مجله انفورماتیک سلامت و زیست پزشکی
سال دهم شماره 4 (پیاپی 38، زمستان 1402)

Identifying and diagnosing Alzheimer's disease in brain tissue is one of the serious challenges in diagnosis in the field of medical image processing. Currently, MRI is the most common way to diagnose Alzheimer's disease, and failure to correctly identify the tissue involved in it can lead to incorrect diagnosis as healthy brain tissue. Deep learning algorithm as a process of detecting features related to damaged tissue and extracting useful information. In this research, we decided to use the convolutional neural network in the processing of medical images so that we can perform the diagnosis with better accuracy than the previous works.

Using a convolutional neural network, the features of MRI images have been extracted. Alzheimer's images have been analyzed using Matlab2023a software and the intended outputs have been obtained.

Brain Alzheimer's images have been analyzed after pre-processing and entering the deep neural network, and in the output of the proposed algorithm, the identification accuracy and identification speed of the algorithm with the improvement of cloud parameters was higher compared to other common methods, which was 96% accuracy. presented in identification.

The purpose of using deep learning is to make image data with large dimensions and a large number into a conceptual form for machines. It is expected that in the future feature extraction will be done more accurately and more details will be available to machine vision systems to recognize objects in the image.

Considering the crucial role of IT unit in maintaining, preserving, and enhancing information systems and providing timely information to various individuals, the services provided by this unit must be of high quality. In this regard, the present study aimed to evaluate the quality of services provided by the Information Technology unit in three selected hospitals in Isfahan city using the SERVPERF model.

This is a quantitative and applied study. The statistical population consisted of all the employees who received service from the information technology unit in the educational hospitals of Isfahan city. The sample size was 351 people based on the Morgan’s table. The service quality of the information technology unit in the studied hospitals was investigated using the standard questionnaire of the SERVPERF model (non-weighted) in five areas.

The average of service quality of the information technology unit was 3.23, which had a statistically significant difference with the average value of 3 (P<0.05). The highest average is related to reliability (3.28) and responsiveness (3.25), respectively. The lowest average is related to the physical and tangible dimensions (3.14).

The results show a negative gap in the service quality of information technology units in hospitals. To improve the quality of services in the dimensions of empathy, responsiveness, satisfaction, humility, goodwill, and information updates, regular training classes should be held for the employees of the information technology unit.

Today, heart attack is one of the most common causes of death in adults all over the world. According to the announcement of the Ministry of Health, Treatment, and Medical Education, 11 to 15 percent of deaths in Iran are caused by heart attacks, and in the world, Iran has the highest number of deaths due to heart disease in 2022. It has been estimated that deaths from these diseases will increase to 20 million people. Therefore, predicting this disease is one of the most challenging topics in the medical field, and today most prediction systems are created using artificial intelligence and machine learning algorithms.

This applied and descriptive research was conducted in 2022 using the information of 600 people who referred to Peymaniyeh and Motahari hospitals in Jahrom city. In this research, data were collected based on the available sources from both hospitals. To implement and evaluate the results, MATLAB programming language was used.

The parameters used in this research are among the classification parameters, including classification rate, precision, recall, and F-measure, which were obtained as 90.7, 90.2, 91.5, and 90.8, respectively.

The results show that the proposed model will be able to predict the probability of stroke with a high percentage.

CRISPR/Cas system is a bacterial-acquired immune system against viruses. spCas9 protein-derived from Streptococcus pyogenes is the most common Cas protein used in genome editing. The Cas9 proteins suffer from some problems like unwanted off-target cleavage, which is the major limitation in the application of the CRISPR system, especially for therapeutic issues. The present study aimed to in silico design of a mutant Cas protein to enhance the fidelity of the enzyme.

In this study, a new Cas9 protein was designed in silico via the selection of some mutations. The interaction of the mutant and wild-type Cas9 proteins with DNA was determined by molecular docking. Finally, the stability of the mutant and wild-type proteins was evaluated using molecular dynamics.

The outcome of this study resulted in designing a mutant Cas9 protein bioinformatically containing 5 amino acid substitutions. Molecular docking scores for the wild-type and mutant proteins were -1073.86 and -349.41, respectively.

Molecular docking indicated that the number of hydrogen bonds between protein and DNA reduced in the mutant state. Moreover, based on the molecular dynamic findings, the stability of both mutant and wild-type Cas9 proteins was similar.

A Roadmap is a tool to help organizations facilitate the successful implementation of any technology. Then, this study aimed to identify and prioritize the stages of blockchain technology roadmap implementation in health-oriented organizations.

To refine and evaluate the appropriateness of steps extracted from the subject literature, the fuzzy Delphi method was used. Access to the most reliable group agreement of experts on a specific issue is done using a questionnaire and asking experts’ opinions, often according to their feedback.

After identifying and extracting the factors through the study of various articles and localization and determining the importance of the variables, by applying the weight limit in the model, the level of experts’ agreement with each of the components was obtained and their suggested and corrective points were divided. The resulting absolute mean indicates the intensity of experts’ agreement with each research factor.

The results of the survey of experts’ views show that the priorities of monitoring technology, identifying the application of blockchain technology in the organization, identifying structural, technical, legal, and financial challenges, designing, removing governance and upstream obstacles, appropriate capital transfer, cooperation between old and new infrastructure, and increasing membership, high importance and priorities of basic training, identifying the benefits of digital transformation and competitive advantage, internal and external stakeholders, and expanding the business model to other sectors are of lower importance.

The minimum data set is considered an important tool in the registration systems and monitoring programs, which provides the possibility of collecting and transferring data at the country level. Considering the importance of tuberculosis in Iran and especially the high incidence of this disease in the marginal provinces of the country, the present study was designed and implemented to determine the minimum data set for the electronic health records of tuberculosis patients.

This descriptive study was conducted in two phases. In the first phase, a comprehensive review was conducted in PubMed, Science Direct, SID, and Magiran databases to identify data elements. The data were collected using the data extraction form and polled using the Delphi method. Descriptive statistics and SPSS version 16 were used for data analysis.

The minimum data set of tuberculosis was divided into two categories: administrative data with five classes and 35 data elements, and clinical data with five classes and 43 data elements.

The minimum data set of tuberculosis is an effective tool for managing and recording the information of patients suffering from this disease. The results of this study can help researchers and developers in the process of designing and implementing an integrated information system for registering the information of patients with tuberculosis.

Since the start of 2020, SARS-CoV-2 has infected a significant number of individuals, prompting extensive research. Antimicrobial peptides can be considered as a promising treatment for emerging viral pathogens due to their safety, efficacy, and specificity.

In this study, first, 104 natural antiviral peptides were chosen from APD databases.  Then, the third structure of proteins was modeled by PEP-FOLD 3 server. The structures were refined and optimized for docking operation. Subsequently, peptide-protein docking was performed using AutoDock Vina. The most favorable peptide-protein complex, chosen based on binding energy, was employed for molecular simulation using GROMACS. The simulation was carried out for 100 ns at 310° K and pH=7. Gromos54a7 force field was used in this study and the SPC water model was used as solvent.

The obtained results from molecular dynamics examine the stability of complex structure and energy calculations. RMSD, RMSF, radius of gyration, and SASA analyses indicate the stability of the peptide-protein complex during the simulation. Additionally, LJ, CL, HBond, and ΔG analyses were conducted to calculate the energy interactions between the peptide and the Spike protein.

The results indicate that antimicrobial peptides can effectively bind to the SARS-CoV-2 spike protein, acting as inhibitors with a favorable binding energy. Consequently, these peptides can be employed for therapeutic and experimental studies of COVID-19.