---

Social changes have cajoled the need to the updated information. These information majorly obtained from medical records of patients, are characteristically very important. Radiographies as part of medical records of patients, are considered as medical documents due to their worth and efficiency. In the present analytical-descriptive study, conducted in training-treatment centers of Tehran in 1997 through completed questionnaires, the filing, retrieval and delivering of radiography documents to the applicants is evaluated. Post comparison with standards of American college of radiology indicated that these documents are not filed in proper conditions and the same rules are not followed in delivering them.

---

Introduction:Considering the present situation, while utilizing various software programs in different hospitals, different data are inserted and stored, in the system some of which have no considerable value.

Methodology:The present research, descriptive and cross-sectional in nature, was carried out to consider the extent of utilizing the software programs of Medical Record Departments in the universities of medical sciences in Tehran whose Medical Record Departments are computerized. The data was collected by a check- list and analyzed using descriptive statistical procedures.

Results: The extent of utilizing software programs of Medical Record DepaJiments in most hospitals of Iran University of Medical Sciences is very low (40%) and low (40%). In most hospitals of Tehran University of Medical Sciences it is very low (40%) and low (40%) and in all hospital of Shahid Beheshti University of Medical Sciences it is very low (30%) and low (70%) and in all hospitals in the study it is low (55%).

 Conclusion: The rate of the scant benefits of the software in Medical record departments, indicates that regret fully the available software don't have the necessary and sufficient qualification and they can't supply the requests of hospital's medical record department as desired.

---

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.

---

Introduction: Registration of information obtained from laboratory findings, is an important method of transferring the results by laboratory professionals and can be of great help to diagnosis patient's clinical problems. Determination of data elements of this part has an important role in designing an electronic health records system. This study, aimed to determine the minimum data set of laboratory reporting system.

Methods: The participants of this cross-sectional, descriptive applied study, conducted in the first half of 2015, consisted of 95 laboratory staff working in Shahid Rajaee Cardiovascular, Medical and Research Center in Tehran. Data was collected using a researcher made questionnaire consisting of 11 parts the validity and reliability of which were determined through content validity and test_ retest method, respectively. The data were analyzed using SPSS software.

Results: According to the findings, the highest mean scores were related to final diagnosis (9/6), test result (9/4), test date (9), insurance credit date (8/4), and kind of anesthesia (8/7) while the lowest mean scores were related to referring physician's address (3/8), test tools (3/3) and Social History (5/3).

Conclusion: Considering the significance of laboratory data and information in the diagnosis and treatment of patients and the role of information systems in collecting, processing and distributing this information, it is crucial to pay attention to the minimum set of data related to these reports such as demographic, administrative, clinical, insurance, anesthesia and laboratory, observation and interpretation for exchanging with electronic health record system.

---

Introduction: Big volume of patient’s medical data is one of the medical error reasons in coronary care unit (CCU). The purpose of this study was the designing a system that can monitored the patient’s vital sign continuously and when there are abnormal, producing alarms and proposed appropriate medical interventions according to the patient’s conditions in CCU.

 Methods: This was application-development study that done in cross-sectional method in Shahid Rajai hospital at Tehran in 2015. 15 physicians and 15 nurses of CCU were considered as non-random purposively sampling. MEAN.js technology and MIMIC II Physionet’s database were used for system designing.

Results: Normal and abnormal ranges of Vital signs were assessed according to the environmental and population conditions in this study. Variety of therapeutic interventions due to the patients’ vital signs changing was identified with their priorities. The results showed that the clinical decision support system (CDSS) had accuracy (94/68 %), sensitivity (82/60 %) and specificity (100 %) in proposing of proper interventions and had (92/92 %) accuracy, (80 %) sensitivity and (100 %) specificity in producing of timely alarms.

Conclusion: There are several factors that impact on determining of normal and abnormal ranges of vital signs and interventions priorities. The results showed that CDSS can help professionals in appropriate medical interventions selecting in unanticipated conditions at clinical care processes. At clinical point, this system can improve the understanding of vital signs, patient health conditions and decision-making process that can help in reducing of medical errors.

---

Introduction: Integration of health information systems based on a common language is essential to exchange data with the system. The study aimed to eliminate the existing problem in the integration of information system with electronic health records system through providing a conceptual model of laboratory reporting system, using the Unified Modeling Language and enable information system developers to design their services based on this model and connect to Electronic Health Record System to send their laboratory reports.

Methods: In this applied-descriptive, cross-sectional study, conducted during the first half of 2015, purposive sampling was used to select 95 employees of Rajaee Heart Center laboratory in Tehran. Data were collected using a questionnaire the validity and reliability of which were measured using content validity and test-retest, respectively. Data analysis was done through descriptive statistics using SPSS software version 21. Visual paradigm was used to design a conceptual model.

Results: Data related to reports such as, demographic, administrative, clinical, insurance, anesthesia and laboratory, observation and interpretation were suggested as minimum data set for radiology report. Identified data needs, based on processes and user description, were used to draw use case diagrams based on which activity, class, state, sequence and collaboration diagrams were designed.

Conclusion: Laboratory reports in Electronic Health Record System have a crucial role in diagnosing and managing clinical problems; therefore, providing a conceptual model for laboratory reporting system can eliminate the current problem of data sharing between these systems and electronic health records system.

---

Introduction: Osteoporosis is a common disease in women.  Osteoporosis fractures may cause irreparable damages; therefore, early diagnosis and treatment before fractures is an important issue.  The ojectiveof this study was to develop a decision support system for diagnosing osteoporosis using artificial neural networks.
Method: This developmental study has been done in second half of 2017 based on crossectional method. In  present study initially Osteoporosis affecting clinical factors were identified and the most significant clinical factors were selected through incorporation of a questionnaire-based survey. Subsequently, information of 256 female participants and their BMD test results, five years after initial data entry were used to train neural network. The information was obtained fromwomen who refered to department of Bone Mineral Densityof oushehr university of medical sciences. In order to identify the best network, trial and error method was used and neural networks with different topologies were trained using  Scaled Conjugate Gradient and Levenberg-Marquardt algorithms. Confusion matrix was used to evaluate the network’s accuracy, sensitivity and specificity.
Results: In the first stage, out of 15 essential variables, 12 variables were selected as the most important risk factors. Multilayer perceptron neural network was designed. Results showed that the best structure of network was due to Scaled Conjugate Gradient algorithm with 10 neurons and Levenberg-Marquardt algorithm with 12 neurons in hidden layer. Accuracy comparison was showed that generally Levenberg-Marquardt algorithm had better result. The best sensitivity, specificity, and accuracy was 83.1%, 89.4%, and 86.3% respectively.
Conclusion: In this study developed a diagnostic tool based on local data that could be effective in tracking osteoporosis. Utilizing such a diagnostic tool as a timely referral of individuals and initiating therapy as soon as possible may prevent fractures from occurring and help avoiding the frequent complications of osteoporosis.

---