by random sampling method. Two checklists were applied to gather all the information. First checklist measured completion of data element in Emergency's Medical Records forms and second checklist analyzed the legal aspect Compliance. Since the first checklist used the standard medical record's data item of Ministry of health, it was validated. Reliability and validity of second checklist were verified by of medical records experts' opinions. The statistical significance was set to 0.05. The statistical package SPSS were used for the analysis [Chi-square test]. The amount of data recorded by physician, nurses, and reception staffs were 25.4, 52.6 and 67.1 percent, respectively. In general, legal aspect Compliance was 44.7 percent. Comparing hospitals' legal aspect Compliance ratio showed a statistically significant difference [P=0.0001]. Our study showed that Emergency's Medical Records were incomplete and legal aspects were not complied in medical record documentation. These deficiencies lead to loss of patients' information. Therefore authorities, doctors, and medical experts should pay more attention to completeness of documentation of emergency's patient records in teaching hospitals of Zabol University of Medical Sciences
ABSTRACT
Cardiovascular diseases are among the most common diseases in all societies. Using data mining techniques to generate predictive models to identify those at risk for reducing the effects of the disease is very helpful. The main purpose of this study was to predict the risk of myocardial infarction by Decision Tree based on the observed risk factors. The present work was an analytical study conducted on a database containing 350 records. Data were obtained from patients admitted to Shahid Rajaei specialized cardiovascular hospital, Iran, in 2011. Data were collected using a four-sectioned data collection form. Data analysis was performed using SPSS statistical software version 12 by CRISP methodology. In the modeling section decision tree and Neural Network were used. The results of the data mining showed that the variables of high blood pressure, hyperlipidemia and tobacco smoking were the most critical risk factors of myocardial infarction. The accuracy of the decision tree model on the data was shown to be as 93/4%. The best created model was decision tree C5.0. According to the created rules, it can be predicted which patient with new specified features may affected by myocardial infarction