آزیتا یزدانی

Kidney failure is a common and increasing problem in Iran and worldwide. Kidney transplantation is recognized as a preferred treatment method for patients with end-stage renal disease (ESRD). Machine learning, as one of the most valuable branches of artificial intelligence in the field of predicting patient outcomes or predicting various conditions in patients, has significant applications. The purpose of this research was to predict kidney transplant outcomes in patients using machine learning.

Since CRISP is one of the strongest methodologies for implementing data mining projects, it was chosen as the working method. In order to identify the factors affecting the prediction of kidney transplant outcomes, a researcher-created checklist was sent to some of nephrologists nationwide to determine the importance of each factor. The results were analyzed and examined. Then, using Python language and different algorithms such as random forest, SVM, KNN, deep learning, and XGBoost the data was modeled.

The final model was multilabel, capable of predicting various kidney transplant outcomes, including rejection probability, diabetic reactions, malignant reactions, and patient rehospitalization. After modeling the input data features, the model was able to predict the four kidney transplant outcomes such as rejection, diabetes, malignancy and readmission with an error rate of less than 0.01.

The high level of accuracy and precision of the random forest model demonstrates its strong predictive power for forecasting kidney transplant outcomes. In this study, the most influential factors contributing to patient susceptibility to the mentioned outcomes were identified. Using this machine learning-based system, it is possible to predict the probability of these outcomes occurring for new cases.

With the spread of the Corona pandemic, the statistics of the number of mobile health applications have grown significantly. This research was conducted with the aim of evaluating the content of Persian language applications in the management of Covid-19.

In this review research, a systematic search for Persian language programs in the field of Covid-19 management was conducted in four mobile application markets including Myket, Bazzar, Google Play and App Store. The content of the programs was evaluated based on a researcher-made checklist, which was verified according 3 specialist comments, in the five axes of ease of use, education, monitoring, privacy and data sharing. Programs that received more than 50% of the evaluation score were introduced as selected programs. By removing duplicate programs, 119 programs were extracted, of which 21 programs entered the final stage of quality evaluation based on the inclusion and exclusion criteria and after a complete review of the content and capabilities.

Based on the total points of the program, Safiran Salamat received the most score (31), Ac19 and mask were ranked next with 27 and 22 points, respectively. These three programs along with Corona Amar Tashkhis as fourth program received more than 50% of the content review and 17 other programs received less than 50% of the total score. Government has a great role in programs development (three program were government and one was non- government base). All 4 programs, had acceptable score in ease of use but none of them develop for user tracking. Pearson’s correlation test was used to test the relationship between the quality (total scores of apps) and the popularity (amount of downloads), and no significant correlation was observed.

The results of the present study showed that Iranian mobile applications have an acceptable performance in the fields of education and information sharing, but their low popularity makes the achievement of these goals far from expected. Marketing strategies can be effective as one of the useful policy in increasing the use of mobile health programs. Also, the inclusion of capabilities such as contact tracing and online consultations can be fruitful in the pursuit of goals.

Various studies have demonstrated the benefits of using distributed fog computing for the Internet of Things (IoT). Fog computing has brought cloud computing capabilities such as computing, storage, and processing closer to IoT nodes. The new model of fog and edge computing, compared to cloud computing, provides less latency for data processing by bringing resources closer to users. This is essential for delay-sensitive applications such as remote healthcare and provides more reliable services. In this study, a fog-based system was proposed to monitor the condition of heart patients.

This study was a developmental-applied one. A set of data relevant to coronary heart patients available in the machine learning data repository of the University of California Irvine was used for evaluation. In this system, each of the heart patient's symptoms is evaluated based on the normal range in the fog layer and the status of the patient is determined. In this layer, requests are prioritized based on the number of symptoms that are out of the normal range. The efficiency of the proposed system was evaluated in terms of network usage time, latency, and response time.

The system presented in this study led to the improvement of network usage time by 23.77%, reduction of latency by 23.71%, and enhancement of response time by 32.95%.

Using the priority queue to prioritize requests at the fog layer reduces the response time to emergency requests.

When clinical decision support systems are developed, implementing solutions that enable these systems to be -used on a large scale can reduce the production costs associated with the creation, maintenance and by sharing these systems, producing multiple clinical decision support systems will be prevented. In recent years, one of the approaches used for this purpose in combination with clinical decision support systems is the service-oriented architecture approach. The purpose of this study was to investigate the role and importance of service-oriented architecture in delivering scalable architectures of clinical decision support systems focusing on different approaches to this architecture.

This article is a simple review article. Bibliographic databases of IEEE Explore, Science Direct, Springer, Web of Science, and Scopus were reviewed. The keywords "Service Oriented Architecture" and "clinical decision support systems" were used as keywords along with related terms for searching these databases.

The clinical decision support systems based on service-oriented architecture brings benefits such as Facilitate knowledge maintenance, reducing costs and improving agility. Point-to-point communication, enterprise service bus, service registry, clinical and engine guiding engine, and service choreography and orchestration are general architectural designs that are evident in the use of web-based clinical decision support systems based on a service-oriented architecture approach.

Service-oriented architecture is a potential solution for delivering scalable platforms for clinical decision systems.

 Breast cancer is the most common type of cancer and the main cause of death from cancer in women worldwide. Technologies such as data mining, have enabled experts in this area to improve decision making in the early diagnosis of the disease. Therefore, the purpose of this research is to develop an automatic diagnostic model for breast cancer by employing data mining methods and selecting the model with the highest accuracy of diagnosis.

 In this study, 654 available patient records of Motahari breast cancer Clinic in Shiraz" were used as the sample. The number of records was reduced to 621 after the pre-processing operation. These samples had 22 features that ultimately used ten were used as effective features in the design of the model. Three types of Decision tree, Naive Bayes and Artificial neural network were used for diagnosis of breast cancer and 10-fold cross-validation method for constructing and evaluating the model on the collected data set.

 The results of the three techniques mentioned all three models showed promising results in detecting breast cancer. Finally, the artificial neural network accounted for the highest accuracy of 94/49%(sensitivity 96/19%, specificity 86/36%) in the diagnosis of breast cancer.

  Based on the results of the decision tree, the risk factors such as age, weight, Age of menstruation, menopause, OCP of records duration, and the age of the first pregnancy were among the factors affecting the incidence of breast cancer in women.