1 2423-3870 دانشگاه علوم پزشکی کرمان 335 Clinical Decision Support Systems Proposing an Appropriate Architecture for Decision Support Systems in the Field of Complex Chronic Care: Micro-Services Based Software Architecture in Kidney Transplant Care Rashidi Khazaee Parviz Bagherzadeh Jamshid Niazkhani Zahra Prinejad Habibollah e e Ph.D. in Medical Informatics, Associate Professor, Health Information Technology Dept., Urmia University of Medical Sciences, Urmia, Iran 1 3 2019 5 4 423 434 12 05 2018 06 09 2018 Introduction: Development and successfully implementation of knowledge based clinical decision support system (KBCDSS) in kidney transplantation (KT) could support decision-making, reduce cost and improve quality of care. For practical use of these systems, however, many challenges have to be met.  Besides to well-recognized challenges of design and implementation of information systems in healthcare domain, designing an appropriate architecture for KBCDSS that can address requirements of complex and multidisciplinary chronic care, is a new growing challenge. Method: This case study was done based on the experience achieved in design of kidney transplantation management system in Urmia. Then, considering main applications and challenges of development and implementation of KBCDSS in Kidney transplantation and using the latest advancements in software technology field, appropriate software architecture based on micro-services has been proposed. Results: For each function (process) of the KBCDSS, three different micro-services of data gathering, optimal model designing and its application were proposed. These services, through implementation on provided backgrounds, can respond to different requests of patients and provide them with adequate knowledge and information. Conclusion: Use of this architecture makes it possible for different research teams with different skills and knowledge throughout the country to focus on designing a specific function and doing it in a best way. The proposed architecture can be extended and scaled. Moreover, in spite of increase in size and type of data, users and requests, it can respond well.  
327 Data Mining Using Data Mining Models for Differential Diagnosis of Iron Deficiency Anemia and β-thalassemia Minor Noferesti Samira f Shemshadi Nejad Narges g Heydari Fatemeh f PhD in Computer Engineering, Assistant Professor, Information Technology Dept., Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan, Zahedan, Iran g MSc in Software Engineering, Zahedan, Iran 1 3 2019 5 4 435 446 18 07 2018 11 11 2018 Introduction: One of the most common types of anemia is Iron deficiency anemia that its main differential diagnosis is β-thalassemia minor. The rapid and accurate screening of β-thalassemia minor has particular importance for pre-marriage medical counseling and the prevention of the birth of neonates with β-thalassemia major and differentiating it from iron deficiency anemia to avoid unnecessary prescription of iron. The aim of this study was to apply data mining techniques to differentiate iron deficiency anemia from β-thalassemia minor based on CBC test in order to increase the diagnostic speed and to reduce diagnostic costs. Method: The present study was a retrospective study and was performed on 1000 patients referred to Dr. Heidari laboratory of Zahedan city. To conduct research, CRISP-DM standard methodology and support vector machine data mining algorithms, naive Bayes, Bagging, Adaboots and decision tree have been used. WEKA software was used to analyze the data. Results: The results of the evaluations show that Bagging, Decision tree, Adaboots, support vector machine, and naive Bayes algorithms had respectively 95.73%, 95.5%, 94.6%, 80.2% and 76.6% accuracy in differentiating iron deficiency anemia from β-thalassemia minor. Conclusion: In this study, an automatic method based on data mining techniques for differentiation of iron deficiency anemia from β-thalassemia minor is presented. The results of the evaluations show that Bagging algorithm has higher accuracy compared to other data mining algorithms and differential indices. Also, with the help of the decision tree, rules have been extracted that can be used by the physician in timely diagnosis of the two diseases.   300 Artificial Intelligence in Healthcare Detection of Abnormal Behaviors in Patients with Dementia and Preliminary Symptoms in Smart Home Khosravi Alireza i Hosseini Seno Amin j i M.Sc. in Computer, Faculty of Computer Engineering, Islamic Azad University, Nishabur Branch, Nishabur, Iran j Ph.D. in Computer Network, Assistant Professor, Computer Dept., Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran 1 3 2019 5 4 447 456 18 04 2018 31 05 2018 Introduction: The number of elderly people who need help in their daily routines is increasing rapidly. Dementia is one of the most important causes of disability in elderly people and its outbreak has been a major burden on human societies. The purpose of this research was using intelligent home technology to monitor elderly behaviors, identify abnormal behaviors, and discover the initial signs of dementia before the onset of the disease. Early diagnosis of dementia at an early stage can lead to a high improvement in its treatment and delay the disease. Method: In this applied, descriptive-analytic study, the abnormal behavior and early symptoms of dementia were identified using machine learning techniques.  The kmedoide algorithm was used to analyze abnormal behaviors and to assess the quality of sleep as the primary symptoms of dementia, the valid PSQI questionnaire was used. Matlab 2012 was used for implementation. Results: The results in the abnormal behavioral section indicated that clustering algorithms have high efficacy in detecting abnormal behavior in smart home, and also results in early symptom examinations led to poor sleep recognition in the PSQI as a primary symptom of dementia. Conclusion: The behavior of the elderly, their abnormal behavior and early signs of diseases such as dementia can be recognized using the technology of the system under the supervision of the smart home. 314 Data Mining Comparison of Three Decision-Making Models in Differentiating Five Types of Heart Disease: A Case Study in Ghaem Sub-Specialty Hospital Mousavi Raahil k Sepehri Mohammad Mehdi l k PhD. Student in Industrial Engineering, Faculty of Technical and Engineering, Research and Science University, Tehran, Iran l Tarbiat Modares university 1 3 2019 5 4 457 468 23 05 2018 08 09 2018 Introduction: cardiovascular diseases are becoming the main cause of mortality and morbidity in most countries. This research goal was to predict the types of heart diseases for more accurate diagnosis by data mining and neural network technics. Method: This research was an applied-survey study and after data preprocessing, three approaches of neural network, decision making tree and Bayes simple algorithm were used to predict and recognize in Rapidminer software and neural artificial network model was used for prediction in Matlab software. Results: Genetic algorithm was used for selection of effective variables and neural artificial network models, decision making tree and Bayes simple algorithm were used to predict types of heart diseases in data mining. AHP model was used to determine a model with the best performance for predicting types of heart diseases. Conclusion: Neural network had much better performance than other data mining models used to diagnose types of heart diseases in this research. Also, in detecting disease by artificial neural network, the model with accuracy of more than 80 percent was verified as good and acceptable 276 Mobile health Determining Blood Glucose Concentration using Near Infrared Spectroscopy: Early Findings Javid Bahareh m Fotouhi- Ghazvini Faranak n Zakeri Fahimeh Sadat o m MSc in Information Technology Engineering, Computer Engineering and Information Technology Dept., University of Qom, Qom, Iran n University of Qom o University of Qom 1 3 2019 5 4 469 480 08 02 2018 29 05 2018 Introduction: Diabetes mellitus is one of the diseases that have grown dramatically in today's societies. People with diabetes should continuously measure their blood glucose level. Continuous blood glucose measurement by commonly used methods is painful and difficult. On the other hand, mobile phone can be a useful tool for accessing physicians and telemedicine services more easily. The aim of this study was to provide a medical care system for mobile monitoring of diabetes. Method: This study is an applied study and the proposed system includes a non-invasive sensor for measuring blood glucose using the near-infrared spectroscopy and an Android application. To evaluate the system, experiments were performed on glucose solution and on the body. In these experiments, both the transmittance and the reflectance modes were examined. Results: It was observed that with increasing glucose concentrations, the output voltage of sensor increased in the transmittance mode and decreased in reflectance mode. When testing on the body, the mean error rate was 34.14 in the transmittance mode and 35.9 in the reflectance mode. The results indicated that by combining transmittance and reflectance modes, better results were obtained. In this case, the mean percentage of error was 8.27 and RMSE was 52.18mg/dl. Conclusion: Finally, it can be inferred that near-infrared spectroscopy can be used in the future as an alternative for invasive methods in measuring blood glucose levels. There is also the possibility of providing remote medical services to diabetics using mobile phones.     272 Health Information Technology Detection of Twitter Users' Attitudes about Flu Vaccine based on the Content and Sentiment Analysis of the Sent Tweets Ghanbari Zahra Yousefi Nejad Mohsen Jafari Navimipour Nima Hosseinzadeh Mehdi Ph.D. in Computer Hardware, Associate Professor Computer Engineering Dept., Islamic Azad University, Science and Research Branch, Tehran, Iran 1 3 2019 5 4 494 481 02 02 2018 01 09 2018 Introduction: The influenza vaccine is one of the controversial challenges in today's societies. Considering the importance of using the flu vaccine in preventing the spread of influenza virus, the Twitter network, as a rich source of data, provides suitable conditions for research in this field to examine the attitudes of different people about this vaccine. The results in one hand will help health authorities to make more comprehensive decisions on long-term health plans for people with an awareness of the attitude of individuals towards the flu vaccine; on the other hand, it is concerned with data miners. Method: In this review study, approximately 1.220.539 tweets have been gathered from the Twitter social network during a one month period and have been clustered by using Mallet software. Categorizing users and separating tweets have done with an appropriate approximation. The content and sentiments of the selected tweets were analyzed and the locations of the users were checked. Results: In sentiments analysis, 76.28% of the tweets had a positive weight, 1.87% was neutral, and 19.68% had negative weight, indicating a positive attitude about the influenza vaccine. The location of users showed the highest rate of sending tweets from Canada, Britain and the United States, and Asian countries, and in particular, Iran, had a very small percentage of it. Conclusion: The highest rate of positive tweets were respectively sent by ‘individual’, ‘health’, and ‘organization’ groups indicating the global acceptance of the influenza vaccine and the success of the global health organizations on vaccination.   313 Bioinformatics Bioinformatics Study of the miR-200 Family and the Target Genes in Prostate Cancer Khorasani Maryam Shahbazi Shirin Mahdian Reza Ph.D Student of Molecular Medicine, Molecular Medicine Department, Pasteur Institute of Iran, Tehran, Iran. Associate Professor, Medical Genetics, Medical Genetics Department, Faculty of Medical Sciences, Tarbiat Modares‎ University, Tehran, Iran. Ph.D. in Medical Biotechnology, Associate Professor in Medical Biotechnology Dept., Pasteur Institute of Iran, Tehran, Iran 1 3 2019 5 4 495 506 20 05 2018 10 11 2018 Introduction: Considering the limitations of the common diagnostic test for prostate cancer prostate cancer, the introduction of higher-specific biomarkers for a more accurate and timely diagnosis of prostate cancer is desired. In this study, we aimed to investigate the miR-200 family (miR-200a, miR-200b, miR-200c, miR-141, and miR-429) and their target genes using bioinformatics prediction tools in order to propose potential diagnostic biomarkers for prostate cancer. Method: In this theoretical study, based on bioinformatics study of micro RNA, the DIANA TOLLS-mirPath v.3 database was used to search the target genes of the miR-200 family in the signaling pathways known in prostate cancer pathogenesis. Then, we confirmed the suggested genes by the online predictive tools such as MiRWalk, Targetscan and RNAhybrid. Finally, the functional role of target genes was investigated on the DAIVID bioinformatics database. Results: According to the results of this study, the E2F3 gene is the target of all family members of miR-200, BCL2 is the common target of miR-200b / miR-200c / miR-429 and CCNE2 is the common target of miR-200a / miR-141 subsets. Also, miR-200c and miR-429 can modulate the pathogenesis of prostate cancer by targeting CDKN1B and KRAS genes, respectively. Conclusion: The results of this study showed that members of the miR-200 family targeting the genes involved in important biological processes and molecular pathways of prostate cancer pathogenesis are likely to be effective diagnostic biomarkers in future experimental studies.   263 Telemedicine Feasibility Study for the Establishment of Telemedicine: A Review Study and a Suggestion for Iran Rafati Hossein Molavi Taleghani Yasamin PhD Student in Health Care Management, Health Management and Economics Dept., Health Management and Economics Research Center, School of Management and Medical Information, Isfahan University of Medical Sciences, Isfahan, Iran 1 3 2019 5 4 507 519 13 12 2017 01 09 2018 Introduction: Telemedicine is considered as an integral part of the management of health care services and health information systems. This study aimed to review the studies on the goals and applications of telemedicine in different countries and to present a suggestion for the health system of Iran. Method: In this systemic study using keywords of tele-medicine, electronic health، tele health, health care, system, technology, program and tele medical, the related studies in databases of Iranian National Medical Digital Library were reviewed from April 2000 to April 2017. Results: After applying the entry criteria and evaluating the quality of the studies, 70 eligible papers were selected. The main identified obstacles to the establishment of electronic health in Iran were vagueness and complexity of the IT infrastructure, cultural and educational problems, frequent changes of managers, inability to attract skilled IT staff in the field of electronic health, lack of a specified mechanism for funding electronic health systems and failure to develop technical standards. Conclusion: Telemedicine in Iran can transfer from the pilot phase to a stable major phase provided that it be cost-effective. Therefore, it is suggested that sufficient attention be paid by custodians to issues such as allocating adequate funding, raising the awareness of authorities regarding the necessary infrastructure requirements, and creating motivation and cooperation feeling using briefing and training sessions.