Mina Shayestefar, Mohadese Saffari, F. Kermani, S. Pahlevanynejad, M. Kahouei, M. Mirmohammadkhani, Arash Seidabadi, S. Esmaeili, Mohammad Amin Moradi, Abdolmannan Habibli, A. Firuzi
Introduction: Emergency Medical Services (EMS) is one of the vital links in the care chain, and its services need to be improved. These services can be available through mobile-based automation system, in which low usability level of these systems lead to decrease the acceptance, satisfaction, and confidence of users especially the emergency care team. The purpose of this study was the usability evaluation of a national mobile- based automation system among the pre-hospital emergency care team.Material and Methods: This cross-sectional study was conducted on pre-hospital emergency care team members in Semnan and Shahroud Universities of Medical Sciences in 2022. The usability evaluation of the mobile- based EMS automation system was done using the Software Usability Measurement Inventory (SUMI) questionnaire. Multiple logistic regression models were used to analyze data.Results: One hundred eighty-eight EMS team members from the 31 EMS centers in Semnan province participated in present study. The mean total usability score was 61.93±15.37, the highest mean score was related to the efficiency feature (67.19±19.85) and the lowest mean score was related to the learnability feature (48.21±29.29). There was a reverse and significant relationship between being a manager and the agreement with the usability (p=0.04, OR= -3.383, CI 95%=0.389-29549).Conclusion: This study showed that although an automation system may be widely used in a country, its usability could be at a low level. In order to improve the different function of these systems, it is suggested to participate various clinical experts include prehospital emergency care team in all stages of designing and developing these systems.
简介:紧急医疗服务(EMS)是医疗链条中至关重要的环节之一，其服务水平有待提高。这些服务可以通过基于移动的自动化系统提供，但这些系统的可用性水平较低，导致用户特别是急救团队的接受度、满意度和信心下降。摘要本研究的目的是评估一套全国性的移动自动化系统在院前急救团队中的可用性。材料与方法:本横断面研究于2022年对Semnan和shahoud医学科学大学的院前急救团队成员进行。采用软件可用性测量量表(SUMI)对移动EMS自动化系统进行了可用性评估。采用多元逻辑回归模型对数据进行分析。结果:来自Semnan省31个EMS中心的188名EMS团队成员参与了本研究。平均总可用性得分为61.93±15.37，最高得分与效率特征相关(67.19±19.85)，最低得分与易学性特征相关(48.21±29.29)。作为管理者与对可用性的认同之间存在显著的反向关系(p=0.04, OR= -3.383, CI 95%=0.389-29549)。结论:本研究表明，虽然自动化系统可能在一个国家广泛使用，但其可用性可能处于较低水平。为了改善这些系统的不同功能，建议在设计和开发这些系统的各个阶段都有包括院前急救团队在内的各种临床专家的参与。
{"title":"Usability Evaluation of a National Mobile-Based Automation System for Pre-Hospital Emergency Care (ASAYAR)","authors":"Mina Shayestefar, Mohadese Saffari, F. Kermani, S. Pahlevanynejad, M. Kahouei, M. Mirmohammadkhani, Arash Seidabadi, S. Esmaeili, Mohammad Amin Moradi, Abdolmannan Habibli, A. Firuzi","doi":"10.30699/fhi.v12i0.411","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.411","url":null,"abstract":"Introduction: Emergency Medical Services (EMS) is one of the vital links in the care chain, and its services need to be improved. These services can be available through mobile-based automation system, in which low usability level of these systems lead to decrease the acceptance, satisfaction, and confidence of users especially the emergency care team. The purpose of this study was the usability evaluation of a national mobile- based automation system among the pre-hospital emergency care team.Material and Methods: This cross-sectional study was conducted on pre-hospital emergency care team members in Semnan and Shahroud Universities of Medical Sciences in 2022. The usability evaluation of the mobile- based EMS automation system was done using the Software Usability Measurement Inventory (SUMI) questionnaire. Multiple logistic regression models were used to analyze data.Results: One hundred eighty-eight EMS team members from the 31 EMS centers in Semnan province participated in present study. The mean total usability score was 61.93±15.37, the highest mean score was related to the efficiency feature (67.19±19.85) and the lowest mean score was related to the learnability feature (48.21±29.29). There was a reverse and significant relationship between being a manager and the agreement with the usability (p=0.04, OR= -3.383, CI 95%=0.389-29549).Conclusion: This study showed that although an automation system may be widely used in a country, its usability could be at a low level. In order to improve the different function of these systems, it is suggested to participate various clinical experts include prehospital emergency care team in all stages of designing and developing these systems.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121520741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Dahri, Parisa Zarei Shargh, Atiyeh Sahebzamani, R. Ghasemi, Mostafa Jahangir, F. Moghbeli
Introduction: Nutrition counseling web apps have the ability to improve the quality of health care. The purpose of this study is to design and evaluate the usability of a nutrition counseling web app (virtual clinic) for pregnant women.Material and Methods: It was a descriptive-cross-sectional applied study that first designed and then examined the nutritional counseling web app (virtual clinic) for pregnant women using the heuristic evaluation method. The data was collected with a standard form designed based on the heuristic method. Data analysis was done with SPSS version 26.Results: The number of known individual problems was 34. The highest number of problems was related to the flexibility and efficiency component and the lowest number was related to the component of helping users in diagnosing, identifying and correcting errors. In the end, all the problems identified in the web app were solved and it was given to the evaluators again, and in the end, a score of zero was assigned to all the components, meaning no problem.Conclusion: Compliance with existing standards and rules in the design of web app user interfaces, such as the heuristics mentioned in this study, can reduce problems.
{"title":"Design and Usability Evaluation of Nutritional Counseling Web App (Virtual Clinic) for Pregnant Women","authors":"M. Dahri, Parisa Zarei Shargh, Atiyeh Sahebzamani, R. Ghasemi, Mostafa Jahangir, F. Moghbeli","doi":"10.30699/fhi.v12i0.433","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.433","url":null,"abstract":"Introduction: Nutrition counseling web apps have the ability to improve the quality of health care. The purpose of this study is to design and evaluate the usability of a nutrition counseling web app (virtual clinic) for pregnant women.Material and Methods: It was a descriptive-cross-sectional applied study that first designed and then examined the nutritional counseling web app (virtual clinic) for pregnant women using the heuristic evaluation method. The data was collected with a standard form designed based on the heuristic method. Data analysis was done with SPSS version 26.Results: The number of known individual problems was 34. The highest number of problems was related to the flexibility and efficiency component and the lowest number was related to the component of helping users in diagnosing, identifying and correcting errors. In the end, all the problems identified in the web app were solved and it was given to the evaluators again, and in the end, a score of zero was assigned to all the components, meaning no problem.Conclusion: Compliance with existing standards and rules in the design of web app user interfaces, such as the heuristics mentioned in this study, can reduce problems.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122796539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Considering the worldwide spread of the COVID-19 pandemic, it is critical to use electronic health (e-health) to prevent, diagnose, and treat this disease. According to reports on the use of e-health technology in past and present crises, this technology can have the potential to improve the quality and the quantity of provided services and control and manage diseases in epidemic conditions. The important issue is how to implement this technology fairly and facilitate the use of this technology by health care providers and the general public. Moreover, the concerns about the physician-patient relationship, patient privacy and health costs should be addressed. Therefore, it is necessary for health policymakers and planners to develop laws and guidelines to address legal and ethical barriers to the use of this technology, focusing on vulnerable populations, to manage the crisis and also determine the role of insurers in this area.
{"title":"Learning from Previous Epidemics; Overcoming COVID-19 Using E-Health","authors":"M. Montazeri, Zahra Galavi, L. Ahmadian","doi":"10.30699/fhi.v12i0.431","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.431","url":null,"abstract":"Considering the worldwide spread of the COVID-19 pandemic, it is critical to use electronic health (e-health) to prevent, diagnose, and treat this disease. According to reports on the use of e-health technology in past and present crises, this technology can have the potential to improve the quality and the quantity of provided services and control and manage diseases in epidemic conditions. The important issue is how to implement this technology fairly and facilitate the use of this technology by health care providers and the general public. Moreover, the concerns about the physician-patient relationship, patient privacy and health costs should be addressed. Therefore, it is necessary for health policymakers and planners to develop laws and guidelines to address legal and ethical barriers to the use of this technology, focusing on vulnerable populations, to manage the crisis and also determine the role of insurers in this area.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122546471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Introduction: The aim of this systematic review was to investigate the impact of tele-ophthalmology on screening, monitoring and treatment adherence in eye diseases.Material and Methods: A systematic review of controlled and randomized clinical trial studies without time limit was explored by searching keywords in the title, abstract and keywords of the studies in the reliable scientific databases Embase, Web of Science, Scopus, PubMed on April 20, 2022. A gray literature search was also conducted using the Google search engine to identify the most recent possible evidence. The quality of the studies was evaluated using the Joanna Briggs Institute (JBI) checklist; that the studies with a score above 7 were included in the analysis.Results: A total of 40 articles were identified after removing duplicates. After screening the full text of the articles, 5 studies met the inclusion criteria. In four of the studies, tele-ophthalmology was used for tele-screening and tele-monitoring using tele-imaging approaches, live video conferencing, and websites. Also, in one case, telemedicine reminder studies were used to improve treatment adherence. In the majority of studies, tele-ophthalmology was at least as effective as in-person visit services in screening, monitoring, and adherence to treatment.Conclusion: The results of our systematic review showed that a well-designed tele-ophthalmology program with high-quality cameras and equipment and the use of multiple technologies has the potential to replace or complement in-person visits to an ophthalmologist.
本系统综述的目的是探讨远程眼科对眼病筛查、监测和治疗依从性的影响。材料与方法:于2022年4月20日在可靠的科学数据库Embase、Web of Science、Scopus、PubMed中检索研究题目、摘要及关键词，对无时间限制的对照和随机临床试验研究进行系统综述。还使用谷歌搜索引擎进行了灰色文献检索，以确定最新的可能证据。采用乔安娜布里格斯研究所(JBI)检查表评估研究的质量;得分在7分以上的研究被纳入分析。结果:剔除重复后共鉴定出40篇文献。经全文筛选，有5项研究符合纳入标准。在其中四项研究中，远程眼科通过远程成像方法、实时视频会议和网站进行远程筛查和远程监控。此外，在一个案例中，远程医疗提醒研究被用于提高治疗依从性。在大多数研究中，远程眼科在筛查、监测和坚持治疗方面至少与现场就诊服务一样有效。结论:我们的系统综述结果表明，一个设计良好的远程眼科项目，配备高质量的相机和设备，并使用多种技术，有可能取代或补充眼科医生的亲自就诊。
{"title":"Teleophthalmology: A Systematic Review of Randomized Controlled Trials","authors":"Atefeh Sadat Mousavi, Seyyedeh Fatemeh Mousavi Baigi, Fatemeh Dahmardeh, Marziyeh Raei Mehneh, Reza Darrudi","doi":"10.30699/fhi.v12i0.414","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.414","url":null,"abstract":"Introduction: The aim of this systematic review was to investigate the impact of tele-ophthalmology on screening, monitoring and treatment adherence in eye diseases.Material and Methods: A systematic review of controlled and randomized clinical trial studies without time limit was explored by searching keywords in the title, abstract and keywords of the studies in the reliable scientific databases Embase, Web of Science, Scopus, PubMed on April 20, 2022. A gray literature search was also conducted using the Google search engine to identify the most recent possible evidence. The quality of the studies was evaluated using the Joanna Briggs Institute (JBI) checklist; that the studies with a score above 7 were included in the analysis.Results: A total of 40 articles were identified after removing duplicates. After screening the full text of the articles, 5 studies met the inclusion criteria. In four of the studies, tele-ophthalmology was used for tele-screening and tele-monitoring using tele-imaging approaches, live video conferencing, and websites. Also, in one case, telemedicine reminder studies were used to improve treatment adherence. In the majority of studies, tele-ophthalmology was at least as effective as in-person visit services in screening, monitoring, and adherence to treatment.Conclusion: The results of our systematic review showed that a well-designed tele-ophthalmology program with high-quality cameras and equipment and the use of multiple technologies has the potential to replace or complement in-person visits to an ophthalmologist.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133075027","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
I am writing to express my views on the topic of digital trust in the healthcare industry. With the rapid advancement of technology and the widespread use of electronic health records, it is crucial to understand the impact of digital trust on healthcare. In this letter, I will discuss the importance of digital trust in healthcare, the important challenges faced by the healthcare industry in building and maintaining digital trust, and the potential solutions to address these challenges.
{"title":"Challenges and Opportunities of Digital Trust in the Healthcare Industry","authors":"Khadijeh Moulaei, K. Bahaadinbeigy","doi":"10.30699/fhi.v12i0.437","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.437","url":null,"abstract":"I am writing to express my views on the topic of digital trust in the healthcare industry. With the rapid advancement of technology and the widespread use of electronic health records, it is crucial to understand the impact of digital trust on healthcare. In this letter, I will discuss the importance of digital trust in healthcare, the important challenges faced by the healthcare industry in building and maintaining digital trust, and the potential solutions to address these challenges.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131847025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Introduction: The aim of the present study was to investigate the different roles of m-Health in pandemic management using the Partial Least Square (PLS) modeling technique. Owing to the limited existing literature regarding theorizing and the lack of the default model in predicting the role of m-Health in pandemic management, this method was used for exploratory modeling.Material and Methods: The PLS model was performed with smart-PLS software for the following steps: estimating weight ratios, considering weight ratios as input, estimating parameters, model-fitting and testing hypotheses. In addition, Factor scores in regression equations were used to estimate structural parameters. PLS algorithm, Cronbach's alpha, and Composite Reliability were used for the measurement and reliability evaluation model Goodness-of-fit. In addition, the R2 index was used to evaluate the model adequacy. Bootstrapping was used for significant coefficients. The Goodness-of-fit of the model was examined via the Standardized Root Mean Square Residual (SRMR) criterion.Results: It is determined the measurement models goodness-of-fit which the alpha values were as follows: diagnosis construct=0.786, follow-up=0.772, treatment=0.796, health care providers=0.704 and education=0.839 with more than 0.7 for all measures for Composite Reliability, the structural model measures such as R2 were higher than 0.6 for all areas and the overall model goodness-of-fit was -0.007 for SRMR, the five hypotheses developed in the model were confirmed according standardized coefficients more than 1.96 for all paths. Furthermore, the proposed model concerning the positive and significant role of m-Health in diagnosis, treatment and follow-up, education and health providers during the pandemic era was approved.Conclusion: The results of the present study can be used as a theoretical basis in developing models related to the role of m-Health in pandemic management. Also, health policymakers and practitioners could use the results to manage current and post-coronary conditions and to promote services based on various m-Health apps.
{"title":"An Assessment of m-Health Effect on Covid-19 Management Using PLS Modeling Approach","authors":"L. Erfannia, A. Yazdani, A. Karimi","doi":"10.30699/fhi.v12i0.415","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.415","url":null,"abstract":"Introduction: The aim of the present study was to investigate the different roles of m-Health in pandemic management using the Partial Least Square (PLS) modeling technique. Owing to the limited existing literature regarding theorizing and the lack of the default model in predicting the role of m-Health in pandemic management, this method was used for exploratory modeling.Material and Methods: The PLS model was performed with smart-PLS software for the following steps: estimating weight ratios, considering weight ratios as input, estimating parameters, model-fitting and testing hypotheses. In addition, Factor scores in regression equations were used to estimate structural parameters. PLS algorithm, Cronbach's alpha, and Composite Reliability were used for the measurement and reliability evaluation model Goodness-of-fit. In addition, the R2 index was used to evaluate the model adequacy. Bootstrapping was used for significant coefficients. The Goodness-of-fit of the model was examined via the Standardized Root Mean Square Residual (SRMR) criterion.Results: It is determined the measurement models goodness-of-fit which the alpha values were as follows: diagnosis construct=0.786, follow-up=0.772, treatment=0.796, health care providers=0.704 and education=0.839 with more than 0.7 for all measures for Composite Reliability, the structural model measures such as R2 were higher than 0.6 for all areas and the overall model goodness-of-fit was -0.007 for SRMR, the five hypotheses developed in the model were confirmed according standardized coefficients more than 1.96 for all paths. Furthermore, the proposed model concerning the positive and significant role of m-Health in diagnosis, treatment and follow-up, education and health providers during the pandemic era was approved.Conclusion: The results of the present study can be used as a theoretical basis in developing models related to the role of m-Health in pandemic management. Also, health policymakers and practitioners could use the results to manage current and post-coronary conditions and to promote services based on various m-Health apps.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125612436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zahra Seyfi, Fateme Salehi, S. Pahlevanynejad, Jaleh Shoshtarian Malak, R. Safdari
Introduction: According to WHO, 190 million reproductive-aged women are affected by endometriosis. Using self-care interventions has a significant impact on managing endometriosis-related pain. Despite the enormous potential of different endometriosis applications, the medical professionals’ role has been neglected in the process of app development. This study aimed to extract the requirements for developing a mobile-based app for self-care of endometriosis patients through an overview of the literature, and validate them according to the expert gynecologists’ point of view.Materials and Methods: This cross-sectional descriptive study was carried out in two steps. First, endometriosis-related articles were reviewed. Second, a researcher-made questionnaire (Cronbach’s alpha = 0.98) was designed to validate the identified information elements. Elements that obtained at least an average score of 3.2 (60%) out of 5-point Likert scale, were considered practicable elements for designing the app.Results: Based on the literature review, 36 studies were retrieved and 126 data elements were extracted. The elements were classified into six categories including electronic health record, educational materials, follow-up, pain management, nutritional diet, and lifestyle. All data elements except “using traditional opioids/drugs” were verified.Conclusion: In this study, a minimum data set was achieved for designing an endometriosis mobile app. Due to the lack of international standards for designing health apps, the results of this research can be beneficial for the design and development of any other apps. Investment in this study would improve the quality of care thereby reducing the burden and cost of endometriosis.
{"title":"Identifying Required Data Elements for Designing A Mobile-Based Application for Self-Care of Women Living with Endometriosis","authors":"Zahra Seyfi, Fateme Salehi, S. Pahlevanynejad, Jaleh Shoshtarian Malak, R. Safdari","doi":"10.30699/fhi.v12i0.416","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.416","url":null,"abstract":"Introduction: According to WHO, 190 million reproductive-aged women are affected by endometriosis. Using self-care interventions has a significant impact on managing endometriosis-related pain. Despite the enormous potential of different endometriosis applications, the medical professionals’ role has been neglected in the process of app development. This study aimed to extract the requirements for developing a mobile-based app for self-care of endometriosis patients through an overview of the literature, and validate them according to the expert gynecologists’ point of view.Materials and Methods: This cross-sectional descriptive study was carried out in two steps. First, endometriosis-related articles were reviewed. Second, a researcher-made questionnaire (Cronbach’s alpha = 0.98) was designed to validate the identified information elements. Elements that obtained at least an average score of 3.2 (60%) out of 5-point Likert scale, were considered practicable elements for designing the app.Results: Based on the literature review, 36 studies were retrieved and 126 data elements were extracted. The elements were classified into six categories including electronic health record, educational materials, follow-up, pain management, nutritional diet, and lifestyle. All data elements except “using traditional opioids/drugs” were verified.Conclusion: In this study, a minimum data set was achieved for designing an endometriosis mobile app. Due to the lack of international standards for designing health apps, the results of this research can be beneficial for the design and development of any other apps. Investment in this study would improve the quality of care thereby reducing the burden and cost of endometriosis.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125645026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Introduction: Heart disease is, for the most part, alluding to conditions that include limited or blocked veins that can prompt a heart attack, chest torment or stroke. Earlier identification of heart disease may reduce the death rate. The cost of medical diagnosis makes it perverse to cure it for the large amount of people early. Using machine learning models performed on dataset. This article aims to find the most efficient and accurate machine learning models for disease prediction.Material and Methods: Several supervised machine learning algorithms were utilized to diagnosis and prediction of heart disease such as logistic regression, decision tree, random forest and KNN. The algorithms are applied to a dataset taken from the Kaggle site including 70000 samples. In algorithms, methods such as the importance of features, hold out validation, 10-fold cross-validation, stratified 10-fold cross-validation, leave one out cross-validation are the result of effective performance and increase accuracy. In addition, feature importance scores was estimated for each feature in some algorithms. These features were ranked based on feature importance score. All the work is done in the Anaconda environment based on python programming language and Scikit-learn library.Results: The algorithms performance is compared to each other so that performance based on ROC curve and some criteria such as accuracy, precision, sensitivity and F1 score were evaluated for each model. As a result of evaluation, random forest algorithm with F1 score 92%, accuracy 92% and AUC ROC 95%, has better performance than other algorithms.Conclusion: The area under the ROC curve and evaluating criteria related to a number of classifying algorithms of machine learning to evaluate heart disease and indeed, the diagnosis and prediction of heart disease is compared to determine the most appropriate classifier.
{"title":"Analysis of Accuracy Metric of Machine Learning Algorithms in Predicting Heart Disease","authors":"Sajad Yousefi, Maryam Poornajaf","doi":"10.30699/fhi.v12i0.402","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.402","url":null,"abstract":"Introduction: Heart disease is, for the most part, alluding to conditions that include limited or blocked veins that can prompt a heart attack, chest torment or stroke. Earlier identification of heart disease may reduce the death rate. The cost of medical diagnosis makes it perverse to cure it for the large amount of people early. Using machine learning models performed on dataset. This article aims to find the most efficient and accurate machine learning models for disease prediction.Material and Methods: Several supervised machine learning algorithms were utilized to diagnosis and prediction of heart disease such as logistic regression, decision tree, random forest and KNN. The algorithms are applied to a dataset taken from the Kaggle site including 70000 samples. In algorithms, methods such as the importance of features, hold out validation, 10-fold cross-validation, stratified 10-fold cross-validation, leave one out cross-validation are the result of effective performance and increase accuracy. In addition, feature importance scores was estimated for each feature in some algorithms. These features were ranked based on feature importance score. All the work is done in the Anaconda environment based on python programming language and Scikit-learn library.Results: The algorithms performance is compared to each other so that performance based on ROC curve and some criteria such as accuracy, precision, sensitivity and F1 score were evaluated for each model. As a result of evaluation, random forest algorithm with F1 score 92%, accuracy 92% and AUC ROC 95%, has better performance than other algorithms.Conclusion: The area under the ROC curve and evaluating criteria related to a number of classifying algorithms of machine learning to evaluate heart disease and indeed, the diagnosis and prediction of heart disease is compared to determine the most appropriate classifier.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115846663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. Sayadi, Vijayakumar Varadarajan, Elahe Gozali, M. Sadeghi
Introduction: Hepatitis C virus (HCV) is a major public health threat, which can be treated if diagnosed early, but unfortunately, many people with chronic diseases are not diagnosed until the final stages. Machine learning and its techniques can be very helpful in diagnosis. This study examines the factors affecting hepatitis C diagnosis using machine learning.Material and Methods: A total of 27 features were used with a dataset containing 1385 records of patients with different grades of HCV. The dataset was clean and preprocessed to ensure accuracy and consistency. To reduce the dimension of the dataset and determine the effective features three feature selection, Pearson Correlation, ANOVA, and Random Forest, were applied. Among all the algorithms, KNN, random forests, and Deep Neural Networks were selected to be utilized, and then their evaluation metrics, such as Accuracy and Recall. To create prediction models, fifteen features were selected for the mentioned machine learning algorithms.Results: Performance evaluation of these models based on accuracy showed that Deep Learning with Accuracy = 92.067 had the highest performance. KNN and Random Forest had almost the same performance after Deep Learning. This performance was achieved on dataset containing features that were selected by ANOVA feature selection.Conclusion: Machine learning has been very effective in solving many challenges in the field of health. This study showed that using data-mining algorithms also can be useful for HCV diagnosing. The proposed model in this study can help physicians diagnose the degree of HCV at an affordable and with high accuracy.
{"title":"Effective Factors in Diagnosing the Degree of Hepatitis C Using Machine Learning","authors":"M. Sayadi, Vijayakumar Varadarajan, Elahe Gozali, M. Sadeghi","doi":"10.30699/fhi.v12i0.440","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.440","url":null,"abstract":"Introduction: Hepatitis C virus (HCV) is a major public health threat, which can be treated if diagnosed early, but unfortunately, many people with chronic diseases are not diagnosed until the final stages. Machine learning and its techniques can be very helpful in diagnosis. This study examines the factors affecting hepatitis C diagnosis using machine learning.Material and Methods: A total of 27 features were used with a dataset containing 1385 records of patients with different grades of HCV. The dataset was clean and preprocessed to ensure accuracy and consistency. To reduce the dimension of the dataset and determine the effective features three feature selection, Pearson Correlation, ANOVA, and Random Forest, were applied. Among all the algorithms, KNN, random forests, and Deep Neural Networks were selected to be utilized, and then their evaluation metrics, such as Accuracy and Recall. To create prediction models, fifteen features were selected for the mentioned machine learning algorithms.Results: Performance evaluation of these models based on accuracy showed that Deep Learning with Accuracy = 92.067 had the highest performance. KNN and Random Forest had almost the same performance after Deep Learning. This performance was achieved on dataset containing features that were selected by ANOVA feature selection.Conclusion: Machine learning has been very effective in solving many challenges in the field of health. This study showed that using data-mining algorithms also can be useful for HCV diagnosing. The proposed model in this study can help physicians diagnose the degree of HCV at an affordable and with high accuracy.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116749871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As someone who has been following the development of hyper-automation technologies in healthcare, I wanted to write to you about the many optimistic outcomes that these technologies have already produced. I am writing to express my excitement about many potential and benefits of hyper-automation technologies in healthcare. Hyper-automation, which includes the use of smart technologies such as artificial intelligence, low-code/no-code (LCNC) platforms, machine learning, robotics and other technologies to automate and optimize processes, has the possibility to transform healthcare in many ways [1].
{"title":"A New Revolution in Healthcare Transformation Using Hyper-Automation Technologies","authors":"Khadijeh Moulaei, K. Bahaadinbeigy","doi":"10.30699/fhi.v12i0.422","DOIUrl":"https://doi.org/10.30699/fhi.v12i0.422","url":null,"abstract":"As someone who has been following the development of hyper-automation technologies in healthcare, I wanted to write to you about the many optimistic outcomes that these technologies have already produced. I am writing to express my excitement about many potential and benefits of hyper-automation technologies in healthcare. Hyper-automation, which includes the use of smart technologies such as artificial intelligence, low-code/no-code (LCNC) platforms, machine learning, robotics and other technologies to automate and optimize processes, has the possibility to transform healthcare in many ways [1].","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127455545","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：