مجله انفورماتیک سلامت و زیست پزشکی
سال پنجم شماره 1 (پیاپی 15، بهار 1397)

Psychological anomalies have a significant prevalence in the world, especially in developing countries, such as Iran, and require the development of various interventions for diagnosis, treatment, monitoring and care services. Regarding the nature of psychological abnormalities monitoring, and especially the self-inventory testing method, it is recommended to use telemedicine capabilities for remote monitoring of patients with these abnormalities. The purpose of this study was to design and model a self-reported psychiatric system for depression.
In this study, firstly, by reviewing the texts and observing similar systems, interviewing the psychiatric specialists of Shahid Beheshti Hospital of Kerman, nurses and patients of this center, and presenting and analyzing the questionnaire, the requirements of such a system were elicited and presented in the form of diagrams such as Class and business use Case in UML2.0. In order to provide a general view of prospective view, context diagram was presented. Scenario-based and simulation strategies were used to evaluate the model.
By reviewing 33 similar studies and 45 websites related to similar systems, seven subsets of account, education, counseling, treatment, monitoring, financial affairs and communications were defined and listed with the full definition of relevant items, and communication types were presented by UML diagrams. Also, in the first step of the evaluation of 20 scenarios, the final scenario was approved by experts. Simulation indicators represent the high efficiency of the system.
The results of the evaluation of the proposed system show that the proposed system is satisfactory in terms of qualitative criteria and covers all expected functional requirements.

The study and analysis of each health system has become a necessity for its performance improvement through time. In this context, management and analysis of the number of patients is an important factor in the process of improving manager's decisions. The aims of this study were to explore and evaluate the use of multiple time series forecasting methods to predict monthly hospital inpatient admissions at six public hospitals in Mashhad city and to compare the accuracy performance of these methods.
This cross-sectional modeling study was performed based on monthly data of inpatient admissions at six public hospitals in Mashhad from March 2004 through March 2016. Data were extracted from database of the Statistics Office of Mashhad University of Medical Sciences. Holt-winters, Seasonal Autoregressive Integrated Moving Average (SARIMA), Multilayer Perceptron (MLP) and Generalized Regression Neural Networks (GRNN) models were applied to forecast monthly inpatient numbers at each hospital. The error of the models in regard to the predicted values was reported through Mean Absolute Percentage Error (MAPE).
Holt-Winters method, due to providing the optimal forecasting performance in four hospitals, could be an efficient method for predicting the number of inpatients in hospitals. Totally, the studied models with a MAPE from 2.13% to 4.12% showed acceptable performance in all six hospitals.
Time series analysis is an adequate practical tool for predicting the number of hospital inpatient admissions. Given the unique characteristics of different hospitals, applied methods in this study, including modeling and data analysis can be used in other hospitals to improve their resource allocation and strategic planning.

Combination of artificial intelligence and data mining has been resulted to considerable progress in the prevention and diagnosis of diseases. Complex models have been proposed for the diagnosis of acute leukemia from genetic information, but significant results have not been achieved. This study aimed to predict the type of blood cancer by examining a wide range of parametric and non-parametric methods and to increase the generalization of learning by extracting fewer essential features.
This descriptive and analytical study used Leukemia1 dataset from the Vanderbilt University of USA. This dataset contains a set of bone marrow and blood samples of patients having leukemia used for classification based on three subgroups of leukemia, namely ALL B-cell, ALL T-cell and AML. Parametric classification including linear algorithms, Naïve Bayes, Euclidean distance, nearest average, template matching as well as non-parametric classification using basic estimator algorithms, kernel, k-nearest neighbors and k-nearest neighbors based on the kernel has been used.
Considering all features, the best method was nearest mean prediction method achieving the accuracy of 92.86%. By applying the PCA feature reduction method, too, the best result was related to the nearest mean algorithm and by average number of features of 6.8, the accuracy became 96%. Finally, using data-balancing methods and quadratic algorithm resulted in the average number of features and the accuracy of 5.41 and 98.59% respectively.
The results show the effectiveness of essential features extraction in improving the accuracy of Bayes-based models and its preference over the existing complex models.

Mobile phone, as a manifestation of modern communication technology, has a strong position in human life and is an integral part of daily life. The health industry is also one of the main areas where mobile penetration in the industry has resulted in surprising advances and various challenges. Mobile health (activities and medical operations supported by the mobile phone) serves as a digital assistant for information, health and personal care. Health commercialization is a global phenomenon and many health systems in the world are affected by it. The aim of this study was to prioritize the factors influencing the commercialization of mobile health.
In this applied study, through reviewing studies in the field of mobile health commercialization, 31 leading indicators of mobile health commercialization were identified and after obtaining the opinions of experts and explorative factor analysis, the identified indicators were categorized in 6 dimensions and ranked using a fuzzy hierarchy analysis.
The obtained indicators were respectively, service development, market management, organization and legal processes, technology and infrastructure, finances and large substrates. What is noteworthy in the proposed prioritization compared to the studied documents is the comprehensiveness of the relevant indicators and consideration of the various dimensions of commercialization in relation to similar researches.
Regardless of the prioritization of effective factors on mobile health commercialization, a noteworthy point in this framework is significant importance of convergence of this technology with the economic structure governing health care system of the country, agreement of the technology with basic health infrastructures and methods of improvement of mobile health technology that undoubtedly, each of them, by itself, is an important factor in mobile health commercialization.

Since emotions play an important role in human life, it requires providing an intelligent method to detect emotions using electroencephalogram (EEG) signal based on signal processing techniques. In addition, in this research, using support vector machine (SVM) classifier with genetic evolutionary algorithm is a novelty in classification part.
The proposed method focuses on feature extraction and classification of received signals from brain to improve emotion detection. In this way, firstly, effective EEG channels are identified and then time and frequency features of EEG signals are extracted and classified by an appropriate classifier. The proposed method is applied on DEAP database which includes recorded EEG signals by 32 people watching and listening 40 videos and music.
The experiments show that selection of 7.5 seconds and 3 EEG channels provides acceptable results. In addition, the proposed method reduces computations and required memory and results in 93.86% accuracy for 4 emotion classification.
Improvement in emotion detection based on EEG signals contains several steps in which effective features extraction and classification are two important steps. According to this research, using time-frequency features of EEG signals and optimized SVM classifier with genetic algorithm provides better results.

Cancer is one of the most important health issues in the current and next centuries. Understanding the mechanism of interaction between antibody-protein residues is essential for designing targeted anticancer drugs based on monoclonal antibodies. Prediction of the effective structure is the first step for production of monoclonal antibodies.
This paper is a systematic review of the state-of-the-art researches on prediction of interaction sites and specification of antibody structures. Artificial neural networks or web servers are frequently used for evaluation of interaction sites while some researchers have employed evolutionary algorithms for prediction of the effective structure of antibodies. Accordingly, 14 methods based on the protein spatial structure, 28 researches based on the molecular amino-acide sequence (without usage of the spatial structure), and 18 antigen/antibody structure prediction techniques were reviewed.
We demonstrated that the accuracy of structure-based methods can be increased up to 80% while the acuracy of sequence-based methods was rarely better than 75%. Since the spatial structure of many antibodies is unknown, some researchers raised the accuracy (even to 96%) by only antibody sequences able to interact with some similar antigens in training neural networks. Therefore, we suggest this approach for structure prediction of monoclonal antibodies because of its adequate high accuracy.
In this paper, after reviewing available methods for prediction of antibody-protein interaction sites, some suggestions were made for effective prediction of structure of monoclonal antibodies.

Documenting nursing reports and recording data are among the first and most important tasks of nurses. Speech recognition technology has been introduced as one of the most effective technologies in nursing documentation, which supports the nursing and patient interaction as well as the training of nurses through saving nurse's time. This study aimed to identify the benefits, barriers and facilitators of using this technology in documenting nursing reports.
In this review study, various studies on the use of speech recognition technology in the field of nursing documentation published from 1990 to 2017 were reviewed at Pubmed, Science Direct, Google Scholar, Magiran, SID databases and, finally, ten papers were included in the review. The inclusion criteria were studies published in Persian or English language and the implementation of the speech recognition system in the field of nursing documentation and reporting.
Improvement of workflow, with the highest frequency, was the most important benefit. Reduction of the accuracy of speech recognition software was the first mentioned barrier of using this technology followed by the impact of environmental noises. Sufficient training and use of appropriate tools were found as the most important facilitators of using this technology.
This study helps hospital managers, nursing managers and IT managers of hospitals to better manage selection and implementation of speech recognition system for documenting nursing reports. As a result, reducing productivity due to inaccuracy in voice recognition, lack of improvement in the quality of documentation of nursing reports, increasing the workload of nurses and their involvement in indirect care activities can be prevented.