Showing 37 results for Data
Mohsen Shirazi Mehrabad, Hadi Sharif Moghaddam , Khalil Kimiafar, Amirabbas Azizi,
Volume 11, Issue 4 (12-2017)
Abstract
Background and Aim: Periodic assessment of medical sciences databases is a necessary principle of the process of enhancement these databases. The aim of this study was to Comparatively evaluate structural features of medical bibliographic databases including MedLib, Barakat knowledge network system, Irandoc, SID, Magiran and PubMed, based on Gulliver criteria.
Materials and Methods: This survey was carried out in accordance with Gulliver's assessment checklist 2002. This checklist consists of 12 sections including entry page, searching, limiting, record viewing and manipulating, graphics, record retrieval, selective dissemination of information services, general design, terminology, icon design and placement, help and advanced features. The study was conducted on five national databases and one foreign database.
Results: Among the databases, PubMed gained the first ranking with a score of 89.16 percent. Among the national databases, new SID database with a score of 57.5 percent gained the top rank. Other databases including Irandoc (56.25%), Magiran (54.58 %), Barkat knowledge network system (52.91 %), MedLib (51.25%) and old SID (47.5 %) obtained next ranking respectively.
Conclusion: Despite improvements indices in updated national databases, many of the indicators are far from prestigious databases such as PubMed. It is recommended that in development of national databases, features such as search, help, SDI, entry page, advanced features and record retrieval should be considered.
Mohammad Khodabakhshi , Hossein Dargahi, Hajar Moammai ,
Volume 11, Issue 4 (12-2017)
Abstract
Background and Aim: Because human health is a strategic priority for all communities, investing in this sector will be very important. The purpose of this research is to evaluate the efficacy of hospitals affiliated to Tehran University of Medical Sciences from 2013 to 2015 and their ranking, and provide a perspective for dynamic managers in this area.
Materials and Methods: This is an applied study, and in terms of nature, it is descriptive. The statistical population of this study was 13 hospitals of this university. In this research, the efficacy of hospitals during the years 2013 to 2015 through the data envelopment analysis and Output-based method was evaluated. By carefully examining global research, input and output indicators were identified. Input indexes were the number of beds and the number of doctors (general, residents and specialists); and output indexes were the total days of hospitalization, the number of outpatients, and the number of bed-days.
Results: According to the study model, university hospitals with high efficiency to low efficiency are as follows: Arash, Bahrami, Zanan, Roozbeh, Amiralam, Ziaeeyan, Baharlou, Razi, Valiasr, Sina, Farabi, Imam Khomeini and Shariati hospitals.
Conclusion: According to output-based method, by calculating the efficiency mean of hospitals during the years 2013 to 2015; Arash hospital, Bahrami hospital and Zanan hospital are determined to be the most efficient; and, Farabi hospital, Imam Khomeini hospital, and Shariati hospital are the ones with the lowest efficiency.
Reza Safdari, Maliheh Kadivar, Parinaz Tabari, Hala Shawky Own ,
Volume 11, Issue 5 (1-2018)
Abstract
Background and Aim: Neonatal jaundice is a matter that is very important for clinicians all over the world because this disease is one of the most common cases that requires clinical care. The aim of this study is to use data classification algorithms to predict the type of jaundice in neonates, and therefore, to prevent irreparable damages in future.
Materials and Methods: This is a descriptive study and is done with the use of neonatal jaundice dataset that has been collected in Cairo, Egypt. In this study, after preprocessing the data, classification algorithms such as decision tree, Naïve Bayes, and kNN (k-Nearest Neighbors) were used, compared and analyzed in Orange application.
Results: Based on the findings, decision tree with precision of 94%, Naïve Bayes with precision of 91%, and kNN with precision of 89% can classify the types of neonatal jaundice. So, among these types, the most precise classification algorithm is decision tree.
Conclusion: Classification algorithms can be used in clinical decision support systems to help physicians make decisions about the types of special diseases; therefore, physicians can look after patients appropriately. So the probable risks for patients can be decreased.
Khadije Moeil Tabaghdehi , Marjan Ghazisaeedi , Leila Shahmoradi , Hossein Karami,
Volume 11, Issue 5 (1-2018)
Abstract
Background and Aim: Thalassemia is a chronic disease which is extremely expensive, complex and debilitating. The management skill of thalassemia patients should be enhanced to minimize the risk of disease complications. The main purpose of this study was to develop personal electronic health records for thalassemia major patients.
Materials and Methods: This is a developmental applied study which was conducted to develop a personal electronic health record for thalassemia major. First, a questionnaire was prepared to determine the data elements and was filled by Hematology and Oncology professionals in the country (110 persons). Then, based on the results of needs analysis, the system was designed using PHP programming language and MySQL database and was evaluated by 50 thalassemia patients who referred to the Thalassemia Clinic of Bu Ali Sina Hospital of Mazandaran University of Medical of Sciences during the second half of the month of Aban. Finally, a standard questionnaire of usability and user satisfaction assessment was distributed among them.
Results: Usability evaluation of the system showed that patients evaluated the system at a good level with a mean rating of 7.91 (out of 9 points).
Conclusion: The web-based systems can be used to help thalassemia patients to control injection and reduce the complications of the disease and to promote health.
Marjan Ghazi Saeidi , Sasan Moghimi Araghi , Shadi Babadi ,
Volume 11, Issue 6 (3-2018)
Abstract
Background and Aim: Glaucoma, with an increasing pressure inside the eye, is one of the causes of blindness worldwide. The only glaucoma treatment is regular eye examination and control of intraocular pressure (IOP). The centralized information obtained from these examinations is an essential prerequisite for providing optimal healthcare which is possible by creating electronic records. Minimum Data Set (MDS) is a standard tool for getting access to accurate data, which is among the basic needs for the design of electronic records.
Materials and Methods: This is descriptive-analytical study. The population of this study consisted of glaucoma patients’ medical records at Farabi Eye Hospital, reference books, and glaucoma specialists. The data collection tool was a questionnaire -- containing patients' records, and demographic and clinical data -- which was distributed between 22 available glaucoma specialists. The validity of the questionnaire was assessed by an expert team and its reliability was determined by test-retest method. Data analysis was performed by calculating the frequency percentage and Delphi test.
Results: After reviewing the rate of experts’ agreement with the components of the survey, all of the cases with over 75% approval rate were considered as minimum data set for glaucoma. Minimum data set was divided into three general categories: patient's records, demographic data, and clinical data.
Conclusion: Determination of minimum data set for glaucoma will be an effective step to integrate and improve the management of patients’ records. Moreover, it will be feasible to store and retrieve such records.
Afshin Mousavi Chalak, Aref Riahi, Amin Zare,
Volume 12, Issue 1 (5-2018)
Abstract
Background and Aim: Scientific journals are known as one of the basic tools in knowledge development in today's world and have a special place in publication of the newest achievements of human knowledge and science. This study aimed to evaluate Iranian journals of medical sciences in Scopus database and determine their level in the world.
Materials and Methods: This is an analytical-descriptive study with Scientometrics approach. The research population includes all Iranian journals in the field of medicine which are indexed in Scopus database until 2016. We used SPSS and Excel software to analyze data and NodeXL to draw shapes and pictures.
Results: The findings show that the number of Iranian journals increased from 2 in 1999 to 78 in 2015. Also, 15 cities and 29 centers and universities have played a role in publishing those journals. Meanwhile, the findings show that Iranian indexed journals are at a lower level compared with those of the developed and industrial countries.
Conclusion: The most important reasons for Iranian journals' growth were "the policy of Scopus to increase scientific journals", "observance of standards and compliance with international fashion and standards of medical journals”, and the like. We concluded that Iranian journals compared with those of other countries are not at a good quality position and that it is essential to have an appropriate policy by the Ministry of Health and its subordinate Universities.
Arefeh Kalavani, Maryam Kazerani, Maryam Shekofteh,
Volume 12, Issue 1 (5-2018)
Abstract
Background and Aim: With the development of the Internet and databases and the increasing need to institutionalize evidence-based medicine, physicians' awareness and use of evidence-based medical databases and concepts are considered to be necessary. Therefore, the aim of this study is to evaluate the knowledge and use of evidence-based medical concepts and databases among residents of Shahid Beheshti University of Medical Sciences (SBMU).
Materials and Methods: The present study is an applied and descriptive research. The population of this study comprised 192 SBMU residents in 2016. A questionnaire was used for data collection and SPSS software was applied for data analysis.
Results: The findings showed that residents obtained 2.99 for knowledge and 2.73 for the use of evidence-based medical databases out of a total average of 5 points, which indicates that their knowledge and practical use of evidence-based medical databases are moderate. Databases about which residents have the highest knowledge and practical use are UpToDate, PubMed Clinical Queries, and
Cochrane, respectively.
Conclusion: The majority of residents at Shahid Beheshti University of Medical Sciences do not have sufficient awareness about databases and concepts of evidence-based medicine; in fact, most of the resources that are used to answer their information needs are non-evidence-based resources. Therefore, planning to accept evidence-based medicine and databases and teach them to residents is essential.
Hojatollah Soleimani, Fatemeh Nooshinfard, Fahimeh Babolhavaeji,
Volume 12, Issue 1 (5-2018)
Abstract
Background and Aim: To understand veterans’ needs and to make future generations familiar with the culture of self-sacrifice and martyrdom, we need a database to store information. The first step for designing a base is to provide a conceptual framework of the base. This study aims to provide a conceptual model to create the national base of veterans in Iran.
Materials and Methods: This research was conducted in a two-step, mixed approach. The first step was conducted using content analysis method (quantitative) and the second step using Delphi (qualitative) technique. Data collection tool was Excel 2016 software. With the help of Delphi technique, a researcher-made conceptual pattern was sent to the experts in three rounds. Based on their views, the final plan of national base of veterans was formed.
Results: Among the main components, introduction to the war was removed, history of war changed to history of wars, link to links, other materials to other contents, art and war to war and art, and the sub-component of possibilities turned into the main component. Veterans’ personal information turned into veterans’ database that changed into subsidiary components of the martyrs / veterans / prisoners-of-war / warriors database.
Conclusion: The main components of the conceptual pattern of national base of veterans of Iran include: home page, introduction, conflicts and operations, equipment, war zones, facilities, news, cemeteries of martyrs, veterans’ rules, questions and answers, history of wars, war and art, veterans’ database, archives, links, guide, contact with us, FAQs, other content, resources, about the base, search, map.
Minoo Shahbazi, Reza Safdari, Mohammad Zarei,
Volume 12, Issue 2 (7-2018)
Abstract
Background and Aim: The quality of Electronic Health Records (EHRs) depends on the quality of its content and proper documentation. Determining the Minimum Data Set (MDS) to enhance the quality of electronic health records’ content and helping to improve the quality of health care provision to uveitis patients are essential matters. The aim of this study is to determine the essential MDS for uveitis patients’ electronic health records.
Materials and Methods: In this descriptive-analytical study, data collection tools for collecting the Minimum Data Set were library resources and internet-based database. The MDS was obtained through Likert scale questionnaire and was surveyed by 22 ophthalmologists and retina subspecialists.
Results: Among the elements of the survey, all cases with over 90% approval were considered as main elements. Regarding the importance of presented data elements, no significant difference was found between the responses of ophthalmologists who participated in this study.
Conclusion: The Minimum Data Set of uveitis patients’ electronic health records can be represented by five groups of demographic information: patients’ clinical records, laboratory information, type of uveitis, treatment guidelines, and the information of ophthalmic pictures. A suggested model for manual systems and electronic medical records is available.
Reza Safdari, Somaye Mahdavi, Leila Shahmoradi, Khdijeh Adabi, Shahram Tahmasebian, Mahnaz Nazari,
Volume 12, Issue 5 (1-2019)
Abstract
Background and Aim: To provide effective care, health care providers need timely and appropriate information. Electronic records provide quick access and easy management of data. The aim of this study was to develop electronic health records for patients with hydatidiform mole and evaluation of completeness of medical records
Materials and Methods: This applied study was conducted in 2017. After verifying the minimum data set required for the system, data were extracted from patient records using a checklist and entered into SQL server. SQL server 2012 and Visual Studio 2013 to design electronic records and SPSS 20 for data analysis was used. Extent of data completion in patient records was also assesed.
Results: Data on the completion of paper records indicated that in 100% of cases, “address” item was filled in. The less completed data was related to carotene deficiency (%1.1). Our findings also showed that the eight most important items like age of first menstruation, first gestational age, interval between pregnancies, number of sexual partners, menstruation between pregnancies, contraceptive methods, social habits and radiotherapy, were not completed in all records.
Conclusion: Many of the important minimum data set for hydatidiform mole disease were either not completed or completed in limited numbers in paper records. By developing such health records, we can ensure better prevention and treatment, and regular follow-up for the patients and help them to save their time and costs.
Reza Safdari, Mozhgan Rahmanian, Shahrbanoo Pahlevany Nejad ,
Volume 12, Issue 6 (3-2019)
Abstract
Background and Aim: Preeclampsia is one of the most prominent cases of pregnancy related diseases that threatens health at global level, especially in developing countries. In Iran, with 14% of outbreak, it is the second most common cause of maternal mortality. The main goal of this study was to identify the information requirements of the Android-based preeclampsia self-Management application.
Materials & Methods: This was a descriptive study that was done in 2018 in Amir_Almomenin Hospital affiliated to Semnan University of Medical Sciences in two stages of reviewing the sources and the need for data elements. In the review phase, after studying the articles and study, the data requirements and factors which affecting the prevalence of preeclampsia were identified and a survey of qualified physicians was done by designing a researcher-made questionnaire.
Results: This research results indicate that 63.9% of the respondents assigned to the elements mentioned in the demographic findings. 75.9% of them identified health information elements as very important. Also, 77.85% of the research community considered the elements in the lifestyle sector to be of the highest importance. All participants recognized that reminder in the program was necessary. Approximately 33.33% of them reconsidered sport education to be at the lowest level, while 45.24% rated it as being of the highest importance.
Conclusion: The information requirements of this program were determined in 6 groups of health history, educational tips, lifestyle, alarms, referral, and reporting. These programs can help pregnant mothers with preeclampsia to control their disease to minimize complications by observing proper nutrition and principles of treatment.
Mohammad Reza Shahraki , Mahboubeh Mesgar,
Volume 13, Issue 1 (5-2019)
Abstract
Background and Aim: The liver, as one of the largest internal organs in the body, is responsible for many vital functions including purifying and purifying blood, regulating the body's hormones, preserving glucose, and the body. Therefore, disruptions in the functioning of these problems will sometimes be irreparable. Early prediction of these diseases will help their early and effective treatment. Regarding the importance of liver diseases and increasing number of patients, the present study, using data mining algorithms, aimed to predict liver disease.
Materials and Methods: This descriptive study was performed using 721 data from liver patient in zahedan. In this study, after preprocessing data, data mining techniques such as SVM: Support Vector Machine, CHAID, Exhaustive CHAID and boosting C5.0, data were analyzed using IBM SPSS Modeler 18 data mining software.
Result: The validity obtained for boosting C5.0 94/09, for Exhaustive CHAID algorithm 88/71, for SVM 87/09, for CHAID algorithm 85/47 prediction of liver disease. the boosting C5.0 algorithm showed a better performance of this algorithm among other algorithms.
Conclusion: According to the rules created by boosting C5.0 algorithm, for a new sample, one can predict the likelihood of a person for developing liver disease with high precision.
Farideh Akbarzadeh, Zahed Bigdeli,
Volume 13, Issue 5 (1-2020)
Abstract
Background and aim: A Library is a safe place to research and study for some students, but it creates anxiety for others. The main purpose of this research is to investigate the library anxiety among Kermanshah University of Medical Sciences(KUMS) residents in using information sources and electronic services based on five factors of Bostick scale.
Materials and Methods: The study was a cross-sectional survey. The sample size was 197 persons who were selected using simple random sampling. Data collection tool was a researcher-made questionnaire whose validity was confirmed by experts and its reliability was confirmed by Cronbach's alpha coefficient of 0.809. The questionnaire consisted of 41 questions on a five-point Likert scale. The library anxiety questions were designed and localized based on the five factors of the Bostick scale. Data were analyzed using descriptive statistics, mean, standard deviation and analytical statistics by Kolmogorov-Smirnov test and Pearson correlation coefficient using SPSS 23 software.
Results: The mean score of library anxiety was 78.32, the mean score of familiarity and usage was 32.08 and 29.54. Mechanical and emotional factors had the highest mean of library anxiety factors. Mean library anxiety was not significantly different between male and female residents(p>0.05). There was a significant relationship between residents' library anxiety and their skills in using information resources and e-services.
Conclusion: The results indicate a level of library anxiety among the assistants. Accepting this fact can be a positive step in solving the problems associated with the use of information and electronic resources.
Raoof Nopour, Mohammad Shirkhoda, Sharareh Rostam Niakan Kalhori,
Volume 14, Issue 2 (5-2020)
Abstract
Background and Aim: Colorectal cancer is one of the most common gastrointestinal cancers among human beings and the most important cause of death in the world. Based on the risk of colorectal cancer for individuals, using an appropriate screening program can help to prevent the disease. Therefore, the purpose of this study was to design a model for screening colorectal cancer based on risk factors to increase the survival rate of the disease on the one hand and to reduce the mortality rate on the other.
Materials and Methods: By reviewing articles and patients' records, 38 risk factors were detected. To determine the most important risk factors clinically, CVR(content validity ratio) was used; and considering the collected data, Spearman correlation coefficient and logistic regression analysis were applied for statistical analyses. Then, four algorithms -- J-48, J-RIP, PART and REP-Tree -- were used for data mining and rule generation. Finally, the most common model was obtained based on comparing the performance of the algorithms.
Results: After comparing the performance of algorithms, the J-48 algorithm with an F-Measure of 0.889 was found to be better than the others.
Conclusion: The results of evaluating J-48 data mining algorithm performance showed that this algorithm could be considered as the most appropriate model for colorectal cancer risk prediction.
Marjan Ghazi Saeedi, Gholam Reza Esmaeili Javid, Niloufar Mohammadzadeh, Hamide Asadallah Khan Vali,
Volume 14, Issue 5 (1-2021)
Abstract
Background and Aim: Diabetes is one of the most common metabolic diseases in the world, of which one of the most common and painful complications is diabetic foot ulcer. The accuracy and comprehensiveness of the contents of electronic medical record is effective in improving the quality of treatment and the care of diabetic foot ulcer patients. The aim of this study is to determine the minimum data set (MDS) essential for diabetic foot patients' electronic medical records.
Materials and Methods: In this descriptive-analytical study, authoritative internet and library resources were studied to collect diabetic foot ulcer information elements. Fourteen physicians and nurses working and collaborating with the Wound Healing Center affiliated to Academic Center for Education, Culture and Research (ACECR) were selected for clinical survey, and 5 health information technology specialists of Tehran University of Medical Sciences (TUMS) were chosen for demographic information survey. The study tools were a researcher-made questionnaire, CVR content validity method and test-retest method for reliability.
Results: Out of 23 information elements surveyed in demographic section, cases above 99% of the agreement were selected. Also, out of 86 information elements of the clinical section, more than 51% of the cases were selected. Clinical experts included 6 wound specialists, 4 general practitioners and 6 nurses. In the demographic information section, the lowest agreement was related to the element of identity and Education level with 20% agreement. In clinical information, the lowest agreement was related to surgery, leech therapy and MRI of the foot with 0% and PRP, G-CSF, Sono-Doppler liver with 14%.
Conclusion: The minimum information elements of diabetic foot ulcer electronic medical record were divided into history, wound information, lower limb information, paraclinical results, wound management, and follow-up in clinical section; and in demographic information section, they were divided into identity, admission, finance, reporting, and system capability. The proposed model for manual and electronic medical records is available.
Marjan Ghazi-Saeedi, Roya Riahi, Rasool Nouri,
Volume 14, Issue 6 (1-2021)
Abstract
Background and Aim: In this study, in order to increase the visibility of articles in Scopus journals of Tehran University of Medical Sciences (TUMS), selective dissemination of information (SDI) service was presented and its impact on some citation indices was investigated.
Materials and Methods: This is a semi-experimental study of two groups (pretest-posttest design with a control group). In this study, TUMS Scopus indexed journals (20 titles) were randomly divided into test and control groups and their citation indices were assessed. Then, the SDI services for test group journals were designed based on PubMed's Alert system and presented to the university's top researchers for one year. Finally, the citation indices of the journals of test and control groups were reassessed and compared. For data analysis, independent t-test, paired t-test and, covariance analysis were used.
Results: Comparison of mean citations as well as SJR, SNIP and CiteScore indices before and after the intervention showed no significant difference between the test and control groups. But the average CiteScore in both groups after the intervention was significantly higher than the average before the intervention.
Conclusion: The results showed that the provision of the aformentioned services in the time period defined in this study had no significant effect on the citation indices. However, the valuable experiences gained in this study will undoubtedly be applicable to future research as well as services to researchers, librarians, and journal managers.
Reza Safdari, Seyyed Farshad Allameh, Ms Fariba Shabani,
Volume 15, Issue 6 (3-2022)
Abstract
Background and Aim: Many risk factors can cause biliary system diseases. Hence, this category of diseases is amongst the most common ones. Active patient cooperation is very important in disease management, self-care, and clinical outcomes improvement. A mobile phone application has a high potential in supporting the patients’ self-management. Therefore, this study was conducted to recognize and define data elements to develop a self-care application for biliary patients.
Materials and Methods: The current descriptive study was conducted in 2 stages, resource investigation, and data elements’ need assessment. In the first stage, scientific articles available in databases were used for defining required data elements to develop the application for biliary patients, and a checklist of data elements was prepared. In the second stage, a questionnaire was made based on the checklist. Content and face validity were accepted by the research team and the reliability was calculated 87.2%, using the Cronbach’s alpha test. The mentioned questionnaire was given to Gastroenterologists at Imam Khomeini Hospital complex, and the elected data elements were recognized.
Results: In this application, data elements were categorized into seven sections, including demographic and clinical information, data related to the biliary system diseases, postoperative lifestyle information of the biliary patients, reminders, disease management, and informing. Sixty point five percent of the responders gave the highest importance to data elements in the demographic and clinical data section. Data elements related to patients’ education were considered highly important by 54.2% of the responders. Forty three point eight percent gave the highest importance to data elements in interventional applications’ sections, and only 4.2% gave the least importance to this section.
Conclusion: Based on the identified data elements, a self-care application was designed and developed and can be used as a supplement to specialized care for biliary patients.
Zahra Aghasizadeh, Ali Reza Pouya, Nasser Motahari Farimani, Ali Vafeaa Najjar,
Volume 16, Issue 1 (3-2022)
Abstract
Background and Aim: Hospitals are the most important component of the health system and accurate evaluation of their performance is important. So far, much research has been done on the evaluation of hospitals using DEA models, but in these studies, organizations are considered as a black box and system processes and relationships between them are ignored. In this study, the efficiency of hospitals was evaluated using network envelopment analysis and its results were compared with simple envelopment analysis.
Materials and Methods: The method of the present research was ptactical and the nature of the survey was descriptive. The research population was all hospitals and educational centers affiliated to Mashhad University of Medical Sciences with a capacity of more than one hundred beds, which included twelve public hospitals and forty-eight sections. To collect information, methods of observing and studying documents, records and statistics of hospital activities have been used. For validation, by calculating Spearman correlation coefficient, it was found that the proposed model has a significant correlation with the Black Box DEA Model and the validity of the model was confirmed. SOLVER DEA and EXCEL software were used to implement the model.
Results: The results show that by considering the internal departments of the organization as well as the relations between the departments, a more accurate analysis of the efficiency of the hospitals would be done and we will have a better separation in the ranking between the organizations. Also, by using the network DEA model, the overall efficiency, the efficiency of each department and the rank of each department in comparison with similar departments in other hospitals are determined.
Conclusion: The framework presented in this study can be an appropriate criterion for measuring the efficiency of hospitals and their internal sections by determining the overall position of each hospital relative to other hospitals and by determining the efficiency of the section. By determining the efficiency of the internal departments of hospitals, a suitable priority is provided for allocating resources and investing in different departments in the direction of organizational improvement.
Leila Shahmoradi, Niloofar Kheradbin, Ahmad Reza Farzanehnejad, Niloofar Mohammadzadeh, Atefeh Ghanbari Jolfaei,
Volume 16, Issue 2 (5-2022)
Abstract
Background and Aim: Identifying risk factors is recommended as the first step for depression management in children and adolescents. This study aims to determine the data elements required for developing a clinical decision support system for screening major depression in young people.
Materials and Methods: This research was a descriptive-analytical study. The research population included a variety of mental health specialists that were both psychologists and students in psychiatry and guidance & counseling majors as well as electronic databases including Scopus, Pubmed, Embase, PsychInfo, WOS and Clinical key. The data collection tool was a questionnaire designed in three main sections which was answered by a convenient sample of 8 people who were specialists in the field. To analyze the extracted data Content Validity Ratio (CVR) and Mean measures were calculated for each item in questionnaire. Content Validity Index (CVI) and Cronbach’s Alpha (using SPSS software) were calculated which were equal to 0.74 and 0.824 respectively which confirmed validity and reliability of the research tool.
Results: According to Lawshe’s table, data elements with CVR between 0 and 0.75 and Mean less than 1.5, like “Ethnicity and race” (CVR=-0.25, Mean=1.125), were rejected. Items such as “Gender” (CVR=0.5) with a CVR equal to or less than 0.75, as well as items with a CVR between 0 and 0.75 and a Mean equal to or more than 1.5, like “Marital status” (CVR=0.5, Mean=1.625) were retained and considered to be included as the minimum data set for screening major depression in ages 10 to 25 years. Data elements were categorized in three categories: Demographic, Clinical and Psychosocial
Conclusion: Clinical decision support systems can facilitate providing healthcare at different levels such as screening major depression. These systems can be used for screening major depression risk factors to improve accessibility to mental health practitioners, assure the implementation of guidelines and provide a common language between different levels of healthcare. Determining the minimum data set for screening major depression in ages 10 to 25 years, is the first step toward developing a clinical decision support system for screening individuals for major depression.
Mostafa Shanbehzadeh, Hadi Kazemi-Arpanahi, Raoof Nopour,
Volume 16, Issue 2 (5-2022)
Abstract
Background and Aim: Breast cancer is one of the most common and aggressive malignancies in women. Timely diagnosis of breast cancer plays an important role in preventing the progression of this disease, timely treatment measures, and aftermath reducing the mortality rate of these patients. Machine learning has the potential ability to diagnose diseases quickly and cost-effectively. This study aims to design a CDSS based on the rules extracted from the decision tree algorithm with the best performance to diagnose breast cancer in a timely and effective manner.
Materials and Methods: The data of 597 suspected people with breast cancer (255 patients and 342 healthy people) were retrospectively extracted from the electronic database of Ayatollah Taleghani Hospital in Abadan city with 24 characteristics, mainly pertained to lifestyle and medical histories. After selecting the most important variables by using the Chi-square Pearson and one-way analysis of variance (P<0.05), the performance of selected data mining algorithms including RF, J-48, DS, RT and XG -Boost was evaluated for breast cancer diagnosis in Weka 3.4 software. Finally, the breast cancer diagnostic system was designed based on the best model and through C# programming language and Dot Net Framework V3.5.4.
Results: Fourteen variables including personal history of breast cancer, breast sampling, and chest X-ray, high blood pressure, increased LDL blood cholesterol, presence of mass in upper inner quadrant of the breast, hormone therapy with estrogen, hormone therapy with Estrogen-progesterone, family history of breast cancer, age, history of other cancers, waist-to-hip ratio and fruit and vegetable consumption showed a significant relationship with the output class at the P<0.05. Based on the results of the performance evaluation of selected algorithms, the RF model with sensitivity, specificity, accuracy, and F- measure equal to 0.97, 0.99, 0.98, 0.974, respectively, AUC=0.936 had higher performance than other selected algorithms and was suggested as the best model for breast cancer diagnosis.
Conclusion: It seems that using modifiable variables such as lifestyle and reproductive-hormonal characteristics as input to the RF algorithm to design the CDSS, can detect breast cancer cases with optimal accuracy. In addition, the proposed system can be effectively adapted in real clinical environments for quick and effective disease diagnosis.
