Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
10
01
Prediction of Protein Thermostability by an Efficient Neural Network Approach
102
110
42674
EN
Jalal
Rezaeenour
Mansoureh
Yari Eili
Zahra
Roozbahani
Mansour
Ebrahimi
Journal Article
2016
10
01
Introduction: Manipulation of protein stability is important for understanding the principles that govern protein thermostability, both in basic research and industrial applications. Various data mining techniques exist for prediction of thermostable proteins. Furthermore, ANN methods have attracted significant attention for prediction of thermostability, because they constitute an appropriate approach to mapping the non-linear input-output relationships and massive parallel computing.Method: An Extreme Learning Machine (ELM) was applied to estimate thermal behavior of 1289 proteins. In the proposed algorithm, the parameters of ELM were optimized using a Genetic Algorithm (GA), which tuned a set of input variables, hidden layer biases, and input weights, to and enhance the prediction performance. The method was executed on a set of amino acids, yielding a total of 613 protein features. A number of feature selection algorithms were used to build subsets of the features. A total of 1289 protein samples and 613 protein features were calculated from UniProt database to understand features contributing to the enzymes’ thermostability and find out the main features that influence this valuable characteristic.Results:At the primary structure level, Gln, Glu and polar were the features that mostly contributed to protein thermostability. At the secondary structure level, Helix_S, Coil, and charged_Coil were the most important features affecting protein thermostability. These results suggest that the thermostability of proteins is mainly associated with primary structural features of the protein. According to the results, the influence of primary structure on the thermostabilty of a protein was more important than that of the secondary structure. It is shown that prediction accuracy of ELM (mean square error) can improve dramatically using GA with error rates RMSE=0.004 and MAPE=0.1003.Conclusion: The proposed approach for forecasting problem significantly improves the accuracy of ELM in prediction of thermostable enzymes. ELM tends to require more neurons in the hidden-layer than conventional tuning-based learning algorithms. To overcome these, the proposed approach uses a GA which optimizes the structure and the parameters of the ELM. In summary, optimization of ELM with GA results in an efficient prediction method; numerical experiments proved that our approach yields excellent results.Keywords: Protein Stability, Primary and secondary structures, Extreme learning machine, Neural networks, Genetic algorithm
Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
10
01
Adjustment and Development of Health User’s Mental Model Completeness Scale in Search Engines
111
119
42676
EN
Maryam
Nakhoda
Zahra
Kazempour
Nader
Naghshineh
Mahdieh
Mirzabeigi
Journal Article
2016
10
01
Introduction: Users’ performance and their interaction with information retrieval systems can be observed in development of their mental models. Users, especially users of health, use mental models to facilitate their interactions with these systems and incomplete or incorrect models can cause problems for them . The aim of this study was the adjustment and development of health user’s mental model completeness scale in search engines.Method: This quantitative study uses Delphi method. Among various scales for users’ mental model completeness, Li’s scale was selected and some items were added to this scale based on previous valid literature. Delphi panel members were selected using purposeful sampling method, consisting of 20 and 18 participants in the first and second rounds, respectively. Kendall’s Coefficient of Concordance in SPSS version 16 was used as basis for agreement (95% confidence).Results:The Kendall coefficient of Concordance (W) was calculated to be 0.261(P-value<0.001) for the first and 0.336 (P-value<0.001) for the second round. Therefore, the study was found to be statistically significant with 95% confidence. Since the increase in the coefficient in two consecutive rounds was very little (equal to 0.075), surveying the panel members were stopped based on second Schmidt criterion and Delphi method was stopped after the second round. Finally, the dimensions of Li’s scale (existence and nature, search characteristics and levels of interaction) were confirmed again, but “indexing of pages or websites” was eliminated and “Difference between results of different search engines”, “possibility of access to similar or related webpages”, and “possibility of search for special formats and multimedia” were added to Li’s scale.Conclusion: In this study, the scale for mental model completeness of health users was adjusted and developed; it can help the designers of information retrieval systems in systematic development of these systems and can also help librarians and informatics experts in recognizing the necessary trainings for users in order to improve their information retrieval skills. Also, as a valid and adapted scale for Iranian universities of medical sciences, it can be used for investigating completeness level of health information users’ mental models of search engines.Keywords: Mental Model Completeness Scale, Health users, Search engines
Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
10
01
Services quality in emergency department of Nemazee Hospital: Using SERVQUAL model
120
126
42677
EN
Maryam
Gholami
Manager of Clinical Research Development Center,, Shiraz University of Medical Sciences, Nemazee HospitalShiraz, Iran,postal code: 71937-11351
Zahra
Kavosi
0000-0001-8662-7987
Marziye
Khojastefar
Journal Article
2016
10
01
Introduction: Patient satisfaction is crucial to the long-run success in health care center. With regard to the highest patients’ referral to the emergency department and the existing challenges due to the patient’s need to urgent care, we aimed to evaluate health care services quality in this unit to find out whether the patients have different expectations from health care providers and if they perceive some dimensions of care more important than others.Method: The SERVQUAL scale method was used in this cross-sectional study on 100 patients in June 2015. Patient satisfaction questionnaire based on SERVQUAL model was evaluated with high content validity and the reliability was 0.97 and 0.81. The data collected were analyzed using SPSS, version 20.0 (IBM, USA). Statistical analyses included descriptive statistics, paired and independence sample t-test and ANOVA at the significance level 0.05.Results:The results showed that the quality gap in all dimensions was significant (P<0.001). The largest quality gap was related to responsiveness (-1.08) and the lowest belonged to assurance (-0.8). Demographic characteristics were analyzed and the number of referrals was significant in tangibility and assurance dimensions (P = 0.04); also, in all cases the patients’ expectations (total Mean=4.35) were higher than their perception (total Mean = 3.295).Conclusion: In order to improve emergency services, it is recommended that the hospital management should provide appropriate facilities, reduce waiting time, increase in attention to ordering system based on the patients’ condition, and improve the behavior of health care personnel to patient is placed on the agenda of hospital management.Keywords: Management, Quality of service, Emergency department, SERQUAL model
Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
10
01
The effect of a well-designed computerized physician order entry on medication error reduction
127
131
42678
EN
Hamid
Moghaddasi
0000-0002-5906-0329
Samad
Sajadi
Masoud
Amanzadeh
Journal Article
2016
10
01
Introduction: Paper-based prescription orders, commonly having numerous medication errors, can increase adverse drug events (ADEs) and threaten the patient’s safety. Computerized physician order entry (CPOE), as an appropriate alternative, can significantly reduce medication errors. This study aimed to investigate the effects of well-designed CPOE in reducing medication errors and ADEs.Method: Electronic databases including EBSCO Host, Web of Science, PubMed, SID, Google Scholar, Iranmedex, Irandoc were used to conduct the literature review. We reviewed all the papers published about CPOE and its impacts on medication errors from 1998 until 2015. Thus 56 articles were found. Considering the relevance of their title and abstract with the objectives of the study, and deleting repetitive cases, 32 articles were selected, among which 10 articles were directly related to the objectives of the study.Results:A number of studies indicate that CPOE can reduce the incidence of serious medication errors and ADEs. Nonetheless, there is evidence indicating that CPOE could negatively affect the patient’s health if the system is not well-designed.Conclusion: The replacement of conventional, paper-based prescription orders with well-designed CPOEs in hospitals could play a key role in minimizing medication errors and improving the patients’ safety. To this end, the CPOEs have to be designed according to recent standards and needs.Keywords: Paper-based Prescriptions, Well-Designed CPOE, Medication Errors.
Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
11
19
Evaluation of the structure of websites of educational hospitals of Fars province in 2016
132
137
42679
EN
Mohtaram
Nematollahi
Elham
Fallahnejad
Fatemeh
Niknam
Khadije
Nadri
Fatemeh
Khademian
Journal Article
2016
11
19
Introduction: In the recent years, evaluation of websites has become one of the main organizational instruments for the relationship between provision of services for customers and beneficiaries. Despite the high costs for design and implementation of websites, less attention has been paid to evaluation of these websites’ function. This might be due to the lack of appropriate instruments and frameworks for evaluation of websites. In order to assess hospitals’ information, their websites have to be evaluated regarding webometric criteria so as to identify their strength and weaknesses. Therefore, this study aimed to evaluate the websites of educational hospitals of Fars province in 2016.Method: In this descriptive study, the subjects included all the 43 active websites of educational hospitals of Fars province; they were evaluated by three experts in health information technology. The study data were collected using a checklist whose validity had been confirmed in the previous studies. After all, the data were analyzed using descriptive statistics, SPSS 21 and Excel 2013 software, and the results were presented through tables.Results:The mean scores obtained from three evaluators showed that out of the 43 hospitals under investigation, 35 and 8 hospitals were ranked as good and moderate hospitals, respectively. In addition, the lowest score was related to interactive exchange of views (30.25%), while the highest scores were related to information objectivity (100%), information accuracy (100%), and non-textual views (100%).Conclusion: The overall quality level of most of the hospital was relatively acceptable. But it is necessary that the hospitals improve their websites based on information updatedness, coverage of special addressees, navigation, efficiency and interactive exchange of views. The improvement in the latter criterion will help in reducing the number of daily referrals to the hospitals.Keywords: Evaluation, website, Internet
Shiraz University of Medical Sciences
Health Management & Information Science
2783-302X
3
4
2016
11
19
Injustice in Access to Health Information: The Difference between Health Professionals and Patients
138
139
42675
EN
Hasan
Ashrafi Rizi
Fatemeh
Zarmehr
Journal Article
2016
11
19
The role of information is undeniable in promoting public health (1-3). “Access to health information for all” was the slogan of the World Health Organization in 2004 (4). The proving of this slogan requires access to health information by beneficiaries (health professionals and patients). Access to health information by specialists as partly been achieved, but access to health information for patients and their families is considered low (5-7), which could have adverse effects. Health professionals have quick and easy access to information through libraries and medical information centers, participation in seminars, exchange of scientific information with other professionals, as well as identifying ways to effectively access to health information, but patients and their families do not have access to such facilities and capabilities. Therefore, patients and their families are faced with a phenomenon known as “inequity in access to health information” and the continuation of the injustice leads to health information poverty. Thus, the main question now is what we should do? It seems that the government needs to develop a national policy in the field of health information and it is the most important step. In the next step, the government should expand the concept production via using potentials of different organizations like public media (TV and Radio), health ministry and press and increase the access of patients to health information in the easy language (level of health information between health professionals and patients is different).