Non-invasive fractional flow reserve estimation using deep learning on intermediate left anterior descending coronary artery lesion angiography images.

This study aimed to design an end-to-end deep learning model for estimating the value of fractional flow reserve (FFR) using angiography images to classify left anterior descending (LAD) branch angiography images with average stenosis between 50 and 70% into two categories: FFR > 80 and FFR ≤ 80. In this study 3625 images were extracted from 41 patients' angiography films. Nine pre-trained convolutional neural networks (CNN), including DenseNet121, InceptionResNetV2, VGG16, VGG19, ResNet50V2, Xception, MobileNetV3Large, DenseNet201, and DenseNet169, were used to extract the features of images. DenseNet169 indicated higher performance compared to other networks. AUC, Accuracy, Sensitivity, Specificity, Precision, and F1-score of the proposed DenseNet169 network were 0.81, 0.81, 0.86, 0.75, 0.82, and 0.84, respectively. The deep learning-based method proposed in this study can non-invasively and consistently estimate FFR from angiographic images, offering significant clinical potential for diagnosing and treating coronary artery disease by combining anatomical and physiological parameters.

Integrated personal health record (PHR) security: requirements and mechanisms.

BACKGROUND: Personal Health Records (PHRs) are designed to fulfill the goals of electronic health (eHealth) and empower the individual in the process of self-care. Integrated PHR can improve the quality of care, strengthen the patient-healthcare provider relationship, and reduce healthcare costs. Still, the process of PHR acceptance and use has been slow and mainly hindered by people's concerns about the security of their personal health information. Thus, the present study aimed to identify the Integrated PHR security requirements and mechanisms. METHODS: In this applied study, PHR security requirements were identified with a literature review of (library sources, research articles, scientific documents, and reliable websites). The identified requirements were classified, and a questionnaire was developed accordingly. Thirty experts completed the questionnaire in a two-round Delphi technique, and the data were analyzed by descriptive statistics. RESULTS: The PHR security requirements were identified and classified into seven dimensions confidentiality, availability, integrity, authentication, authorization, non-repudiation, and right of access, each dimension having certain mechanisms. On average, the experts reached an agreement about the mechanisms of confidentiality (94.67%), availability (96.67%), integrity (93.33%), authentication (100%), authorization (97.78%), non-repudiation (100%), and right of access (90%). CONCLUSION: Integrated PHR security is a requirement for its acceptance and use. To design a useful and reliable integrated PHR, system designers, health policymakers, and healthcare organizations must identify and apply security requirements to guarantee the privacy and confidentiality of data.

Performance of machine learning techniques on prediction of esophageal varices grades among patients with cirrhosis.

OBJECTIVES: All patients with cirrhosis should be periodically examined for esophageal varices (EV), however, a large percentage of patients undergoing screening, do not have EV or have only mild EV and do not have high-risk characteristics. Therefore, developing a non-invasive method to predict the occurrence of EV in patients with liver cirrhosis as a non-invasive method with high accuracy seems useful. In the present research, we compared the performance of several machine learning (ML) methods to predict EV on laboratory and clinical data to choose the best model. METHODS: Four-hundred-and-ninety data from the Liver and Gastroenterology Research Center of Shahid Beheshti University of Medical Sciences in the period 2014-2021, were analyzed applying models including random forest (RF), artificial neural network (ANN), support vector machine (SVM), and logistic regression. RESULTS: RF and SVM had the best results in general for all grades of EV. RF showed remarkably better results and the highest area under the curve (AUC). After that, SVM and ANN had the AUC of 98%, for grade 3, the SVM algorithm had the highest AUC after RF (89%). CONCLUSIONS: The findings may help to better predict EV with high precision and accuracy and also can help reduce the burden of frequent visits to endoscopic centers. It can also help practitioners to manage cirrhosis by predicting EV with lower costs.

Identifying predictors of varices grading in patients with cirrhosis using ensemble learning.

OBJECTIVES: The present study was conducted to improve the performance of predictive methods by introducing the most important factors which have the highest effects on the prediction of esophageal varices (EV) grades among patients with cirrhosis. METHODS: In the present study, the ensemble learning methods, including Catboost and XGB classifier, were used to choose the most potent predictors of EV grades solely based on routine laboratory and clinical data, a dataset of 490 patients with cirrhosis gathered. To increase the validity of the results, a five-fold cross-validation method was applied. The model was conducted using python language, Anaconda open-source platform. TRIPOD checklist for prediction model development was completed. RESULTS: The Catboost model predicted all the targets correctly with 100% precision. However, the XGB classifier had the best performance for predicting grades 0 and 1, and totally the accuracy was 91.02%. The most significant variables, according to the best performing model, which was CatBoost, were child score, white blood cell (WBC), vitalism K (K), and international normalized ratio (INR). CONCLUSIONS: Using machine learning models, especially ensemble learning models, can remarkably increase the prediction performance. The models allow practitioners to predict EV risk at any clinical visit and decrease unneeded esophagogastroduodenoscopy (EGD) and consequently reduce morbidity, mortality, and cost of the long-term follow-ups for patients with cirrhosis.

Efficient Framework for Detection of COVID-19 Omicron and Delta Variants Based on Two Intelligent Phases of CNN Models.

Introduction: While the COVID-19 pandemic was waning in most parts of the world, a new wave of COVID-19 Omicron and Delta variants in Central Asia and the Middle East caused a devastating crisis and collapse of health-care systems. As the diagnostic methods for this COVID-19 variant became more complex, health-care centers faced a dramatic increase in patients. Thus, the need for less expensive and faster diagnostic methods led researchers and specialists to work on improving diagnostic testing. Method: Inspired by the COVID-19 diagnosis methods, the latest and most efficient deep learning algorithms in the field of extracting X-ray and CT scan image features were used to identify COVID-19 in the early stages of the disease. Results: We presented a general framework consisting of two models which are developed by convolutional neural network (CNN) using the concept of transfer learning and parameter optimization. The proposed phase of the framework was evaluated on the test dataset and yielded remarkable results and achieved a detection sensitivity, specificity, and accuracy of 0.99, 0.986, and 0.988, for the first phase and 0.997, 0.9976, and 0.997 for the second phase, respectively. In all cases, the whole framework was able to successfully classify COVID-19 and non-COVID-19 cases from CT scans and X-ray images. Conclusion: Since the proposed framework was based on two deep learning models that used two radiology modalities, it was able to significantly assist radiologists in detecting COVID-19 in the early stages. The use of models with this feature can be considered as a powerful and reliable tool, compared to the previous models used in the past pandemics.

Application of ICT in effective crisis management: A systematic review.

INTRODUCTION: Effective crisis management can reduce the costs and consequences of a crisis and has a significant impact on saving human lives in critical situations. Proper use of information and communication technologies (ICTs) can improve all crisis management phases and crisis communication cycles according to the needs of stakeholders. The purpose of this review article is to identify which ICTs have been used in effective crisis management and what managerial tasks they support. METHOD: A systematic review was conducted based on PRISMA protocol. The investigated articles that have been published in English were all indexed in PubMed, Science Direct, IEEE, Web of Science, and Google Scholar databases from 2005 to 2019. The keywords searched were "Crisis Management," "Emergency Management," "Information and Communication Technology," and their synonyms. RESULTS: A total of 1,703 articles were retrieved, and 81 articles that met the inclusion criteria were retained. In terms of content, there were 54 case studies/review articles, 38 proposals, and seven prototypes among which 18 case studies and proposals were the same. According to surveys, 18 ICT tools and technologies have been used in effective crisis management with the purpose of supporting managerial tasks such as situation assessment, decision-making, coordination/command and control, communication with the public, and supply of basic services in order to enable crisis management and logistics. CONCLUSION: This study showed that proper use of ICT can help crisis managers optimize their performance that will consequently result in effective crisis management and the reduction of casualties. In the crisis management cycle, several tools and technologies have been used for various purposes, however; some crisis managers' tasks were still not taken into consideration sufficiently, and thus, some recommendations for further research in this field were provided.

Minimum Data Set for a Poisoning Registry: A Systematic Review.

Poisoning, as a well-known medical condition, puts everyone at risk. As a data management tool, a registry plays an important role in monitoring the poisoned patients. Having a poisoning minimum data set is a major requirement for creating a poisoning registry. Therefore, the present systematic review was conducted in 2019 to identify the minimum data set for a poisoning registry. Searches were performed in four scientific databases, i.e., PubMed, Scopus, Web of Science, and Embase. The keywords used in the searches included minimum data set, "poison", and "registry". Two researchers independently evaluated the titles, abstracts, and texts of the papers. The data were collected from the related papers. Ultimately, the minimum data set was identified for the poisoning registry. Data elements extracted from the sources were classified into two general categories: administrative data and clinical data. Ninety-eight data elements in the administrative data category were subdivided into three sections: general data, admission data, and discharge data. One-hundred and thirty-one data elements in the clinical data category were subdivided into five sections: clinical observation data, clinical assessment data, past medical history data, diagnosis data, and treatment plan data. The minimum data set is a prerequisite for creating and using a poisoning registry and data system. It is suggested to evaluate and use the poisoning minimum data set in accordance with the national laws, needs, and standards based on the opinion of the local experts.

Functions and Outcomes of Personal Health Records for Patients with Chronic Diseases: A Systematic Review.

Introduction: The personal health record (PHR) makes it possible for patients to access, manage, track, and share their health information. By engaging patients in chronic disease care, they will be active members in decision-making and healthcare management. Objectives: This study aimed to identify the functions and outcomes of PHR for patients with four major groups of chronic diseases (cardiovascular diseases, cancers, diabetes, and chronic respiratory diseases). Method: A systematic review was conducted on studies published in PubMed, Scopus, Web of Science, and Embase. Searching and screening were performed using the keyword of "Personal Health Record" without time limitation, and ended in August 2018. Results: In total, 3742 studies were retrieved, 35 of which met the inclusion criteria. Out of these 35, 18 studies were conducted in the United States, 24 studies were related to patients with diabetes, and 32 studies focused on tethered PHRs. Moreover, in 25 studies, the function of viewing and reading medical records and personal health information was provided for three groups of chronic patients. Results showed that the use of PHRs helps the management and control of chronic diseases (10 studies). Conclusion: It is recommended that integrated PHRs with comprehensive functions and features were designed in order to support patient independence and empowerment in self-management, decrease the number of referrals to health centers, and reduce the costs imposed on families and society.

Telemedicine Services in Chronic Obstructive Pulmonary Disease: A Systematic Review of Patients' Adherence.

Background: The current systematic review aimed to determine the effect of telemedicine services on adherence in patients with chronic obstructive pulmonary disease (COPD) and to describe the type of adherence and applied devices and modules. Materials and Methods: We reviewed PubMed, Scopus, Web of Science, and Embase databases to identify relevant studies from the time of inception of these databases to March 10, 2019, using three groups of keywords. The first group comprised words describing COPD, the second group included words describing types of telemedicine interventions, and the third group contained words describing adherence. The reference list of identified articles was also hand-searched to retrieve possibly relevant articles. Results: In total 21 articles were included, in which 13 reported a positive effect for telemedicine on patients' adherence. Adherence to treatment was classified under six categories. The highest frequency belongs to the adherence to performing exercises and participation in training sessions, using the system, using devices, measuring (like blood pressure, oxygen saturation, heart rate, weight, temperature, sputum volume) and reporting symptoms and the results of measurements, completing tasks, and medication. Conclusion: This study demonstrated the effectiveness of telemedicine services on adherence to treatment plans in patients with COPD. The following factors contribute to the effectiveness of telemedicine services: patient support by healthcare professionals and easy access to them, uninterrupted execution of telemedicine programs, follow-up and supervision of providers, creating and maintaining motivation in patients, and provision of different self-management modules.

Development of a Knowledge-based Clinical Decision Support System for Multiple Sclerosis Diagnosis.

The diagnosis of multiple sclerosis (MS) is difficult considering its complexity, variety in signs and symptoms, and its similarity to the signs and symptoms of other neurological diseases. The purpose of this study is to design and develop a clinical decision support system (CDSS) to help physicians diagnose MS with a relapsing-remitting phenotype. The CDSS software was developed in four stages: requirement analysis, system design, system development, and system evaluation. The Rational Rose and SQL Server were used to design the object-oriented conceptual model and develop the database. The C sharp programming language and the Visual Studio programming environment were used to develop the software. To evaluate the efficiency and applicability of the software, the data of 130 medical records of patients aged 20 to 40 between 2017 and 2019 were used along with the Nilsson standard questionnaire. SPSS Statistics was also used to analyze the data. For MS diagnosis, CDSS had a sensitivity, specificity and accuracy of 1, 0.97 and 0.99, respectively, and the area under the ROC curve was 0.98. The agreement rate of kappa coefficient (κ) between software diagnosis and physician's diagnosis was 0.98. The average score of software users was 98.33%, 96.65%, and 96.9% regarding the ease of learning, memorability, and satisfaction, respectively. Therefore, the applicability of the CDSS for MS diagnosis was confirmed by the neurologists. The evaluation findings show that CDSS can help physicians in the accurate and timely diagnosis of MS by using the rule-based method.

Notifiable Diseases Surveillance System with a Data Architecture Approach: a Systematic Review.

INTRODUCTION: The wide range of notifiable diseases and the need for immediate reporting complicate the management of these diseases. Developing a surveillance system using precise architectural principles could ease the management of these diseases. AIM: The present study reviews the data architecture of notifiable diseases surveillance systems to provide a basis for developing such systems. METHODS: A systematic review was conducted on the literature focused on data architecture of notifiable diseases surveillance systems. The searches for relevant English language articles were conducted based on the paper keywords, as well as the words Mesh and EMTREE. RESULTS: The findings were categorized into five groups, including organizations involved in the generation and monitoring of notifiable diseases' data. The databases in the present study were relational and used a centralized architecture for information sharing. The minimum dataset was determined in two information categories. The data standards were categorized into three main groups. The key approaches for data quality control included checking the completeness, timeliness, accuracy, consistency, adequacy, and validity of the data. CONCLUSION: Developing a notifiable diseases surveillance based on data architecture principles could lay the foundation for better management of such diseases through eliminating the obstacles experienced during data generation, data processing, and data sharing.

National information system for rare diseases with an approach to data architecture: A systematic review.

The study aims to systematically review literature on the rare diseases information system to identify architecture of this system from a data perspective. The search for relevant English language articles, based on keywords in title, abstract, Mesh and Emtree terms, was done in Pubmed and Embase (from 1980 to June 2017), Scopus, Science Direct and Cochran (from 1980 to July 2017). Articles were selected if they addressed data architecture of information systems with a focus on rare disease, and if at least one of their objectives dealt with design, implementation, and development of rare diseases information systems. Thirty-five studies met the inclusion criteria. The findings were categorized into six groups. This first group addressed organizations acting as data generators, data users, and data governors. The second group was related to data sources and databases. Datasets and data elements formed the third group of findings, including common datasets, specific datasets, and complementary datasets. The fourth group of findings was in relation to data standards. Data sharing and interactions among relevant bodies included the fifth group of the findings. The last group of findings was pertinent to procedures and criteria used for checking the quality of data, as cross review checking was a main procedure assessing the accuracy, consistency, and completeness of data. Design and development of an integrated information system for rare diseases considering data architecture principles in practice could help eliminating issues with management of rare diseases through facilitating sharing information and experiences.

Intelligent Computer Systems for Multiple Sclerosis Diagnosis: a Systematic Review of Reasoning Techniques and Methods.

OBJECTIVE: Intelligent computer systems are used in diagnosing Multiple Sclerosis and help physicians in the accurate and timely diagnosis of the disease. This study focuses on a review of different reasoning techniques and methods used in intelligent systems to diagnose MS and analyze the application and efficiency of different reasoning methods in order to find the most efficient and applicable methods and techniques for MS diagnosis. METHODS: A complete research was carried out on articles in various electronic databases based on Mesh vocabulary. 85 articles out of 614 articles published in English between 2000 to 2018 were analyzed, 30 of which have been selected based on inclusion criteria such as system scope and domain, full description of reasoning method and system evaluation. RESULTS: Results indicate that different reasoning methods are used unintelligent systems of MS diagnosis. In 27% of the studies, the rule-based method was used, in 20% the fuzzy logic method, in 18%the artificial neural network method, and in 35% other reasoning methods were used. The average sensitivity, specificity and accuracy of reasoning methods were0.91, 0.77, and 0.86, respectively. CONCLUSIONS: Rule-based, fuzzy-logic and artificial neural network methods have had more applications in intelligent systems for the diagnosis of MS, respectively. The highest rate of sensitivity and accuracy indexes is associated to the neural network reasoning method at 0.97 and 0.99, respectively .In the fuzzy logic method, the Kappa rate has been reported as one, which shows full conformity between software diagnosis and the physician's decision .In some articles, in order to remove the limitations of the methods and enhance their efficiency, combinations of different methods are used.

E-Health: a global approach with extensive semantic variation.

In recent years, there has been considerable attention towards the development of information and communication technology (ICT) in health care delivery known as 'E-Health'. The term "E-Health" is almost a new concept and the E-Health projects mainly aim to improve service delivery to people, though different countries might have different approaches in using E-Health. The focus of this study is to review factors influencing the development of E-Health projects, as these factors could lead to an extensive semantic variation. This study reviews the E-Health status in different countries based on existing reports and documents about E-health projects in developed and developing countries and also based on the reports and documents provided by WHO, International Telecommunication Union (ITU); and World Bank. The review of the documents showed that the E-Health status in different countries is depended upon three key factors including the potential of ICT, economic capacity and the level of health status. The review of the documents indicated that there might be different meanings for the concept of E-Health in different countries, and the semantic variation in E-Health concept is related to the level of E-Health developments and implementations. Therefore, developing a clear definition of E-Health is needed.

A new model for the organizational structure of medical record departments in hospitals in Iran.

The organizational structure of medical record departments in Iran is not appropriate for the efficient management of healthcare information. In addition, there is no strong information management division to provide comprehensive information management services in hospitals in Iran. Therefore, a suggested model was designed based on four main axes: 1) specifications of a Health Information Management Division, 2) specifications of a Healthcare Information Management Department, 3) the functions of the Healthcare Information Management Department, and 4) the units of the Healthcare Information Management Department. The validity of the model was determined through use of the Delphi technique. The results of the validation process show that the majority of experts agree with the model and consider it to be appropriate and applicable for hospitals in Iran. The model is therefore recommended for hospitals in Iran.