فهرست مطالب mehran kamkar haghighi

Artificial intelligence (AI) research within medicine is growing rapidly. AIis poised to transform medical practice. AI has been studied in several areas of healthcare and medical practice, including diagnosing, treating and caring of patients. Warfarin is one of the most commonly prescribed oral anticoagulant. Among all anticoagulants, warfarin has long been listed among the top ten drugs causing adverse drug events. Due to narrow therapeutic range and significant side effects, warfarin dosage determination becomes a challenging task in clinical practice.The purpose of this study was to determine exact dose of warfarin needed for patients with artificial heart valve using artificial neural networks (ANN).

Development:

 To achievethe best model, some multi-layer perceptron ANNswere constructed with different structures.The dataset used included846 patients who had been referred to the PT clinic in Tehran heart center in the second six monthsof the year 2013. Finally, the best structure of ANN forwarfarin dose was investigated and used for prediction system developments.In this paper the implementation of ANNs and proposed system in MatLab environment are described.

Application:

 The effectiveness of ANNs were evaluated in terms of classification performance using 10fold cross-validation procedure and the results showed that the best model is a network that has 7 neurons in its hidden layer with an average absolute error of 0.1, disturbance rate of 0.33 and regression of 0.87.

Theachieved results revealthat ANN-based system is a suitable tool for warfarin dosepredictionin Iranian patients with an artificial heart valve. However, no system can be guaranteed to achieve 100% accuracy, but using such methods can reduce medical errors and thereby improve healthcare and patient safety

  Artificial intelligence is a branch of computer science that has the ability of analyzing complex medical data. Using artificial intelligence is common in diagnosing, treating and taking care of patients. Warfarin is one of the most commonly prescribed oral anticoagulants. Determining the exact dose of warfarin needed for patients is one of the major challenges in the health system, which has attracted the attention of researchers. The purpose of this study was to determine the exact dose of warfarin needed for patients with artificial heart valves using artificial neural networks (ANN). A total of 9 multi-layer perceptron ANNs with different structures were constructed and evaluated based on a dataset including 846 patients who had referred to the PT clinic in Tehran Heart Center in the second half of the year 2013. Finally, the best structure of ANN for warfarin dose was investigated. All simulations including data preprocessing and neural network designing were done in MATLAB environment. The effectiveness of ANNs was evaluated in terms of classification performance using 10-fold cross-validation procedure and the results showed that the best model was a network that had 7 neurons in its hidden layer with an average absolute error of 0.1, turbulence rate of 0.33, and regression of 0.87. The achieved results reveal that ANNs are able to predict warfarin dose in Iranian patients with an artificial heart valve. Although no system can be guaranteed to achieve 100% accuracy, they can be effective in reducing medical errors.

Today, problems such as lack of filing space, the high volume of paper documents and expedite in access to patient medical records, induced to increasing of hospital’s attention to the use of imaging technique in medical record department. The aim of this study was to survey the application of document imaging for storage of medical records of hospitals in Iran. This descriptive cross-sectional study was performed in 2012-2013. Data were collected from all hospitals in Iran (890 hospitals). Instrument for data collection was a checklist that sent to hospitals by ministry of health. Data were analyzed using descriptive statistics in SPSS (version 16) software. The results showed that 14.9% of hospitals using document imaging for storage medical record in addition to the traditional filing approach. The most of the forms (65.9%) were Scanned using black and white method. 73.2% of the hospitals have scanned the selected medical record forms from patient record according to their policies. The result of the study indicates the challenges regarding the use of documents imaging approach in hospitals in Iran. Thus, the development a comprehensive guideline for implementing and using document imaging in medical record department by the ministry of health recommended.

ICT development has led to the emergence of virtual organizations phenomenon. Virtual hospital is one of these virtual organizations which present digital version of services and information of a hospital. In scientific literature, the term “virtual hospital” covers other concepts as well as the concept of a hospital. The study aimed at analyzing conceptual and practical evolution of virtual hospital. Considering these purpose different documents of the 1950s were reviewed and categorized under four conceptual terms. Practically, we related some actions to each term, as well.

This study was conducted as a review of articles collected from PubMed, Web of Sciences and Google Scholar databases.

Definitions of virtual hospital were differed from time to time. There is also different experience of implemented virtual hospitals in different countries. The first virtual hospital refers to the medical digital library to provide telemedicine services, in which then was named a virtual medical university. In the first decade of the 21st century, virtual hospital as a three-dimensional environment based on virtual reality emerged. Of those countries which adopted this technology were Germany, United Kingdom, United States, New Zealand, China and Singapore.

By advancing virtual reality techniques and development of Nano-electronics, we will be witnesses of production of advanced “point of care systems" with a kind of interaction between patients and physicians in a way that they feel they are really in a real hospital with possibility of track and care of patients instead real hospitalization.

Compared with the leading countries in the field of health information management, the current laws for medical record retention in Iran are very general, vague and they are inappropriate in terms of medical records usage, and there is not any reference to retention of many special medical records. Thus, the aim of this study was to revise the medical records retention laws for hospitals in Iran. This was an applied study which conducted in four phases from 2012 to 2013. In the first phase the study population consisted of all hospitals in Iran (890 hospitals), respectively, and in other phases of the study the consisted population were experts in the field of medical records. Instrument for data gathering was questionnaire. Data were analyzed by using descriptive statistics in SPSS software. The highest volume of requests for medical records in hospitals in Iran were related to legal purposes and patient continued treatment, and the lowest was related to research and educational purposes, respectively. Overall, hospitals identified 39 cases of medical records to revise in laws for retention. Type of admission, patient age, type of medical records usage were the most important criteria for determining the period of medical records retention. A retention period was considered for 27 types of medical records, of those 19 cases approved by National Archives of Iran. Basic retention period for inpatient medical chart was considered 10 years from the last patient encounter. The laws for medical record retention in Iran were revised. In comparison with pervious laws, the new laws consider more the legal, treatment, research aspects of medical records and the right of underage patient.

The present research is an attempt to describe the quantity and quality of publication trends of media literacy based on Scopus reports. The population under study was composed of 510 documents on media literacy published through 2011. The results were analyzed based on date of publication, type of document, language of the documents, source of publications, subject areas, authors and their affiliations, and the countries involved in developing the articles. Citation indicators formed the second phase of investigation in the present study. With a negligible amount of fluctuation, the number of publications on media literacy has increased steadily over the years, with the greatest number occurring in 2011. The analysis of data based on document types indicated that, of the 510 documents, 330 were articles (64.70%), 85 were reviews (16.66%), and 64 were conference papers (12.54%). 446 documents (84.45%) were published in English and the rest presented in other languages. The United States with 190 documents (37.25%), the United Kingdom with 43 documents (8.43%), and Australia with 14 documents (2.74%) were the most represented countries, with the most prolific authors known as Austin, Hobbs, and Cheung. Thematically, the greatest number of documents were produced in Social Sciences with 360 documents (70.57%), followed by Medicine with 92 documents (18.03%). The largest number of documents has been published in Comunicar followed by American Behavioral Scientist, and Simile. The most cited articles from 1996 up to 2011 included 22 documents on the H-index zone. Analysis of the results of H-index zone by subject categories indicated that most documents on h-index zone belonged to social sciences and Medicine areas. Psychology had the most influence on media literacy, as was shown by the ratio of most cited documents to total number of documents on media literacy in any of the subject categories. The results highlight the multidisciplinary nature of media literacy. As for the H-index zone, 16 documents (73.91%) belonged to the United States. Overall, the United States, with 190 (37.25%) publications (out of a total of 510), had an important role in enhancing the quantity and quality of the media literacy literature

Nowadays all educational institutes are trying to use technology in their structure. This effort has been faced with different barriers, including cost, time, and support. Therefore, using open source softwares can partially help us in using technology. In this article, we review main features of several open source learning management softwares, while presenting a tool which includes all the necessary features of a Learning Management System(LMS). An evaluation tool with 118 operational features for LMS softwares was developed. Five famous open source softwares of learning management system were compared based on its variables. These sofwares were: Moodle, Olat, Dokeos, ILIAS, and Docebo. Most of the open source LMS softwares have operational characteristics such as mass media, curriculum and student management, personalization, and financial management. However, they are different in details. There are quite a number of similarities and some differences between open source LMS softwares. Generally, choosing an open source LMS would be based on the demands of any educational organization. In this article, necessary characteristics of a suitable open source learning management computer program are presented