Showing 37 results for Data
H Dargahi , N Masuri , R Safdari , S Fazaeli , M Yousefi ,
Volume 4, Issue 2 (9-2010)
Abstract
Background and Aim: Analysis of efficiency in hospitals, as the most expensive operating unit of the health system, is very important. This costly unit has several departments that one of them is medical records. This study is trying to analyze the efficiency of medical records department for the enhancement of using medical records facilities.
Materials and Methods: In this study, technical, scale and managerial efficiency of medical records department has been studied by data envelopment analysis method, and assuming the scale efficiency variable and the input axis. Information used in this study was the input variables (number of technician personnel and lower and Master of Science personnel and higher), output variables (number of emergency and outpatient and inpatient medical records and the number of filing unit visitors to respond) during 2007-2009.
Results: The average technical efficiency of medical records departments is 84 percent, that indicates there is at least 16 percent capacity for an increase in performance. Average of management and scale Performance in units during the 3 years of study are 95 and 89 percent respectively. Most input surplus is relevant to technician and lower personnel. The average performance of these units in general hospitals is 80 percent and in specialized activities is 92 percent.
Discussion and Conclusion: Relationship between studied indicators in this study with performance medical records departments showed that using such as employee personnel with undergraduate degrees and higher and educated in medical records filed, the use of managers with enough experience in this department and more use of computer systems for unit activities can fill 16 percent capacity of performance improvement in these units.
Sj Ghazimirsaied, M Hemmat, H Dargahi, J Khansari,
Volume 4, Issue 3 (3-2011)
Abstract
Background and Aim: Using Hirsch index as an important tool to describe the scientific outputs of researchers has caused some authors to increase their self-imposed parameters, increase, citing themselves. Therefore it is necessary to consider the effect of self-citation on Hirsch index for every author to have better measuring on the quality of researchers scientific production.
Materials and Methods: This research is descriptive method of citation analysis in general and specifically self-citation analysis. The study, are Iranian prolific authors in the field of medicine that have at least 30 documents indexed in Web of Science database between 2004 to 2006. Citations following up was studied till December 2010 Results was analysis using Excel software version 2007.
Results: The average self-citation observed between prolific authors in medical field was 25/89 percent. Hirsch index for 30/77 percent of authors had changed considerably. The authors rating scheme based on Hirsch index was done after removing self - citation so that 38/46 percent of authors decreased to lower level.
Conclusion: Considering that 10 to 30 percent of self-citation can be normal and justified, the status of self-citatin of Iranian prolific authors in medical field is desirable. Also, lower rates of self - citation of these authors doesnot affect Hirsch index.
Mohammad Reza Rezayi Mofrad, Fatemeh Rangraz Jeddi, Maryam Rangraz Jeddi,
Volume 5, Issue 3 (11-2011)
Abstract
Background and Aim: Knowledge about the external causes of accidents is vital for their prevention, and insufficient data on external causes can reduce their usefulness. That is why, the adequacy of the sources of data is of great importance. The aim of this research is to study the adequacy of data regarding the injuries' external causes for coding based on ICD-10 in inpatient medical records and emergency wards of Kashan Shahid Beheshti Hospital.
Materials and Methods: This prospective descriptive cross-sectional research was done on 1000 patients in Kashan Shahid Beheshti Hospital in 1386 (2007). The data needed for coding were chosen from medical records based on ICD-10 rules and for the following groups: transportation accidents, poisoning, burns, lightning, assaults, respiratory threats, intentional self harm, contact with venomous animals, and exposure to animate and inanimate mechanical forces. Then, the data were put in a checklist and analyzed with SPSS and descriptive statistics.
Results: The data required for the three main characters of the external causes of injuries were adequate in 740 files (47%) the figure for the fourth character of the external causes of transportation accidents was found to be 430 (88.7%). Figures for the place of occurrence and the type of subjects' activities at the time of accidents were found to be sufficient in 109 cases (21.16%) and 50 cases (5%), respectively.
Conclusion: Data on the eternal causes of injuries do not have the required adequacy. More evaluations are essential to enhance the adequacy of such data
Roohollah Askari, Reza Goudarzi, Hossein Fallahzadeh, Bahareh Zarei, Arefeh Dehqani Tafti,
Volume 6, Issue 3 (9-2012)
Abstract
Background and Aim: Paying attention to efficiency of cost and performance in hospitals as the largest and the most costly performing unit of the health care systems is very crucial. This study aimed to assess the efficiency of hospitals related to Yazd University of Medical Sciences (YUMS).
Materials and Methods: In this study, the efficiency of Hospitals of YUMS was assessed by Data Envelopment Analysis method during years 2000- 2008. The variables were of two types: output variables including the percentage of occupied beds, inpatient days and the number of surgical procedures and input variables were number of active beds, nurses, medical staff and other personnel. The data was analyzed using Deap2.1 software.
Results: Average of technical, management and scale efficiency of hospitals was 0.958, 0.986 and 0.963 respectively. We concluded that the capacity of efficiency promotion in hospitals is increasable up to 5%. In addition, the nurses as one of the most important input variables, had the most apparent slack inputs.
Conclusion: Although the level of efficiency was optimal and there was little unused capacity for increasing efficiency in hospitals, however, managers should plan to increase the efficiency. Finally, assessing the effect of variables such as service quality and patient satisfaction on hospitals efficiency is recommended.
Fatemeh Rangrazjeddi , Alireza Moraveji , Fatemeh Abazari ,
Volume 7, Issue 6 (3-2014)
Abstract
Background
and Aim: Evidence Based Medicine (EBM) is the explicit use of current best
evidence in making decisions about the care of individual patients. Hospital information system (HIS) can act as a
bridge between medical data and medical knowledge through merging of patient's
data, individual clinical knowledge and external evidences .The aim of this
research was to determine the Capability to establish EBM by HIS.
Materials
and Methods: This descriptive cross-sectional study was carried out on HISs of 30
hospitals from March to October 2011. Data were collected using a researcher-
constructed checklist including applicant’s background information as well as
information based on research objectives. Validity of the checklist were
assessed by the qualified specialists and then the data were analyzed using
descriptive statistics and SPSS software.
Results: HISs lacked the essential components for providing access to CDSS,
Reference databases and internet-based health information in 19, 16 and 20
hospitals were 63.3%, 53.3% and 66.7%, respectively. Twenty-two hospitals (70%)
had more than two-thirds of the essential components to access clinical and
administrative data repositories 23 hospitals (76.7%) had at least one
essential component to access contextual and case specific information.
Conclusion: The Capability of HIS is better in order to place EBM in
having access to the clinical and administrator data repositories while it
needs more attention in other areas.
Seyed Javad Ghazi Mirsaeid , Zahra Pouramini,
Volume 7, Issue 6 (3-2014)
Abstract
Background
and Aim: The lack of paying attention
to overlap between two databases cause purchase of duplicate resources waste of
funds. This study examined overlap of articles in the field of cardiovascular
which was indexed in Scopus and Web of science databases during years 2001 to
2010.
Materials
and Methods: In this study, at first,
sub-headings in cardiovascular field from medical thesaurus (Mesh 2012) was
extracted, then each keyword in the title of the articles in both databases
were searched and articles retrieved. Then bibliographic information of these
articles entered into Endnote X3 software and afterwards was arranged based on
alphabetically title. As a result common articles between the two databases and
unique articles to each database was determined. Using SPSS version 0.1.0.8 the amount of relative and traditional overlaps was
calculated between the two databases.
Results:
Totally 45,680 articles were
retrieved. There were 27,979 common titles, 14,875 articles belonged only to
Scopus and 2826 articles belonged to Web of Science. Finally traditional
overlap was 61/5%. Overlaps of Web of Science with Scopus 65/28% and Scopus
with Web of Science were 65/28% and 90/82% repectively.
Conclusion: The amount of relative overlap between the two
databases as well as relative overlaps from Scopus with Web of Science is more
than the relative overlaps from Web of science with Scopus. It means many
articles that have been indexed in Scopus don’t exist in the Web of science.
Maryam Ahmadi, Azadeh Bashiri,
Volume 8, Issue 2 (7-2014)
Abstract
Background and Aim: In order to better design an electronic health record system in the
country, determining standardized data elements for creating an integrated
information system is important. In this study, the minimum data set of
radiology reporting system is determined.
Materials and Methods: In this descriptive cross-sectional study, 13 radiologists, 3
anesthesiologists, 3 general practitioners and 3 insurance experts working in
the Imaging Center of Imam Khomeini hospital in Tehran were chosen. The
research tool was a questionnaire having 11 parts. Content validity and
test-retest method were used to measure the validity and reliability of the
questionnaire, respectively. Data analysis was performed using the SPSS
software.
Results: The highest means
reported were radiologists' written explanations and suggestions (9.6), image
interpretation (9.5), the name of contrast material (9.4), the name of imaging
procedure (9.3) type and date of previous measures (9.1), and the final
diagnosis (9) and the lowest averages belonged to referring physician's
address (4.8), relationship between patients and the primary individual insured
(4.3), and religion (2.2).
Conclusion: In an electronic health record system, due to
the importance of radiology reports for the diagnosis and future management of
a patient's clinical problems, it is necessary to pay attention to the minimum
set of data related to these reports such as administrative, insurance, patient
identity, and clinical data, and the results of radiological examinations for exchanging
with electronic health record system.
Reza Safdari, Hossein Dargahi, Farzin Halabchi, Kamran Shadanfar, Robab Abdolkhani,
Volume 8, Issue 2 (7-2014)
Abstract
Background
and Aim:
The quality of health record depends on the quality of its content and proper
documentation. Minimum data set makes a standard method for collecting key data
elements that make them easy to understand and enable comparison. The aim of
this study was to determine the minimum data set for Iranian athletes’ health
records.
Materials
and Methods: This study is an applied research of a descriptive - comparative type which was carried out in 2013. By using internal and external forms of documentation, a checklist was
created that included data elements of athletes health record and was subjected
to debate in Delphi method by experts in the field of sports medicine and health information management.
Results: From 97 elements which
were subjected to discussion, 85 elements by more than 75 percent of the
participants (as the main elements) and 12 elements by 50 to 75 percent of the
participants (as the proposed elements) were agreed upon. In about 97
elements of the
case, there was no significant difference between
responses of alumni groups
of sport pathology and sports medicine
specialists with medical record, medical
informatics and information
management professionals.
Conclusion: Minimum
data set of Iranian athletes’ health record with four information categories
including demographic information, health history, assessment and treatment
plan was presented. The proposed model is available for manual and electronic
medical records.
Taha Samad Soltani , Mostafa Langarizadeh, Maryam Zolnoori,
Volume 9, Issue 3 (9-2015)
Abstract
Background and Aim: Data mining is a very important branch in deeper
understanding of medical data, which attempts to solve problems in the diagnosis
and treatment of diseases. One of the most important data mining applications is to
examine the existing data patterns. The present study aims to examine the existing
data patterns of patients with asthma.
Materials and Methods: This study was performed on 258 patients with
respiratory symptoms, who referred to Imam Khomeini and Masih Daneshvari
Hospitals in 2009. All records were entered into Excel software, and data mining
add-ins were used. Analyses such as key influencers, cluster analysis of patients,
and detecting exceptions have been done.
Results: The most common clinical sign of asthma among subjects was severe
coughing, which was highly affected by thrills. The data were aggregated into 5
clusters for more general analyses. Their common denominator was then identified
and the records with exceptional features were determined. Then, following cost
analysis and setting the threshold value at 612, a questionnaire was developed
based on data features for diagnosis of asthma.
Conclusion: The developed framework for data mining and analysis is an
appropriate tool for knowledge extraction based on the data and their relationships.
Meanwhile, it can identify and fill the existing gap in medical decision- making
when using clinical guideline
Zahra Abazari , Aref Riahi , Fariba Sohbatiha, Hasan Siamian , Mousa Yamin Firoz ,
Volume 9, Issue 3 (9-2015)
Abstract
Background and Aim: Scholarly journals are quite necessary for each
society’s scientific life, especially the medical society, because they represent the
academic community’s achievements to a large extent at regional, national and
international levels. The present research, therefore, aims at a comparative study on
the qualitative and quantitative growth of journals and articles in medical sciences
and related fields in Eastern Mediterranean Regional Office (EMRO) member
countries in Scopus.
Materials and Methods: This is a descriptive survey with a scientometric
approach. The population of the study includes scientific journals and articles in
medical sciences indexed in Scopus database. In this study, EMRO academic
products and 140 scientific journals have been investigated.
Results: The results show that a large number of member countries’ scientific
works have been produced and published in medical fields (The main topic of
144,628 out of 573,067 documents published by these countries has been medical
fields). Meanwhile, the number of journals which were indexed during the studied
period increased from 17 to 127.
Conclusion: The production of scientific documents and academic journals in
the field of medicine in EMRO member countries has increased during the studied
period and has had a considerable leap in the final years. Academic articles have
increased along with the increase in scientific journals in these countries.
Reza Safdari, Leila Shahmoradi, Maryam Ebrahimi ,
Volume 9, Issue 3 (9-2015)
Abstract
Background and Aim: Pathology Information Systems provide opportunities for pathologists and clinical laboratory professionals to influence clinical care and modern research programs. The objective of this study was to determine the minimum data set of Anatomical Pathology Information System from the experts’ point of view.
Materials and Methods: This study is considered an applied research conducted through a descriptive cross-sectional research method. The research instrument was a questionnaire containing data elements related to sample and those related to the patient. This questionnaire was completed by three groups of participants including 22 experts in the field of Pathology and Laboratory Medicine, 23 experts in Health Informatics and Health Information Management, and 6 Insurance experts. The collected data were analyzed using descriptive statistics and SPSS software.
Results: The results indicated that all information elements contained in the questionnaire except the address of the pathologist, resident or the person who performs the act of gross examination were considered as informational elements essential to the system and the high average of five was allocated to them.
Conclusion: Based on the results of this study, the Minimum Data Set of Anatomical Pathology Information System can be presented in two main categories: Clinical and non-clinical information, which include identity information, management information, insurance information, clinical information and the data related to the study of anatomiaca pathology samples.
Mehdi Khakian, Javad Neshani Sadabad, Mohammad Hadian, Hosein Ghaderi, Malihe Ram, Yaser Jouyani,
Volume 9, Issue 4 (11-2015)
Abstract
Background and Aim: In a severely inflationary environment with unemployment, social problems increase and, therefore, high health care expenses are imposed on the society.
Materials and Methods: This was a correlational study. Panel data model and EVeiws 6 software were used in this study. The data were collected from the World Bank website. The required pre-tests, including F-Limer and Hauseman tests, were given to check the appropriateness of data and to determine a appropriate model. Following the pre-tests, the results were estimated in the form of a regression model.
Results: The results indicated that F-test and t-statistic were significant, and that R2 statistic was high. In the three models, R2 was 99%, 99% and 98%, respectively. Moreover, it can be said that employment is positively related with life expectancy, but negatively related with infant mortality and total fertility rate. Also, inflation is negatively related with life expectancy, but positively related with infant mortality, and total fertility rate. Finally, Gross Domestic Product (GDP) is negatively related with total fertility rate and life expectancy, but has no meaningful relationship with infant mortality (p = 0.31).
Conclusion: Employment, inflation and GDP are the variables that have the greatest impact on health indicators. however, life expectancy is more sensitive to explanatory variables.
Narjes Mirabootalebi, Maryam Ahmadi, Mohammad Dehghani, Shahram Khani, Mohsen Azad,
Volume 10, Issue 5 (1-2017)
Abstract
Background and Aim: Electronic Medical Record system collects and stores laboratory data, digital images and electronic versions. It plays a major role in reducing medical errors and duplication and health care providers immediate access to patient medical records. This study aimed to examine the viewpoints of Hormozgan University of Medical Sciences' administrators on the role of electronic Medical records system.
Materials and Methods: The study was a descriptive-analytical research to examine the viewpoints of Hormozgan University of Medical Sciences' administrators and physicians on the role of electronic medical records system. The study population consisted of 61 managers, matrons and health information managers of Hormozgan hospitals and 121 faculty physicians and residents. Data collection tool was a researcher-made questionnaire. The validity was determined and verified by content validity method and experts' views. Cronbach's alpha coefficient was used for assessing reliability, which was 83%. Data collected from the questionnaires was analyzed using SPSS software and descriptive statistics and analytical statistics.
Results: Results indicated that "data management" (N=146) with 77.5%, "job objectives and processes" (N=160) with 87.9%, "communication" (N=163) with 89.6%, "data privacy and security" (N=152) with 83.1% had the most important roles in the health system.
Conclusion: Generally, managers and physicians attitudes about the role of electronic medical records system in the health system was evaluated satisfactorily. According to the advantages of the system and removing major obstacles in its implementation, a new step would be taken in order to promote health.
Sajad Mazaheri , Maryam Ashoori, Zeynab Bechari,
Volume 11, Issue 3 (9-2017)
Abstract
Background and Aim: Nowadays heart disease is very common and is a major cause of mortality. Proper and early diagnosis of this disease is very important. Diagnostic methods and treatments of the disease are so expensive and have many side effects. Therefore, researchers are looking for cheaper ways to diagnose it with high precision. This study aimed to identify a model for the treatment of heart disease.
Materials and Methods: In this descriptive cross-sectional study, the sampling method was census. The sample consisted of data from Khatam and Ali Ibn Abi Talib Hospitals in Zahedan. The data were developed as an Excel file, and Clementine12.0 software was used for data analysis. In the present study, C5.0, C & R Tree, CHAID, and QUEST algorithms and artificial neural network were carried out on the collected data.
Results: The accuracy of 76.04 by C & R algorithm indicates the better performance of Decision Tree Algorithms than that of the Neural Network.
Conclusion: This study aimed to provide a model for the prediction of a suitable heart disease treatment to reduce treatment costs and provide better quality of services for physicians. Due to considerable implementation risks of invasive diagnostic procedures such as angiography and also obtaining successful experiences of data analysis in medicine, this study has presented a model based on data analysis techniques. The improvable point of this model is the provision of a decision support system to help physicians to increase the accuracy of diagnosis in the treatment of diseases.
Ali Mohammad Mosadeghrad, Parvaneh Esfahani , Marziyeh Nikafshar,
Volume 11, Issue 3 (9-2017)
Abstract
Background and Aim: Increasing healthcare organizations’ efficiency is a necessity due to the resource scarcity in health sector. The aim of this study was to evaluate hospitals’ efficiency in Iran.
Materials and Methods: This study was conducted using a systematic review and meta-analysis approach to find empirical research papers published on hospital efficiency in Iran between 1997 and 2016. Seven electronic databases and two search engines were searched using appropriate key words. Bibliography section of the retrieved papers and related journals were also searched for papers that were not yet indexed in the data bases. 1563 publications were identified. All retrieved papers were assessed using a checklist before analysis. Finally 91 empirical studies were reviewed.
Results: Data Envelopment Analysis, Pabon Lasso and Stochastic Frontier Analysis methods were mostly used for measuring hospital efficiency respectively. The average efficiency of Iran hospitals varied between 0.584 and 0.998. Hospitals affiliated to Social security organisation were more efficient. In contrast, non teaching public hospitals and charity and private hospitals were less efficient. Number of hospital beds and manpower were the most used input variables and number of outpatients and inpatients patient and surgical procedures were the most used output variables in Data Envelopment Analysis. Stochastic Frontier Analysis method has more advantage in measuring hospital efficiency compared to Data Envelopment Analysis.
Conclusion: Iran hospitals suffer from inefficiency. Thus, managers should identify the reasons for hospitals’ ineffeiciency and apply measures for increasing their efficiency and reducing wastage of limited resources.
Seyed Abbas Mahmoodi , Kamal Mirzaie, Seyed Mostafa Mahmoodi ,
Volume 11, Issue 3 (9-2017)
Abstract
Background and Aim: Gastric cancer is the second leading cause of cancer death in the world. Due to the prevalence of the disease and the high mortality rate of gastric cancer in Iran, the factors affecting the development of this disease should be taken into account. In this research, two data mining techniques such as Apriori and ID3 algorithm were used in order to investigate the effective factors in gastric cancer.
Materials and Methods: Data sets in this study were collected among 490 patients including 220 patients with gastric cancer and 270 healthy samples referred to Imam Reza hospital in Tabriz. The best rules related to this data set were extracted through Apriori algorithm and implementing it in MATLAB. ID3 algorithm was also used to investigate these factors.
Results: The results showed that having a history of gastro esophageal reflux has the greatest impact on the incidence of this disease. Some rules extracted through Apriori algorithm can be a model to predict patient status and the incidence of the disease and investigate factors affecting the disease. The prediction accuracy achieved through ID3 algorithm is 85.56 which was a very good result in the prediction of gastric cancer.
Conclusion: Using data mining, especially in medical data, is very useful due to the large volume of data and unknown relationships between systemic, personal, and Behavioral Features of patients. The results of this study could help physicians to identify the contributing factors in incidence of the disease and predict the incidence of the disease.
Shahram Sedghi, Somayeh Ghaffari Heshajin ,
Volume 11, Issue 4 (12-2017)
Abstract
Background and Aim: Indexing a country's scientific journals in international citation databases can lead to the promotion of its academic status and its participation in global knowledge production. This study aimed to assess the conformity of Iranian English-language medical journals’ citations with the objective criteria of journals in the selected databases.
Materials and Methods: This was a descriptive, evaluative research. The study population included 52 Iranian English-language medical journals that are not indexed in Web of Science, PubMed and Scopus databases and 465 articles in these issues, and about 11235 citations to the articles. The data have been collected by a checklist. For data analysis, Excel software was used.
Results: Some 88.5 percent of journals had a style for writing references; a style that has been observed by most of them. The rate of self-citation was low. Only 2.9 percent of citations were done in the year this study was performed. Journals with 87.2 percent had received the highest number of citations. The old citation time and the imbalance in the types of cited resources were the most important reasons of the weakness of the studied journals and of their not being indexed in the mentioned databases.
Conclusion: Providing valid styles for writing references and controlling the citations accurately should be put on the agenda of journals. The time of references must be newer, and there should be a relative balance in the types of referenced sources.
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.
