Journal of Health and Biomedical Informatics
Year:2020 | Volume:7 | Issue:2|Papers Count:12

Introduction: Using modern technologies like virtual reality in rehabilitation can promise a great movement in medical sciences as sometimes, these technologies shorten the path of reaching the goal. In the present study, a virtual reality environment with the ability of physical interaction was designed to test and measure the hand motion, and a sample of electronic equipment was presented alongside the virtual reality to help the patients requiring rehabilitation, so that they can use the special and unique feature of this technology for faster improvement and easier access to the exercises in every location, especially at home. Methods: The design and manufacturing processes were performed in two sections: software and hardware. In the software section, the connection to the hardware section and the available processors and sensors in this section was provided under Windows Operating System by designing the virtual reality environment and the required coding, by using the artificial intelligence available on the software, and by defining the movement conditions. Results: Software-wise and hardware-wise investigation and evaluation of the designed and manufactured equipment were performed according to the type of services provided to 5 patients based on the criteria proposed by Martilla and James involving the importance and performance indicators. The testing and evaluation performed based on these indicators showed the rate of user satisfaction with the provided services and equipment. Conclusions: The results obtained from this study showed that a new treatment method can be provided for rehabilitation by measuring the level and amount of the patient’ s hand movement and transferring these movements to the virtual environment proportional to the real conditions. Thus, alongside traditional rehabilitation methods, this new method can be effective in the improvement and quicker return of the people in need of rehabilitation to normal conditions.

Introduction: Thermography is a non-invasive imaging technique that can be used to diagnose breast cancer. In this study, a method was presented for the extraction of suitable features in dynamic thermographic images of breast. The extracted features can help classify thermographic images as cancerous or healthy. Method: In this descriptive-analytical study, the images were taken from the IC/UFF database. A total of 196 people, including 41 cancer patients and 155 healthy individuals were investigated. Each person had 10 thermographic images and in total, 1960 images were analyzed. The images were captured using the FLIR ThermaCam S45 camera. The proposed model was presented based on a series of breast thermographic images of an individual to extract 8 suitable features. The extracted features included mean, standard deviation, entropy, kurtosis, homogeneity, energy, skewness, and variance. Results: The extracted features were evaluated by the classifiers including the decision tree, support vector machine, quadratic symmetric analysis, and K-nearest neighbor algorithm using the ten-fold cross validation. The accuracy and sensitivity were 99% and 99. 33% for decision tree algorithm, 98. 46% and 95. 12% for support vector machine algorithm, 100% and 100%, and 99% and 97. 56% for K-nearest neighbor algorithm. Conclusion: The results of this study showed that among the first-order statistical features, mean difference, skewness, entropy, and standard deviation are the most effective features which help to detect asymmetry. The features extracted by the proposed model can help classify the individuals into healthy or cancer-affected by thermal images.

Introduction: Breast cancer is one of the most common types of cancer whose incidence has increased dramatically in recent years. In order to diagnose this disease, many parameters must be taken into consideration and mistakes are possible due to human errors or environmental factors. For this reason, in recent decades, Artificial Intelligence has been used by medical practitioners to diagnose this disease. Method: In this applied-descriptive study, the diagnosis of breast cancer using stacked generalization was presented in the form of an ensemble model based on MLP neural network, ID3 decision tree, and support vector machine methods. To improve the performance of the ensemble classification model, a new approach called separator block was used. This block is responsible for identifying instances that cause errors in the classification model. Results: In order to evaluate the accuracy of the proposed method, the Wisconsin database for breast cancer was used. The experimental results showed the superiority of the proposed method over other similar methods. The accuracy of the classification model presented on the WBCD, WDBC, and WPBC datasets from the Wisconsin database was 99. 54%, 99. 58% and 99. 84%, respectively. Conclusion: Data mining algorithms can provide new and more cost-effective systems in the field of health and treatment that can diagnose breast cancer with high accuracy. In this study, modeling based on the stacked generalization technique was of high accuracy in the diagnosis of breast cancer.

Introduction: Chronic diseases are among the most challenging health issues in the world. Although no definitive treatment has been found for such diseases, electronic health strategies can dramatically reduce their complications by enhancing patients' awareness and monitoring their treatment. The main objective of this study was to design an education-based follow-up system for cardiac patients based on mHealth. Method: This research was an applied-developmental one. To determine the data elements, a questionnaire was developed and needs assessment was conducted with the faculty members at University of Mazandaran and 2 health system specialists. The data were analyzed using descriptive statistics and after identifying the entities, the conceptual model of the system was designed and implemented based on the Unified Modeling Language (UML). The questionnaire was finally provided to 30 cardiac patients to assess its usability and user satisfaction. The data were analyzed using descriptive statistics with SPSS Software (version 16). Results: Some modifications were made to the system based on end users’ opinions and ultimately the system was developed with 7 parts including interaction with physician, remote visit, training, notification of medication intake, prescription, follow-up monitoring of patients, and communication with the emergency ward. The final evaluation of usability and user satisfaction showed that users rated the program with a mean score of 7. 17 out of 9 at a good level. Conclusion: Given that users evaluated the system as good, it can provide effective interaction between physician and patient and monitor patient care along with ongoing training to improve the treatment process.

Introduction: The cost estimation of a hospital information system software refers to estimating the cost and time required to develop the hospital information system software prior to the start of the project, which will continue until the end of production and development of the system. Estimating the cost of software to produce hospital information system is one of the major concerns of project management in health companies. Cost estimation models that estimate the cost of system construction in the early stages of project construction, with minimal information available from the project, are useful and needed. Selection of an appropriate cost estimation method enables efficient control of time and cost of system construction. Method: In this retrospective study, 23 open source software projects for hospital information system were selected and the cost of software design and 16 independent variables of each hospital information system software were extracted. The data were then transformed into a test and training set and using a continuous decision tree algorithm, a prediction model was proposed to estimate the cost of designing a hospital information system. The algorithm was then evaluated with four other continuous algorithms. Results: In this study, the continuous decision tree algorithm was implemented using the 10-fold method and two parameters including mean squared error and mean absolute percentage error were used for evaluation. In the proposed model, error of 74. 31 units was obtained for the mean squared error and 17% for the mean absolute percentage error. Conclusion: It was shown in this study that the proposed model had an acceptable error rate indicating that it performed better than similar methods and can be used to estimate the cost of اhospital information systems.

Introduction: Today, healthcare organizations worldwide are aware of the significance of technology and its impact on the quality of care. Hospitals are one of the most crucial systems in which the utilization of information is particularly important for several reasons. Using discreteevent simulation and developing a recommender agent, this study aimed to allocate IoT devices to patients in such a way as to minimize the number of medical errors and the length of treatment. Method: To carry out this research, first, the current condition of the medical care system was modeled using discrete-event simulation. Then, the scenario of introducing IoT into the model was simulated. Finally, using agent-based modeling, the recommender agent was developed to optimize the allocation of IoT devices to the patients. Results: Implementing recommender agent in the simulation model indicated that using IoT and recommender agent in medical processes leads to reducing medical errors and length of treatment. Conclusion: Utilizing the IoT in medical processes reduces errors, although the extent of its effectiveness varies at different stages of treating various diseases. Since some disease-specific IoT devices overlap in their functions, and given the limited number of these devices in hospitals, it is recommended that a recommender agent be used to ensure maximum effectiveness. Recommender agents make informed decisions as to how IoT devices can be efficiently allocated to patients at each stage of their treatment.

Introduction: Prescribing and consuming drugs more than necessary which is known as polypharmacy, is both waste of resources and harm to patients. Polypharmacy is especially important for elderly patients; therefore, the factors affecting it must be identified and analyzed properly. Method: In this retrospective study, first, several classifier algorithms, i. e., C4. 5, SVM, KNN, MLP, and BN for polypharmacy identification were compared in terms of performance using WEKA software. In this process, 16 new features were extracted alongside the four existing features from data on 81, 677 prescriptions of 19, 428 outpatients aged 70 to 95 years whose prescriptions were dispensed in pharmacies contracted by the Iran Health Insurance Organization-Tehran province. The performance comparison was done using corrected t-test with resampling. In order to identify the effect of elderly patients’ characteristics on polypharmacy, two important parameters of the C4. 5 were optimized by grid search using 50% of the dataset and then run on the rest of the dataset. The resulted rules were then presented in the form of a decision tree and verbal expressions. Results: Paired comparison of the classifiers indicated better performance of C4. 5 and BN compared to the others. C4. 5 had the ability to identify the factors that affect polypharmacy. In addition, parameter tuning improved the accuracy and AUC of applied algorithms. It also reduced the size of the resulted decision trees as well as the number of generated rules significantly. Conclusion: The data mining approach and C4. 5 can identify and explain the characteristics of the elderly effective on the polypharmacy. The higher percentage of visits to general practitioners and contacts with a limited number of pharmacies are the most important characteristics.

Introduction: Social network analysis is an analytical method based on graph theories that identifies relationships between individuals or factors to analyze the social structures resulted from those relationships. The objective of this study was to analyze co-authorship and co-word networks based on scientometric indicators and centrality measures in the studies on multiple atrophy system disease published in Web of Science database from 1988 to 2018. Methods: In this descriptive-analytical case study, the articles published in Web of Science database from 1988 to 2018 were collected using medical subject headings (MeSH) and various scientometric techniques including co-word analysis, co-authorship analysis, and network mapping. Results: In this study, 6767 articles on multiple system atrophy disease were retrieved. These articles were written by 39184 authors from 3884 organizations and 80 countries and were collected from 832 journals. In this study, based on co-occurrence, 8 clusters in the subject area of multiple system atrophy disease were identified the most important of which were multiple system atrophy disease, Lewy body, orthostatic, hypotension, progressive paralysis, positron tomography, and genes. Conclusion: Scientometric studies on this disease show a thematic map that can be effective in policy-making for studies in this field. Moreover, by examining these indicators, the issues in this field were identified and through this, the cases that are less taken into consideration can be detected and investigated as future research topics.

Introduction: The metastasis of breast cancer, the spread of cancer to different body parts, is considered as one of the most important factors responsible for the majority of deaths caused by breast cancer in women. Diagnosing the breast cancer metastasis at the earliest stages helps to choose the best treatment and improve the quality of life for patients. Method: In the present fundamental research, the dataset of Iranian patients available at Breast Cancer Research Center of Motamed Cancer Institute in Tehran was utilized. This study used Mamdani fuzzy inference system, Takagi-Sugeno fuzzy inference system and adaptive neuro-fuzzy inference system (ANFIS) to predict breast cancer metastasis at early stages. Results: The best prediction error was obtained using adaptive neuro-fuzzy inference system based on fuzzy c-means approach. The opinion of the experts at Breast Cancer Research Center of Motamed Cancer Institute and the prediction error of the assessed model indicated that this prediction system is well-formed. Conclusion: The optimal proposed prediction system can be used as a clinical decision support system to assist medical practitioners in the healthcare practice.

Introduction: The ability to transfer data over the Internet of Things (IoT) to make right and timely decisions through accurate data collection has provided incredible interactive power and has resulted in an intelligent world with automated decision-making capability. The objective of this study was to investigate the status of IoT-based health information systems in a three-dimensional conceptual framework. . Method: In this descriptive-applied study, first, a comprehensive literature review was conducted to extract studies related to the architecture of IoT-based health information systems from the PubMed, Scopus, Web of Science, and IEEE databases. Then, to analyze and classify the extracted information and reach a consensus on explaining the status of IoT-based health information systems, three sessions of contemplation were held with the formation of a specialized committee. Results: Based on the results of this study, the status of health information systems was elaborated according to the most important functions and applications in three levels including community communication, diagnostic and treatment protocols, and IoT infrastructure. The status of information systems in this framework reflects the relationship between different parts of an organizational structure in the field of health from data collection at the lowest level to knowledge production at the highest level. Conclusion: The practical concept of the IoT as an underlying infrastructure has been overlooked in the design of most current health information systems. Therefore, the proposed model can be used as a guide for designers and specialists in information technology and medical informatics in designing these systems leading to an increase in the design quality of the systems.

Introduction: The major issue for the future of bioinformatics is the design of tools to determine the functions and all products of single-cell genes. This requires the integration of different biological disciplines as well as sophisticated mathematical and statistical tools. This study revealed that data mining techniques can be used to develop models for diagnosing high-risk or low-risk lifestyles for colorectal cancer. Method: In this retrospective study, a dataset consisting of information relevant to 84 patients and 225 healthy individuals with 25 attributes was collected. This information was on patients diagnosed from 2006 to the first quarter of 2014. The most widely used techniques in the medical informatics literature including support vector machine, Naive Bayes, decision tree, and k-nearest neighbor were used to develop the models. Results: The developed models are able to distinguish people's lifestyles efficiently. A welldeveloped non-technical measure can properly determine the true value of individual predictions, whether true or false, at actual costs, and indicate a true measure of the cost savings in the health system by each model. Among the developed models, only two models were able to meet the criteria set for use in the real world. Conclusion: The developed models should not only be technically evaluated, but should also be examined in terms of metrics accepted for the medical field as well as feasibility for real problem solving.

Introduction: Emotions play an important role in health, communication, and interaction between humans. The ability to recognize the emotional status of people is an important indicator of health and natural relationships. In DEAP database, electroencephalogram (EEG) signals as well as environmental physiological signals related to 32 volunteers are registered. The participants in each video were rated in terms of level of arousal, capacity, liking/disliking, proficiency, and familiarity with the video they watched. Method: In this study, a practical empirical method was adopted to classify capacity, arousal, proficiency, and interest by ranking the features extracted from signals using algorithms on EEG signals and environmental physiological signals (such as electromyography (EMG), electrooculography (EOG), galvanic skin response (GSR), respiration rate, photoplethysmography (PPG), and skin temperature. After initializing the signals from the database and pre-processing them, various features in the time and frequency domain were extracted from all signals. In this study, SVM and KNN classifiers, K-means clustering algorithm, and neural networks, such as PNN and GRNN were used to identify and classify emotions. Results: It was indicated in this study that the results of the classification of emotions using various methods and classifiers were well-established with high accuracy. The best accuracy results were obtained by applying the proposed method using SVM classifier based on features extracted from environmental signals (85. 5%) and EEG signals (82. 4%). Conclusion: According to the results of the classification of emotions in this study, the proposed algorithm provides relatively better results compared with previous similar methods.