جستجوی مقالات مرتبط با کلیدواژه « خوشه بندی » در نشریات گروه « پزشکی »

In recent decades, the field of health insurance has emerged as one of the vital components of the healthcare system, propelled by continuous advancements in technology and the increasing complexity of medical services and technologies. With the advent of new challenges in this industry, there has been a heightened effort to find innovative solutions to enhance service quality, optimize resource management, and increase the satisfaction of insured individuals. One significant approach in improving this domain involves the application of data mining techniques to identify behavioral patterns among health insurance policyholders during outpatient visits to diagnostic and treatment facilities.

The present study is a descriptive cross-sectional study. The claim data of health insurance in Bushehr province of Iran was used. After data preparation, analysis was performed using SPSS Clementine12.0 software. The values of insurance start time, number of visits, and the value of the type of insurance were used to model the K-means algorithm in two modes including demographic mode and Recency-frequency-monetary (RFM). Sampling was done by census method. The statistical population includes the information of all outpatient referrals of the insured covered by health insurance of Bushehr province to 1,420,579 referrals to diagnostic and medical centers in 2018, which has been prepared by the researcher’s direct referral to the database of medical records.

The root mean square deviation values for RFM-based clustering and demographics are 21 and 21.65, respectively. And the Dunn’s Index confirmed the better RFM-based clustering. The RFM-based K-Means algorithm classified the data into four clusters, with 44% of the insured in Cluster One, 4% in Cluster Two, 22% in Cluster Three, and 30% in Cluster Four. Based on this, cluster 2 insured, including women with insurance of other classes with 4% of the population, were identified as the most referred, and cluster 3, including women with rural insurance, with 22% of the population, were identified as the least referred insured.

The obtained model divided the insured into 4 clusters. This model allows the organization to predict the referral patterns of each insurer based on their age, gender, and type of insurance and provide appropriate services for different clusters. By using these models and technique in decision making process, the insurers satisfaction will be improved.

The use of statistical methods to reach the clustering and ranking of health in the society can give a proper view of the state of health in Iranian provinces. The aim of the current research was to cluster and rank Iranian provinces based on some health indicators.

This was a descriptive study. Clustering and ranking Iranian provinces were carried out according to several items such as the number of employees working in faculties of medical sciences, doctors, paramedics, hospitals, active beds, primary health care providers, laboratories, rehabilitation centers, nuclear medicine centers, clinics and emergency centers. The data were collected from the statistical yearbooks of the provinces.  Clustering analysis and data visualizations were performed in R software and ranks were obtained using Topsis software.

The results showed that the provinces of Ilam, Yazd, Semnan, South Khorasan, Zanjan, Ardabil, Fars, Kohgiluyeh and Boyer Ahmad, and Chaharmahal and Bakhtiari had the highest health scores and belonged to the third cluster. Their ranks were 1 to 9 respectively. In the first cluster the following provinces were observed: Qom, Tehran, Alborz, and Hamedan with scores of 0.552, 0.540, 0.460, and 0.36 respectively indicating that these provinces had the lowest health scores and their ranks were 28 to 31. The other provinces appeared on the second cluster and ranked 10 to 27 with almost equal scores.

In order to achieve health equity, the indicators should be improved in provinces belonged to the first cluster to in order to achieve the standard per capita.

The combination of ontology-based retrieval systems leads to the semantic retrieval of words. The aim of this study was to review ontology articles in information retrieval using scientometric techniques.

The present study was conducted using the documentary method and word cluster analysis. The research population comprised 2595 articles indexed in two databases, Scopus and Web of Science, from 2001 to 2023. The data were analyzed using Excel, BibExcel, SPSS 26 and UCINET. VOSviewer was used to draw research maps.

The growth of articles in ontology and information retrieval was low and the annual growth rate averaged 0.11%.Stanford and California universities were the most prolific organizations, contributing to 6 articles, and the field of computer science was the most prolific with 43% of the articles written. The word clustering led to the formation of 4 thematic clusters: semantic retrieval of information, non-human ontology, classification of systems, and role of technology. In addition, there was a positive correlation between science production and centralities (degree centrality 0.323, closeness centrality 0.278, and betweenness centrality 0.447).

The evolution of the words used in the articles has shown that although the growth of article production in this field has increased from the beginning, the development of ontology technologies in information retrieval started with a weak semantic system called information classification, and after the various stages of development, it now uses machine learning to understand user requirements and process information with the help of artificial intelligence.

Since the beginning of the Covid-19 epidemic, many countries have been involved in fighting the disease. The outbreak of this disease has caused irrecoverable damages to countries in various aspects such as human resources, economic situation, and social welfare. The purpose of this study was to evaluate the performance of world countries in the face of covid-19 in respect of the role of vaccination and to propose applicable approaches for countries with lower performance.

In this research, a three-phase method was developed to evaluate the performance of 88 countries in the face of Covid-19. In the first phase, the countries were clustered, using the k-means algorithm. In the second phase, the data envelopment analysis model was implemented once on the clusters and then on all the countries without considering the clusters. In the third phase, after presentation of the concept of resilience in the Covid-19 era, an Analytic Hierarchy Process was implemented with three criteria, including the results of data envelopment analysis model without considering the clusters, the results of data envelopment analysis model considering the clusters and resilience, and then the ranking of the countries' performance in the face of Covid-19 was provided.

Based on the results, 15 performance scores were obtained for the countries in the face of Covid-19, among which China, Fiji, Seychelles, Kyrgyzstan and Tanzania had the highest rankings and Bangladesh, Nepal, Georgia and Pakistan had the lowest performance levels. Iran is in the sixth place and in the average performance position of the countries.

Based on the findings of this study, the countries with low performance level in the face of Covid-19 need to apply various strategies in different areas in order to improve their performance level. These strategies include planning and approval of joint programs to control and prevent the spread of disease, applying quarantine policy and restrictions on communities, planning and implementation of appropriate strategies regarding the export and import of drugs and medical equipment, allocating appropriate funds to research projects on Covid-19, banning the export of drugs effective in the treatment of Covid-19, and providing accurate and up-to-date information for raising people’s awareness.

The purpose of this study was to cluster students with profiles of motivational beliefs and orient the goal of high and low achievement in terms of academic performance.

The research method of this study was correlational and part of clustering schemes. The statistical population was all incoming students of Kermanshah University of Medical Sciences in the academic year of 1397-98 who were selected by stratified relative sampling method. Data were used through standard motivational strategies questionnaires for Pintrich and Digrott learning, Elliott and McGregor achievement goal orientation, and self-reported student average scores (semester grade point average) to assess academic performance. Data analysis was performed using SPSS software and descriptive statistics and inferential statistics. Cluster analysis, diagnostic function analysis and t-test were used for independent groups.

Based on the research results, two clusters were identified for students. The first cluster, with motivational beliefs and high achievement goal orientation, was called high motivation-orientation cluster and the second cluster with motivational beliefs and low progress goal orientation was called low motivation-avoidance cluster. Then, to confirm the clustering, the analysis of the diagnostic function was performed, which showed that the clustering was confirmed. The t-test with a significance level of 0.01 showed that there is a significant difference between the two clusters in terms of academic performance.

It can be concluded that motivational beliefs and high achievement goal orientation are important factors in increasing studentschr('39') academic performance.

Asthma is a common and chronic disease of respiratory tracts. The best way to treat Asthma is to control it. Experts of this field suggest the continues monitoring on Asthma symptoms and adjustment of self-care plan with offering the preventive treatment program to have desired control over Asthma. Presenting these plans by the physician is set based on the control level in which the patient is. Therefore, successful recognition and classification of the disease control level can play an important role in presenting the treatment program to the patient and improves the self-care and strengthens the early interventions to alleviate the Asthma symptoms.  

Based on this objective, we collected the data of 96 Asthma patients within a 9-month period from a specialized hospital for pulmonary diseases in Tehran. Then we classified the Asthma control level by fuzzy clustering and different types of data mining method within a multivariate dataset with the multi-class response variable.

Our best model resulting from the balancing operations and feature selection on data have yielded the accuracy of 88%.

Our proposed model can be applied in electronic Asthma self-care systems to support the decision in real time and personalized warnings on the possible deterioration of Asthma control. Such tools can centralize the Asthma treatment from the current reactive care models into a preventive approach in which the physician’s decisions and therapeutic actions are resulting from the personal patterns of chronic Asthma control and prevention of acute Asthma.

Introduction:

 Diabetes is a metabolic disorder in the body that is impaired by the ability to produce insulin hormone. The main purpose of the present study is to discover the hidden knowledge in the data of diabetic patients, which can assist clinicians in clustering new patients and prescribing appropriate medication according to each cluster.

In this paper, we use MR-VDBSCAN algorithm. The implementation of this algorithm is based on the map-reduce framework of Hadoop. The main idea of the research is to use local density to find the density of each point. This strategy can prevent clusters from joining at different densities.

The algorithm is based on the selected dataset, tested and evaluated, and the results show high accuracy and efficiency. The results were compared with the results of k-Means clustering, The MR-VDBSCAN algorithm has a higher execution speed than that of the algorithm and has the ability to detect clusters with different density of superiority of this algorithm than the comparable algorithm. The results show that the MR-VDBSCAN algorithm can provide better performance than other algorithms. In particular, the similarity of the proposed algorithm is 97% for the diabetes set.

The results show that the MR-VDBSCAN algorithm performs better clustering than the K-means algorithm and can place patients into subgroups that assist physicians in prescribing.

The aim of this research was to analyze and illustrate scientific productions of Islamic Azad University researchers under title of Medical Sciences in Web of Science (WOS) data base.

The present study was a kind of applied scientific research which studied the quantitative performance of Islamic Azad University of Medical Sciences in WOS database from beginning to 2018. Statistical population of this study was all scientific productions of Medical Sciences of Islamic Azad University (11155 records) in WOS database.

The first scientific output of medical sciences of Islamic Azad University was indexed in 1996 and the highest number of indexed output was in 2016. Kazem Parivar has been ranked the first among all researches and had the highest scientific collaboration was with the USA academic centers. The journal "African Journal of Biotechnology" was also recognized as the source of the medical science core of the Islamic Azad University on the Web of Science. The most frequently use key word was "Iran" and key words "Pharmaceutical Chemistry" and "Pharmacology and Pharmacy" had the most frequent synonyms. Finally, the keywords of Islamic Azad University's scientific productions in medical sciencesweare divided into 7 general clusters.

The results of this study indicate that Islamic Azad University of Medical Sciences researchers have been able to obtain the third rank among the medical universities of Iran with a good effort. But they have not used their potential to recognize Iran's progress in controlling the spread of communicable diseases worldwide.

The emergence of single-cell RNA-sequencing (scRNA-seq) technology has provided new information about the structure of cells, and provided data with very high resolution of the expression of different genes for each cell at a single time. One of the main uses of scRNA-seq is data clustering based on expressed genes, which sometimes leads to the detection of rare cell populations. However, the results of the proposed methods mainly depend on the shape of the cell populations and the dimensions of the data. Therefore, it is very important to develop a method that can identify cell populations regardless of these obstacles.

In the proposed method, which was a library method, at first, the number of clusters (cell populations) was estimated. Estimating the number of clusters is important because in the real world, basic information such as the number and type of cell populations is not available. Thereafter, using a graph-based Gaussian kernel, while reducing the dimensions of the problem, the cell populations were identified by means of the kmeans++ clustering.

The results of the implementation showed that the proposed method can achieve an acceptable improvement compared to other machine learning methods presented in this regard. For example, for the ARI criterion, values of 100, 93.47 and 84.69 were obtained for Kolod, Buettner, and Usoskin single-cell data sets, respectively.

The proposed method can cluster and thus identify cell populations with high accuracy and quality without having any basic information about the number and type of cell populations, regardless of the high dimensions of the problem.

with increasing demand for treatment, patients are monitored with help of Internet of Things(IOT). Patient's monitoring devices and technologies include heart rate measurement, blood pressure measurement, blood glucose and other vital signs. The purpose of study is to provide a model of clustering patient physical monitoring gadgets and apps in Healthcare Internet of Things (HIOT) environment using data mining techniques, so based on the needs and characteristics of the user, the more appropriate results of choosing technologies acquired.

This study is a review and functional since its result. The data includes 6 unique features of 60 selected technologies including function, price, connectivity route, power supply, location and type of use that has been extracted from R&D and advertising sites of technologies and also relevant articles. data analysis method is clustering technique and K-medoids algorithm. to identify the most effective features, random forest algorithm has been used.

the proposed clustering model takes into account 6 as inputs and clusters gadgets and apps in accordance with selected characteristics as the model outputs. clustering problem data is clustered in 4 categories.  Silhouette index is 0.45, which indicates the validity of the model. The type of application and then the price had the greatest impact on clustering.

By this model, patients or users can find the most appropriate technology based on the type of disease and other effective features, such as price. So with accurate physical and momentary monitoring, disease progression decrease and prevention of disease will improve.

Detecting the abnormal performance of diabetes and subsequently getting proper treatment can reduce the mortality associated with the disease. Also, timely diagnosis will result in irreversible complications for the patient. The aim of this study was to determine the status of diabetes mellitus using data mining techniques.

This is an analytical study and its database contains 254 independent records based on 13 characteristics. Data is collected by a researcher from one of the specialized diabetes centers in Mashhad.

After preprocessing of the obtained data, different methods of pattern recognition were applied. Using multilevel MLP neural networks, LVQ neural networks, SVM support vector and Kmeans clustering method, the mean square error (RMSE) was calculated. The correctness of each learner's performance is 94%, 92%, 96%, and 93%, respectively.

Reducing the diagnosis of diabetes is one of the goals of the researchers. Using data mining techniques can help to reduce this error. In this study, among different protocols used for pattern recognition, SMV method displayed a significantly better performance.

Due to the current role of medical tourism as an industry, better understanding of its market can be important. One way to understand the market and its targets is through clustering them, and understanding the characteristics of each cluster. The present study was conducted to determine and analyze the demographic, geographic, and behavioral variables within the clusters of medical tourism market. This was a descriptive-survey conducted using a questionnaire. 151 questionnaires were completed by foreigner patients in selected hospitals in Tehran City, Iran, who were selected using one-stage cluster sampling. The results of the questionnaires were examined using K-means and chi-square correlation coefficient via SPSS software. The findings identified four different clusters of medical tourists, namely first, second, third, and fourth clusters, with significant differences in terms of the studied variables. In other words, the examined demographic variables included gender, age, education and income, the country of origin of tourists was considered as a geographical variable, as well as behavioral variables including the number of trips, the length of stay in Iran, the type of medical service received, the main source of information for travel in Iran, the method of regulating treatment, doing side activity, and the type of side activity. All the variables had significant differences in different clusters. The differences in clusters should be considered by policymakers and activists in this area. It is important to provide a regular and systematic program for recognizing and planning of Iraqi medical tourists. Furthermore, medical tourism managers can provide an increasing number of side plans in cooperation with hospitals and agencies for this potential market.

Non-communicable diseases are related to the risk factors such as smoking, inappropriate nutrition and lack of physical activity. The purpose of this study was to use factor analysis for obtaining the scale of combined risk factors, to rank the provinces based on it.
The data of this study were included 20 risk factors according to province and sex among 15-64 year-old subjects. This data were extracted from the report of the non-communicable diseases risk factors surveillance of Iran in 2009. We used the principal component method of factor analysis for men and women, separately. Finally we ranked the provinces by calculated scores of the first factor.
Based on the first factor, for men, East Azerbaijan, Qom, Ardebil and Mazandaran provinces had the highest morbidity risk for non-communicable diseases and Sistan and Baluchistan, South Khorasan, Kerman and Hormozgan provinces had the lowest risk, respectively. Also, among women, Mazandaran, Qom, Kermanshah and eastern Azerbaijan provinces had the highest morbidity risk of non-communicable diseases and Sistan and Baluchistan, South Khorasan, Hormozgan provinces had the lowest risk, respectively.
The results showed that factor analysis could show very well the risk of noncommunicable diseases in different provinces of Iran. Based on the results, the provinces which had higher incidence of morbidity of non-communicable diseases need more attention to nutrition and health education.

Blood donation rate in developed countries is 18 times higher than developing countries. It is estimated that if only five percent of Iran population embark on blood donation, it will be adequate to meet the needs of the community. The aim of this paper is to identify the blood donators’ loyalty behavior for proper planning to extend and enhance blood donation habits among the community.
A cross-sectional survey was applied through census in the present study. The data extracted from blood transfusion center of Tehran from 2005 to 2010 was used in this study. Clementine 12.0 was used for data analysis. K-Means clustering is based on demographic data and RFM values modes which were applied to obtain the best ratio among different fields.
The mean value of root mean square standard deviation for RFB-based clustering and demographic were 10.7194 and 11.1411,respectively. This finding confirmed better data clustering by RFB-based algorithm. The data were placed by RFB-based algorithm in four clusters. The fourth cluster consisted of single males who obtained the best loyalty rank and the third cluster consisted of married females who obtained the least loyalty rank.
Applying data mining methods for analysis and classification of blood donors changes current attitude towards blood donation procedure. Survey of donor behavior helps us to identify faster and more precise donor loyalty as well as having proper management of the blood transfusion centers.

The aim of this study was to evaluate text mining and clustering of computer engineering documents retrieved from the Web of Science database. This is a descriptive-analytical study which was conducted in a survey method using text mining approach. The research community was all computer engineering documents indexed in the Web of Science, among which 6016 cases were reported between 2004 and 2016. The collected data were analyzed by HistCite software, Excel version 2013 and RapidMiner version 7.3. In order to perform clustering, after preprocessing the data and running K-means (a clustering algorithm), 8 main clusters were established. The clusters were Internet and Technology, Security of Healthcare Information Systems, Human-Computer Interaction, Semantic Web, Computer Models, Computer Systems Performance, Networks & Databases, Knowledge Discovery Algorithms and Other Topics. To evaluate the clusters, two criteria of precision and recall were used and a value of 0.81 was obtained for both criteria. Using words selected as keywords in the clustering can help the user save time and retrieve the related information.

Non-melanoma skin cancer (NMSC) has recently been one of the three most common cancers in Iran. Inappropriate management of the disease has led to an increase in the prevalence and overhead costs. Data mining techniques are helpful in the analysis of patient records and accurate management of diseases. This study aimed to find hidden patterns and relationships in the data of NMSC patients using data mining algorithms.
In this applied study, study population consisted of medical records of 828 NMSC patients referred to the Cancer Institute of Imam Khomeini Hospital in Tehran during 2006-2015. Demographic variables and NMSC risk factors were clustered using K-Means algorithm. Apriori algorithm was applied as well for extraction of association rules and determination of patient’s common information with a confidence of ≥ 0.9.
According to the studied variables, NMSC patients were classified in four clusters and three important factors influencing the disease were identified as abnormal BMI, high risk occupations and previous history of cancer. Seven rules were approved by association rules and the highest associations were found between the past history of the disease, the involved site, the relapse, and the type of NMSC.
For the first time, this study could highlight the most important factors affecting NMSC using data mining methods. These factors should be considered either in self examination or screening skin tests in high-risk groups. In future studies, the contribution of physiological, ecological and genetic factors in the development of skin cancer should be jointly investigated as well.

One of the applications of population attributable risk percent (PAR%) is to estimate the disease burden in a population exposed to several risk factors. Therefore, this study was conducted to estimates the PAR% of the space-time clusters of pulmonary tuberculosis.
In this study, the data of pulmonary TB cases were obtained from the health department of Hamadan University of Medical Sciences. After detecting significant clusters using the spatiotemporal scan statistic, PAR% was used to analyze the clusters and to detect the location of clusters more accurately.
Four primary space-time clusters and three secondary spatiotemporal clusters were detected for patients with pulmonary tuberculosis and 92% of the patients who did not have a clear state in term of HIV infection. Despite differences in the location of clusters and PAR% attributed to them, the second primary cluster of pulmonary tuberculosis cases (consisting of the cities of Razan, Famenain and Kabudrahang) had the highest amount of PAR% that needs more attention.
The presence of significance spatiotemporal clusters in Hamadan highlights the necessity of the use of PAR% to distinguish cluster areas and to implement prevention and control policy. However, more analytical studies are needed to detect the on the determinants of the occurrence of pulmonary TB.

Urgent need for blood and lack of an alternative for it necessitates the presence of a model to assist doctors in providing the proper services for the donors and also the right management of blood transfusion centers. The present study is aimed at determining blood donors’ status.
Cross-sectional survey was applied in the present study through census. The population included the data extracted from blood transfusion center of Birjand from Khordad to Shahrivar 1392 which was provided as an Excel file by the direct visit of the researcher from the blood transfusion organization. In the present study, first, two-step clustering and then C50, C&R TREE, CHAID, and QUEST algorithms were executed to obtain the best ratio among different fields. Analysis was performed using Clementine12.0 software.
The obtained accuracy for executing C50, C&R Tree, CHAID, and QUEST equals 0.9998, 0.9960, 0.9930, and 0.8913, respectively. The results of indices including sensitivity, Specificity, accuracy, precision, FM, GM, FPR, FNR, and ER for C50 are indicators of better performance of this algorithm compared to the other ones. Important variables in modeling are blood pressure label, blood donation status and temperature.
The proposed model helps us in predicting faster and more precise status of blood donation and also the proper management of the blood transfusion centers and it canbe and effive step for efficient usage of blood donation and decreasing the blood maintenance costs.

Due to the high prevalence of depression and the considerable pressure it puts on individuals, society and healthcare system, it is essential to conduct sufficient research to help with decision making in prevention, treatment and control of this condition. To assist with research planning and setting priorities, this paper aimed to identify the thematic structure of papers related to depression treatment.
This was an applied research study which used Scientometrics approach. To obtain data, the keyword “Depression” was searched as a mesh descriptor with the subdivision “Therapy” in PubMed database for the period of 2005 to 2014. The data were analyzed using co-word and clustering methods with the help of Excel and SPSS software packages.
The growth of scientific production in this field appeared to have been balanced throughout the ten-year period examined in the study. The most active research areas for the two five year periods (2005-2009 and 2010-2014) were drug therapy, psychology, and medication adherence. Two hierarchical graphs of descriptors for each five-year period were prepared both of which were composed of 12 clusters with 34 common descriptors.
The findings based on the inclusion index showed that only 20 percent of topics in the second five-year period of the study were novel. Therefore, it could be concluded that research areas that were related with each other in previous years will probably co-occur with other topics in the future might disappear. In every discipline, some topics are considered to be fundamental and research works are being carried out on them almost every year.