Journal of Health and Biomedical Informatics

Introduction: The Length of Stay (LOS) in the hospital is used as an indirect indicator of resources consumption and efficiency in hospitals. Identifying factors associated with this systematic review can be valuable in planning to optimize the utilization of the existing resources. The goal of the present study was to investigate factors associated with length of stay and it has been conducted as a systematic review.
Method: In this systematic review, papers were retrieved by the use of specified key terms in their titles and no restricted time in Persian and English databases. Papers were selected according to how they were in line with the criteria for inclusion and exclusion and finally, information were extracted and entered to Excel 2010 software for analysis.
 Results: 18 articles out of 347 were selected. These studies introduced four criteria associated with length of stay including clinical, demographic, administrative, and hospital factors. Applied methods for identifying these criteria were statistical techniques and data mining techniques such as decision tree regression and artificial neural networks. The goal of all studies was making a new model for identifying factors associated with LOS or was evaluating other methods introduced in other studies.
Conclusion: Findings of this study represent that identifying factors associated with LOS can be variable according to data collection place, studied variables, and applied data mining techniques. So we suggest researchers to help hospital managers and planners with identifying and reducing factors associated with LOS.

Introduction: Medical records are considered as an essential element of patient’s health care provision. Due to a rising service provision by healthcare centers, there is an increase in the medical record loads as well. It has led to a series of problems‌, such as limited physical space, records wearing and an increased need for resources. Moreover, the most important efficiency of records, which is their application in clinical research, is questioned. In the present study, researchers have presented a model of minimum data sets which helps to index and electronically archive hard-copy records according to the selected data and metadata.

Method: This study was an applied research type, conducted in three stages in 2013 via modified Delphi technique. Target population consisted of specialists working in hospitals. As the sample, 8 physicians who were specialists or subspecialists participated in interviews and filled out checklist surveys. The collected data were later analyzed using Excel 2013.

Results: The results show that data elements such as “final diagnosis” and “operations and others” were the most common items considered by the physicians in clinical follow up, and most common medical records was “operation’s repots” . Finding significant correlation among physician’s research questions was not possible due to large variety of subjects.

Conclusion: The researchers presented a framework of minimum data sets for a purposive archiving of records for clinical and research-based applications. This framework can act as the applied goal setting of the retrieval model based on physicians’ clinical requirements in their medical follow-ups. Furthermore, considering physicians’ needs for accessing records through analyzing their probable requests can provide a possibility of data retrieval in diverse conditions.

Introduction: The Importance of disease classification for facilitating medical research is clear. The Medical diagnosis classification is usually done through International Classification of Disease (ICD) system. Sometimes, diagnostic terms in medical records require to be replaced by equivalent term according to international classification of disease system. In order to optimize the patient’ medical records, using information technology, especially designing and developing application in classification of local medical diagnosis are recommended. This research aimed to identify local cardiovascular diagnoses and develop an application for classification and coding them.

Method: This research is an applied study, conducted on 500 medical records in Mashhad Imam Reza and Ghaem hospitals. After that, the concept mapping developed between diagnostic terms and the ICD terms. Data were collected through observation, interview, and checklist, and then the application was developed for coding diagnoses. Furthermore, the coding agreement coefficient related to first and second final diagnoses recorded in medical records was calculated among three raters via interclass correlation coefficient (ICC).

Results: In this research, 1081 codes were investigated and 676 diagnoses of them were recorded in the record summary form. The number of the local diagnoses and abbreviations with their codes were 147 cases. The coding agreement rate among raters was 70% and 88% in the first and second final diagnosis, respectively.

Conclusion: Due to the excellent agreement between raters about the local cardiovascular terms performed through the coding application, it can be concluded that the designed application has high reliability in coding and can be used for classification of diagnoses in different hospital departments.

Introduction: The high demand for the patients' documents cause a great change in service provision methods. Different systems have been established during decades to feed this need. The use of information technology in different parts of health care system, particularly in hospitals, has high potential for improving the quality of provided services. One of these technologies is Electronic Medical Record (EMR). This study is aimed to determine the factors affecting the intention to use EMR from the perspective of top and middle managers of Shiraz educational hospitals.
Method: This research is a cross sectional analytic-descriptive study. The study population were top and middle managers of Shiraz educational hospitals. Data were collected using searcher-made questionnaire with six sections. The data was collected by a researcher-made questionnaire that its content validity was confirmed by specialists. Its reliability was confirmed using Cronbach’s alpha. The data was analyzed by Regression and Pearson, independent sample t-test, and ANOVA Tests using SPSS16 software.
Results: The results showed‌ that there isn't a relationship between demographics and the variables in the study. Also there was a significant relationship between effort expectancy, facilitating conditions, familiarity with technology, perceived ease of use, and attitude toward use of EMR with intention to use.
Conclusion: With the improvement of effort expectancy, facilitating condition, managers' familiarity with technology, perceived ease of use, and attitude toward use can raise the intention to use EMR by top and middle managers. Increasing the intention to use can also avoid probable failure of the system during performance.

Introduction: Pharmacy Information System (PIS) is one of the subsystems of Hospital Information System (HIS) that has been designed to meet the needs of pharmacy. Assessment could improve the existing systems and make competition between companies.
Method: This cross-sectional study assesses the performance of Pharmacy Information System (PIS) in Shiraz, Iran hospitals in March 2013. Data were collected by direct observations and interviews with the users of the software. Data collection tool was a valid and reliable standard check list which consists of Hospital Information System evaluation criteria that was published by the Ministry of Health and Medical Education in December 2011. The evaluation criteria have been graded by users based on their importance. Collected data were analyzed using descriptive statistics and Microsoft Excel software 2010.
Results: The Pharmacy Information Systems (PIS) in studied hospitals in terms of accounting and insurance capabilities were in quite desirable condition with a total average score of 40.Ware housing and reporting as well as recording of information related to drugs and medication were in acceptable condition with a total average score of 27/71 and 36/96, respectively. However, intelligent clinical capabilities with a total average score of 11/74 were in an undesirable condition. Other clinical capabilities with a total average score of 31/27 were in a relatively good condition.
Conclusion: Many of pharmacy information systems, which are the most important component of clinical support systems, have been designed for the purpose of medication management and medication costs instead of supporting clinicians in prescribing process. However, these PIS software gained the lowest score in the intelligent clinical features. Therefore, upgrading the capabilities of electronic alerts during inappropriate prescription of drug as well as clinical decision support systems and improving hospital pharmacy information system is necessary.

Introduction:  Electronic Medical Records, which is a valuable system to access the patients information at the hospital, is one of the innovative technologies for the utilization of health information. For its successful implementation, this system should be assessed regarding the factors affecting its adoption and use. The purpose of this study was to review the published articles on the factors influencing the adoption of electronic medical records systematically and according to Information Technology Adoption Theories and to identify and classify the factors affecting the adoption of this system.

Method: The present study is a systematic review survey. Data were collected by searching strategy in valid databases such as Google Scholar, Emerald, Science Direct, SID, MagIran, IranMedex, Pubmed from  2004 to 2014, and then the data were recorded on checklist.

Results: Among the studies that use information technology theories to survey the factors affecting adoption of electronic medical record, TAM model was used more than other models. Factors such as perceived ease of use, perceived usefulness, and social influence of TUATU are the most effective on adoption of electronic medical records.

Conclusion: The results of the study showed, perceived ease of use, perceived usefulness, and social influence are effective factors in adopting EMR. Consequently these factors are recommended to be considered in planning to run systems.

Introduction: Chronic kidney failure is a common disease in the world and kidney transplantation is the most effective treatment in patients with chronic kidney failure. The aim of this study was to predict the survival of transplanted kidney and identify its effective factors, and also to provide a model for higher prediction accuracy.

Method: In this retrospective study, data from 423 cases of kidney transplant patients during 2006-2011 in Afzalipour Teaching Hospital in Kerman were obtained. The neural networks, decision tree and support vector machine were used to predict kidney transplantation survival and information fusion was used to combine the results of these classifiers and design a model with higher prediction accuracy. In addition, for identifying factors affecting the survival of transplanted kidney, genetic algorithm was used and for data analysis and implementation of algorithms, Clementine 12 and Weka 2.3 were used.

Results: The accuracy of neural networks, decision tree, and support vector machine were 94%, 92%, and 92%, respectively, and the accuracy of information fusion was 95.74%. Also, recipient BMI and gender, donor age, compatibility of donor and recipient blood group, and history of kidney transplantation as the effective factors on renal transplantation survival were identified by genetic algorithm. The prediction accuracy of this model was 91.67%.

Conclusion: The results show that information fusion can increase the prediction accuracy. Also, the genetic algorithm as an effective method can be used for identifying the optimal features.

Introduction: FAD is the cofactor of FAD-FR protein family. Sulfite reductase flavoprotein alpha-component is one of the main enzymes of this family. Based on applications of this enzyme in biotechnology and industry, it was chosen as the subject of evolutionary studies in 19 specific species.
Method: Gene and protein sequences of sulfite reductase flavoprotein alpha-component, 5S rRNA sequences, and taxonomic tree were extracted from 19 selected bacterial species. Then, phylogenetic trees of 5S rRNA and gene and protein sequences were compared with each other and with taxonomic tree. Phylogenetic trees were drawn by Mega7 software using neighbor-joining algorithm and taxonomic tree was extracted using NCBI taxonomy browser.
Results: By comparing the corresponding tree pairs, the percentage of equivalent species and the mean equivalence score of species were calculated for each tree pair. The gene-protein tree was allocated the highest scores in both quantities. In comparing the taxonomic tree with three other trees, gene-taxonomy tree achieved the highest percentage in the mean equivalence score and protein-taxonomy tree obtained the highest percentage of equivalent species.
Conclusion: Based on the results of the present research, the best replacement for each of the trees investigated in this study regarding evolutionary relations was identified. In other words, this study helps detect which evolutionary tree can be replaced for another evolutionary tree.