Search published articles


Showing 6 results for Mousavi
Comparison of Three Decision-Making Models in Differentiating Five Types of Heart Disease: A Case Study in Ghaem Sub-Specialty Hospital
Seyedeh Raahil Mousavi, Mohammad Mehdi Sepehri,
Volume 5, Issue 4 (Winter 2019)
Abstract
Introduction: cardiovascular diseases are becoming the main cause of mortality and morbidity in most countries. This research goal was to predict the types of heart diseases for more accurate diagnosis by data mining and neural network technics.
Method: This research was an applied-survey study and after data preprocessing, three approaches of neural network, decision making tree and Bayes simple algorithm were used to predict and recognize in Rapidminer software and neural artificial network model was used for prediction in Matlab software.
Results: Genetic algorithm was used for selection of effective variables and neural artificial network models, decision making tree and Bayes simple algorithm were used to predict types of heart diseases in data mining. AHP model was used to determine a model with the best performance for predicting types of heart diseases.
Conclusion: Neural network had much better performance than other data mining models used to diagnose types of heart diseases in this research. Also, in detecting disease by artificial neural network, the model with accuracy of more than 80 percent was verified as good and acceptable

A Decision Support System for Diagnosis of Diabetes and Hepatitis, based on the Combination of Particle Swarm Optimization and Firefly Algorithm
Farhad Soleimanian Gharehchopogh, Seyyed Keivan Mousavi,
Volume 6, Issue 1 (Spring 2019)
Abstract
Introduction: Clinical Decision Support Systems (CDSS) are designed in the form of computer programs that help medical professionals make decisions about disease diagnosis. The main aim of these systems is to assist physicians in diagnosing diseases, in other words, a physician can interact with the system and use them to analyze patient data, diagnose diseases, and other medical activities.
Method: This is a descriptive-analytic study. The datasets include 768 records of diabetes with 8 features and 155 records of hepatitis with 19 features, which were provided by the Global Website of UCI. In this study, the Particle Swarm Optimization (PSO) algorithm was used for Feature Selection (FS) and the Firefly Algorithm (FA) was used to classify diabetes and hepatitis into two healthy and unhealthy classes. 80% of the data was used for training and the remaining (20%) was used for testing.
Results: The experiments showed that the accuracy of the PSO and FA for the diabetes dataset was 84.41% and 82.08%, respectively. Also, the accuracy of the PSO and FA for the hepatitis dataset was 81.84% and 80.34%, respectively. The accuracy of the proposed model for the diabetes and hepatitis datasets was 95.38% and 94.09%, respectively.
Conclusion: According to the results, the proposed model had a lower error rate in diagnosis compared to the PSO and FA. The results of this study can help doctors in timely diagnosis of diabetes and hepatitis

Evaluation of a Virtual Reality-Based Wearable Device for Patients with Ankle Movement Disorders
Majid Eslami, Iman Mousavian, Farideh Eskandari Farsani, Reyhane Dadgostar , Mohamad Asadollahi , Negar Rahimi , Atefeh Hatami , Samaneh Mohammadkhani ,
Volume 9, Issue 1 (6-2022)
Abstract
Introduction: Rehabilitation is one of the priorities that should be performed on patients with stroke injuries or accidents leading to disability. This study aimed to evaluate the equipment and designed virtual reality environment to improve the treatment of patients with mobility problems in the lower torso (ankle).
Method: The research consisted of three basic parts. In the section of mechanics, a movement mechanism was developed after design, and with the help of electronic equipment and Arduino (1.18.5), movements were measured. And finally, by designing a virtual reality environment in Unity software, communication with hardware, processors, and sensors was provided.
Results: Paying attention to graphic attractiveness and encouraging users to reuse the virtual reality system is one of the desirable results of this project, which can be effective in motivating users. In addition, considering the existence of distance and time of movement in a virtual reality environment, which depends on the user's movements in the real environment, it is possible to intelligently assess the patient's progress based on the number of sessions and distance traveled.
Conclusion: Virtual reality-based rehabilitation methods can have a good effect on the treatment process due to the graphic attractiveness in this environment, and along with other rehabilitation methods, can be effective in faster recovery of people who need rehabilitation services. This method can help patients return to normal living conditions and reduce the time of this process.

A Convolutional Neural Network Model for Detection of COVID-19 Disease and Pneumonia
Seyed Mohammad Mousavi , Soodeh Hosseini ,
Volume 10, Issue 1 (6-2023)
Abstract
Introduction: COVID-19 has had a devastating impact on public health around the world. Since early diagnosis and timely treatment have an impact on reducing mortality due to infection with COVID-19 and existing diagnostic methods such as RT-PCR test are prone to error, the alternative solution is to use artificial intelligence and image processing techniques. The overall goal is to introduce an intelligent model based on deep learning and convolutional neural network to identify cases of COVID-19 and pneumonia for the purpose of subsequent treatment measures with the help of lung medical images.
Method: The proposed model includes two datasets of radiography and CT-scan. These datasets are pre -processed and the data enhancement process is applied to the images. In the next step, three architectures EfficientNetB4, InceptionV3, and InceptionResNetV2 are used using transfer learning method.
Results: The best result obtained for CT-scan images belongs to the InceptionResNetV2 architecture with an accuracy of 99.366% and for radiology images related to the InceptionV3 architecture with an accuracy of 96.943%. In addition, the results indicate that CT-scan images have more features than radiographic images, and disease diagnosis is performed more accurately on this type of data.
Conclusion: The proposed model based on a convolutional neural network has higher accuracy than other similar models. Also, this method by generating instant results can help in the initial evaluation of patients in medical centers, especially during the peak of epidemics, when medical centers face various challenges, such as lacking specialists and medical staffs.


Intelligent Diagnosis of Larynx Cancer Using Machine Learning Methods
Fereshteh Arad, Seyyed Mohammad Mousavi, Soodeh Hosseini, Maryam Amizade, Ayyub Sheikhi,
Volume 11, Issue 2 (9-2024)
Abstract
Introduction: Larynx cancer can be benign or malignant based on various factors. This research aimed to provide a machine learning-based model to improve the diagnosis of individuals with larynx cancer.
Method: In the first step, the voices of the people who visited the medical centers (including the sounds (A), (E), and (O)) were recorded and considered as a data set. In the second step, the data were classified into three classes (benign cancer, malignant cancer, and healthy) by a specialist. In the third step, the data cleaning was done. In the fourth step, the features related to sound were extracted from the data. In the fifth step, five machine learning models including SVM, Decision Tree, Naïve Bayes, MLP, and Random Forest were implemented on the data set. Finally, the performance of the models was evaluated using evaluation criteria such as accuracy, F-score, and other evaluation criteria.
Results: The results of the implementation showed that the SVM model had a higher accuracy than other models for the sound (A) and sound (O) with an accuracy of 0.818, and the sound (E) with an accuracy of 0.818 in the model MLP had the highest accuracy.
Conclusion: The present study evaluated machine learning models for the diagnosis of laryngeal cancer based on audio data. The results showed that the use of the SVM model for the diagnosis of laryngeal cancer can help diagnose this disease more accurately and provide reliable results.
 

Investigating the microRNAs Involved in the Acute Phase of Hepatocellular Carcinoma Caused by Hepatitis C Virus
Seyedeh Fatemeh Mousavi Kardar, Mahnaz Mohammadi, Behnaz Esfandiari,
Volume 11, Issue 3 (12-2024)
Abstract
Introduction: Hepatocellular carcinoma is one of the most common cancers in the world. In this study, we examined and nominated the genes present in the pathways of hepatocellular carcinoma associated with HCV using bioinformatics analysis.
Method: The appropriate dataset for analysis was selected from the GEO database. This dataset included gene expression profiles in hepatocellular carcinoma associated with HCV. Gene clusters with high and low expression levels were categorized. Rich databases such as Enrichr, STRING, and GEPIA were also used. Finally, the candidate genes were isolated.
Results: A total of 512 genes with high expression and 500 genes with low expression were involved in the progression pathways of hepatocellular carcinoma. The pathways associated with the cell cycle, cell adhesion, AMPK, PPAR, and MAPK were clearly observed. After evaluating the relationship between protein networks, ADH4, FBP1, and ACS1 showed increased expression, while CDK4, E2F1, and MAPK3 genes displayed decreased expression. All these genes were noted in the survival curve; over a period of about 15 months, the survival rate of patients was less than 20%. miR-21-5p, hsa-miR-24-3p, and hsa-miR-25-3p were significantly more effective in regulating these genes.
Conclusion: Bioinformatics analyses of key and important genes were introduced through the examination of gene expression profile data. ADH4, FBP1, and ACS1 genes showed increased expression, whereas the CDK4, E2F1, and MAPK3 genes displayed decreased expression, which may play an important role in targeting the genes involved in hepatocellular carcinoma associated with HCV.

Page 1 from 1     

© 2025 CC BY-NC 4.0 | Journal of Health and Biomedical Informatics

Designed & Developed by : Yektaweb