مجله انفورماتیک سلامت و زیست پزشکی
سال دهم شماره 2 (پیاپی 36، تابستان 1402)

COVID-19 is a new virus that causes infection in the upper respiratory tract and lungs, and the number of deaths due to the disease has increased daily on the scale of a global epidemic. Chest X-ray images have been useful for monitoring various lung diseases and have recently been used to monitor COVID-19 disease.

In this research, a multi-stage process was used to recognize COVID-19 from X-ray images. In the first stage, pre-processing was done to normalize the data. In the second step, which is the most important step of the proposed method, feature extraction was done. The feature extraction operation was based on deep learning networks. After feature extraction, machine learning algorithms were used to classify images. The algorithms used in this section are support vector machine, nearest neighbor, and decision tree algorithms. The results of these categories are combined in the fourth step based on the majority vote.

The parameters used in this research are among the classification parameters, including precision, accuracy, recall, and F-criterion, which were obtained as 96.5, 92.25, 94, and 93, respectively.

The results of the experiments show the acceptable efficiency of the proposed method because, in addition to reducing the calculations by the separable layer, the combination of categories and their weighting has been used to obtain the final result.

Diabetes is a chronic disease worldwide, with an increasing annual death rate. Many health professionals seek innovative ways to detect and treat it early. Rapid advances in machine learning have improved disease diagnosis. However, because of the small amount of labeled data, the frequency of null and missing values, and the imbalance of databases, creating an optimal predictor for disease diagnosis has become a great challenge. This study aimed to present a pipeline-based classification framework for predicting diabetes on two datasets of Indian diabetic patients with two classes (patient and healthy groups) and Iraqi with three classes (patient, healthy, and prediabetes groups).

An important part of this framework is preprocessing. Different ML models based on the One-Vs-One approach for the three-class mode are implemented in the framework. Because of the imbalance of the data set, besides the accuracy evaluation criterion, the area under the receiver operating characteristic (ROC) curve is also used. To increase the level of these two criteria, the Hyper-parameters of each model are optimized using optimization methods to build a powerful model with less training and testing time through various feature selection methods.

The proposed framework was assessed for diabetes prediction on two datasets of Indian and Iraqi diabetic patients. It was revealed that using AdaBoost for the Indian dataset (ACC=89.98, AUC=94.11) and random forest for the Iraqi dataset (ACC=98.66, AUC= 98.62), good accuracy and performance were obtained.

Regarding ACC parameters, precision, accuracy, recall, and F1-Score, the pipeline-based framework has an optimal performance in predicting diabetes, therefore, it can be used in clinical decision support systems.

Simultaneously with the COVID-19 epidemic, many efforts were made to manage and treat the disease. One of the main activities was the development of health information systems to help monitor this disease, but due to the speed of the disease’s spread, there was not enough time to evaluate the usability of these systems. Therefore, the present research was conducted to evaluate the usability of the Medical Care Monitoring Center (MCMC) system.

In this cross-sectional descriptive study (2022), the usability of the MCMS system was evaluated using a heuristic evaluation method. The system’s usability was investigated based on the Nielsen’s usability principles. All the problems identified by evaluators were collected in a single list and the mean severity of each problem was calculated.

There were 41 usability problems. The lowest mismatch with usability principles was related to “Help and documentation” (n=1) and the highest one was related to "user control and freedom” (n=8) and “Match with real world” (n=7). In addition, most of the identified problems had a relatively high degree of severity and were placed in the category of major problems.

Using the usability evaluation, a significant number of usability problems of the system were identified which, if not resolved, can cause increased errors, dissatisfaction, and decreased quality of information; therefore, it is necessary to solve these problems by the designers and developers of this system.

Alzheimer’s disease is one of the most common neurodegenerative diseases in adults. The progressive nature of Alzheimer’s disease causes widespread damage to the brain, and early diagnosis can manage the disease and slow down its progression effectively.

In this study, a dataset related to the early prediction of Alzheimer’s was used. Spark framework was used for data management and three machine learning algorithms including Naïve Bayes, Decision Tree, and Artificial Neural Networks with the best hyperparameters were implemented and compared. To prevent overfitting and measure the efficiency of the models, a 5-fold cross-validation method was utilized. Furthermore, a method was used for interpreting machine learning black box models.

The decision tree and artificial neural network models obtained 98.61% accuracy and 98.60% F1-Score in the Spark framework including one or three computers. Important features in the decision-making process of the artificial neural network were identified using the interpretability technique. In addition, the computational time required for training the proposed models was calculated through different approaches, and the use of multiple computers was 35.95% faster than a single computer.

With increasing the number of Alzheimer’s disease patients around the world, the need for a decision support system using machine learning algorithms, which can predict the disease early in a huge amount of data, is felt more. Therefore, the machine learning models proposed in this study for early prediction of Alzheimer’s disease as an interpretable auxiliary tool in the decision-making process can help clinicians.

Cardiovascular disease is one of the main causes of death worldwide. One of the important factors is readmission due to the lack of training. Considering the widespread use of mobile phones, this study aimed to design a recommender system for patients with cardiac arrhythmia.

This is an applied-developmental study that was conducted in a quantitative (descriptive) method and in 2 stages. First, the recommended educational parameters and application requirements of the software were determined based on literature review. Then, the obtained contents were provided to 16 cardiologists working in Shahid Rajaei and Hazrat Rasool Akram Hospitals in Tehran. To evaluate the usability, the application was given to 50 patients with cardiac arrhythmia and was checked with the quiz questionnaire version 5.5.

In the recommendations section, experts deemed all items except "Omega-3 consumption" necessary. In the usability evaluation section, the items "Identifying the nearest emergency center, sending the patient’s geographic location to the doctor, finding the nearest medical center, and the possibility of changing color, and calculating BMI" were not confirmed. The usability evaluation of the application with an average score of 7.98±0.62 indicates a good level.

The mobile-based recommender application can cause the patients to play a greater role in their treatment and acquire skills in the field of training after hospital discharge and lead to a reduction in re-hospitalization and cost.

Accurate diagnosis of Alzheimer’s disease in the early stages plays an important role in patient care, and preventive measures should be taken before irreversible brain damage occurs. With increasing age, there are changes in memory, which is normal, but the symptoms of Alzheimer’s disease are more than temporary forgetfulness. Early and intelligent diagnosis of Alzheimer’s disease in different situations can greatly help patients and physicians.

In the proposed method, a convolutional neural network will be used to improve the recognition of people with Alzheimer’s disease from healthy people in emotional states. First, the required pre-processing is done on the electroencephalography signal, and then, it will be applied as an input to the network. Next, the genetic algorithm is used to optimize the weights of the convolutional neural network.

The research shows that the frontal lobe of the brain is related to emotions and the use of F3 and F4 channels reflects more information compared to other channels, so with this information, the process of recognizing Alzheimer’s patients in emotional states is better.

The proposed method was evaluated with other categories in valence and arousal states. It was observed that this method has a better efficiency compared to other methods with an accuracy of 92.3% in valence and 94.3% in arousal in recognizing people with Alzheimer’s disease.

Integrated Health Information Systems (HIS) are necessary to achieve national and international goals in health and development, which are facing cooperation problems due to diversity and heterogeneity. Interoperability as a key characteristic of data sharing and the main prerequisite of integration enables healthcare providers to make timely decisions for diagnosis, treatment, action, and patient care. Therefore, this research aimed to provide a category of interoperability concepts in electronic health (E-Health).

This research is a narrative review to categorize the interoperability concepts in E-Health. For this purpose, Scopus, Google Scholar, PubMed, Science Direct, and IEEE databases were searched using the keywords "Interoperability framework" and "Integration" with the combination of AND along with "E-Health". Therefore, all the articles referring to the concepts of interoperability were selected.

The result of the search in the aforementioned databases was 304 articles. By removing duplicate, out-of-reach, and unrelated articles, only 40 articles were examined, and topics related to the concepts of interoperability were classified based on six axes (dimensions, levels, obstacles, integration, architecture, and measurement). Finally, its applications and challenges were described in a narrative review.

Due to the nature of the health system, integrity and intelligence are very important in this area. Therefore, to facilitate the exchange of information and the use of health information systems from each other’s services, paying attention to the presented classification has an undeniable effect, and also, an important role in the integrity and intelligence of the environment, and increases the efficiency and effectiveness in the quality of providing health care services.