Introduction: According the studies that revealed the absence of specific and applied appropriate standards related to medical records, incompatibility of medical record departments with standards are prevalent, and also according consensus opinions of Iranian experts -wide universities of medical sciences on medical records activities, conducting a research on determining, confirming, and approving medical records standards and finding an evaluation mechanism and appropriate tools according to pioneer countries and through the national appears to be necessary.

Methods: In this descriptive-analytic study, we collected performance standards, evaluation mechanisms, and evaluation checklist for health information (medical record) of USA, Australia, Canada, New Zealand, Lebanon, Zambia, and Southern Africa through the email, literature review, Fax and Internet. Also we asked views of faculty members of medical record departments in 17 Iranian universities and Health Deputy experts about evaluation of medical record departments through a questionnaire related to proposed model (2005- 2006).

Results: Our findings showed that maximum agreements were focused on staffing and directing standards (66/7%). Staff development and education standards accounted for the minimum agreements (52/67%). More than 50% of experts believed that the current evaluation system is not desired and 99% were agreed on developing special sub- committees. Nearly all of experts (96/9%) agreed on adopting self-assessment process before on-site survey. 

Conclusion: Consensus of some medical records experts and faculty members to proposed model for medical records evaluation standards -despite availability of medical record standards determined by Iran Ministry of Health- should be attributed to shortcoming in available standards, evaluation mechanisms, and evaluation checklist.

Introduction: Nowadays, assisted reproductive technologies are widely used to treat infertility in couples. Studies indicate that the rate of premature birth after using Assisted Reproductive Technologies has been increased as compared to normal pregnancies. The purpose of our study was predicting premature birth in pregnant women via Assisted Reproductive Technologies using artificial neural networks.

Methods: In this retrospective study, initially 45 variables were identified as effective factors for prediction of premature birth in pregnant women via Assisted Reproductive Technologies and data of 130 women were extracted using clinical records in Sarem hospital in Tehran from 1998 to 2014 in October and November, 2014. The most important variables were identified as effective variables using feature selection algorithm and decision tree in SPSS Clementine. Multi-Layer Perceptron network was designed to predict the premature birth in Matlab software. Confusion matrix was used for evaluation in order to calculate accuracy, sensitivity and specificity.

Results: We identified fifteen effective features using feature selection algorithm and decision tree as inputs of the neural networks. Multi-Layer Perceptron network was designed and evaluated. The accuracy, sensitivity and specificity of the test data were 87.2%, 80.0% and 88.2%, respectively and for the total data were 95.4%, 95.0% and 95.5%, respectively.

Conclusion: According to the results, designed neural network for predicting premature birth in pregnant women via Assisted Reproductive Technologies can be helpful in prevention of premature birth complications.