Search

Background and Aim: Cancer is the second leading cause of death in the world, which leads to the death of more than 10 million people in the world every year. Its early diagnosis, management and proper treatment play an important role in reducing complications and mortality. One of the support tools in early diagnosis, treatment and management of this disease are Clinical Decision Support System (CDSS), which are divided into two groups, rule-based and non-rule-based. Rule-based decision support systems are created based on clinical guidelines, while non-rule-based decision support systems use machine learning. In this research, the effects of decision support systems, rule-based and non-rule-based, on cancer diagnosis, treatment and management were measured. Materials and Methods: The present study was conducted using a systematic review method, which was conducted by searching the Web of Science, Scopus, IEEE and PubMED databases until 12/31/2021. After removing duplicates and evaluating the characteristics of the inclusion and exclusion criteria, studies related to the goal were selected. The selection of articles was based on the title, abstract and full text The data collection tool was the data extraction form, which included year of study, type of study, system of body, organ of body, the service provided by the decision support system, type of decision support system, effect, effect index and the score of effect index. Narrative synthesis were used for data analysis. Results: Out of 768 articles, 16 articles related to the objectives of the study were identified. Studies were presented in two categories of clinical decision-support systems: Rule-based and non-Rule based. The effects evaluated in the clinical decision support systems were Rule-based, dose adjustment, symptoms, adherence to treatment guidelines, care time, smoking, need for chemotherapy and pain management, all of which except pain management were significant and positive. The effects evaluated were in the category of non-Rule based clinical decision support systems, diagnostic and therapeutic decisions, controlling neutropenia, all of which were significant and positive except controlling neutropenia. Conclusion: The results obtained for the effectiveness of both Rule-based and non-Rule-based decision support systems indicated different benefits of these two categories. Therefore, using their combination in the field of cancer can bring very useful results.

Introduction: One of the most effective ways to improve the management of asthma in primary care is using guidelines in the patient management process; but due to lack of time, their use is very limited. One way to solve this problem is mechanized guideline in a form of decision-support system that requires computer-interpreted guideline (CIG). In this study, a CIG was developed for asthma management in primary care. Methods: This qualitative study was performed using mini-Delphi method uses a workflow-based approach to develop a CIG. The workflows and data components were extracted through Business Process Model and Notation (BPMN) language and Enterprise Architecture (EA) software. Afterwards, they were confirmed through an expert panel of five asthma specialists. Results: The developed CIG included three major workflows, four sub-workflows, and 21 data components. Main workflows included treatment, drug interaction, and follow-up time. Sub-workflows were related to treatment workflow that were developed based on the patient visit number and age. Conclusion: Because the accuracy of this workflow was confirmed by asthma specialists, it is expected that the design of this CIG will lead to development of a cost-effective software for the management of asthma and better detection of drug interactions.

Background and Aim: Cardiovascular diseases and medication errors are among the leading causes of morbidity and mortality around the world. Electronic prescribing and Medication Administration(ePMA) systems can prevent medication errors to some extent. This study aimed to determine the information requirements of ePMA systems. Materials and Methods: This descriptive study was conducted in Imam Khomeini Hospital of Tehran and School of Allied Medical Sciences affiliated to Tehran University of Medical Sciences (TUMS) in the summer of 2019 in two phases: literature review and survey-based questionnaire. Information items obtained from reviewing the texts of 100 articles were organized in three questionnaires. In the survey phase, questionnaires were distributed among physicians, nurses, and the experts of health information management(HIM) and medical informatics, using census sampling method. The reliability of the questionnaires was measured using Cronbachchr('39')s coefficient alpha. Statistical analysis was done using SPSS. Results: The findings showed that based on specialists’ point of view, patientschr('39') demographic information items and unique identifiers gained the highest average, above 4.7. Physicians agreed most with clinical information, including medication history and generic names. From the nurses’ point of view, the information items of the patients’ problems and the procedures performed and the types of drug doses obtained a complete average of 5. Conclusion: The need for information items varies among different users of ePMA systems, but there may be items that are common for them. Future studies should further investigate financial and pharmaceutical information requirements based on the perspectives of other hospital pharmacy and accounting staff.