Search published articles


Showing 3 results for Gholamzadeh
Decision Modeling for Diagnosis and Screening of Ovarian Epithelial Cancer
Reza Safdari, Leila Shahmoradi, Marjan Daneshvar, Elmira Pourtorkan, Mersa Gholamzadeh,
Volume 12, Issue 1 (5-2018)
Abstract
Background and Aim: The Ovarian epithelial cancer is one of the most deadly types of cancers in women.Thus, the purpose of this study was to investigate the most effective factors in predicting and detecting Ovarian cancer in the form of a decision tree to facilitate the Ovarian cancer diagnosis.
Materials and Methods: The present study was a descriptive-developmental study. The main research tool applied in this study was a checklist which was designed based on the medical records, published studies, scientific references, and expert consultation.To determine the content validity of the checklist, the CVR method was applied. Next, survey research was done with aid of Likert-based checklist based on expert opinions in gynecology. Finally, to develop the decision tree, the results of the expert survey were analyzed and the final model was implemented based on the survey results.
Results: The data elements of final decision tree were derived from the result of expert surveys, guidelines, clinical pathways and strategies in context of diagnosis and screening of Ovarian cancer. The leaf nodes in the tree include different types of tumor markers, following up, therapeutic measures, and referrals. The accuracy of the decision tree was approved by the experts. The most important tumor markers that obtained from the decision model in this study were CA19-9, ROMA (CA125 + HE4) and CEA.
Conclusion: Clinical decision models can provide specific diagnosis and therapeutic suggestions by creating patient information integration framework. The model developed in this study can improve the diagnosis of epithelial Ovarian cancer considerably by facilitating decision making.

An Overview of the Features and Content of Dermatology Mobile Applications
Nahid Einollahi, Reza Safdari, Marsa Gholamzadeh, Elham Haghshenas, Horieh Masourian,
Volume 14, Issue 4 (Oct & Nov 2020)
Abstract
Background and Aim: Mobile-based programs have been developed as tools to help both patients and physicians in various fields especially in dermatology. Therefore, the main objective of this study was to review the features and contents of dermatology applications.
Materials and Methods: The methodology was comparative and descriptive. Applications in the field of dermatology were evaluated and compared through this research. Inclusion criteria included applications that have been downloaded more than 100 times in Google Play and App Store and applications designed in diagnosis in various fields of dermatology such as treatment, management, remote consulting, and self-care areas. Exclusion criteria included those developed before 2010 and those related to the non-dermatology areas. Besides, different features were considered for comparison based on literature review and expert consultation. Next, the recognized applications were reviewed and compared based on determined categories.
Results: Based on criteria, a total of 33 applications were identified through searching. Of these, 33.3% of Apps were in the field of education, and 24.2% were in self-care. Regarding disease, applications were categorized into nine different domains. Of these, 61% of applications were covering different types of skin diseases. Also, in examining the frequency of the features of the evaluated programs, providing recommendations and suggestions with 57.57% and educational contents and the possibility of uploading images with 51.51%, respectively, had the highest frequency among the features of the programs.
Conclusion: Analysis showed that education and self-care domains have a high rank among others. It indicates that developing such applications could facilitate patient education and self-management by himself or caregivers. However, this area needs more attention and the using health information technology capabilities to make applications smarter in this area.

Classification of Chest Radiology Images in Order to Identify Patients with COVID-19 Using Deep Learning Techniques
Marsa Gholamzadeh, Seyed Mohammad Ayyoubzadeh, Hoda Zahedi, Sharareh Rostam Niakan Kalhori,
Volume 15, Issue 3 (Aug & Sep 2021)
Abstract
Background and Aim: Due to the important role of radiological images for identifying patients with COVID-19, creating a model based on deep learning methods was the main objective of this study.
Materials and Methods: 15,153 available chest images of normal, COVID-19, and pneumonia individuals which were in the Kaggle data repository was used as dataset of this research. Data preprocessing including normalizing images, integrating images and labeling into three categories, train, test and validation was performed. By Python language in the fastAI library based on convolution technique (CNN) and four architectures (ResNet, VGG MobileNet, AlexNet), nine models through transitional learning method were trained to recognize patients from healthy persons. Finally, the performance of these models was evaluated with indicators such as accuracy, sensitivity and specificity, and F-Measure.
Results: Of the nine generated models, the ResNet101 model has the highest ability to distinguish COVID-19 cases from other cases with 95.29% sensitivity. Other applied models showed more than 96% accuracy in correctly diagnosis of various cases in test phase. Finally, the ResNet101 model was able to demonstrate 98.4% accuracy in distinguishing between healthy and infected cases.
Conclusion: The obtained accuracy showed the accurate performance of developed model in detecting COVID-19 cases. Therefore, by implementing an application based on the developed model, physicians can be helped in accurate and early diagnosis of cases. an application based on the developed model, physicians can be helped in accurate and early diagnosis of infected cases.

Page 1 from 1     

© 2024 , Tehran University of Medical Sciences, CC BY-NC 4.0

Designed & Developed by: Yektaweb