M. Montazeri, Ali Afraz, M. Montazeri, Sadegh Nejatzadeh, F. Rahimi, Mohsen Taherian, Mohadeseh Montazeri, L. Ahmadian
Introduction: Our aim in this study was to summarize information on the use of intelligent models for predicting and diagnosing the Coronavirus disease 2019 (COVID-19) to help early and timely diagnosis of the disease.Material and Methods: A systematic literature search included articles published until 20 April 2020 in PubMed, Web of Science, IEEE, ProQuest, Scopus, bioRxiv, and medRxiv databases. The search strategy consisted of two groups of keywords: A) Novel coronavirus, B) Machine learning. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. Studies were critically reviewed for risk of bias using prediction model risk of bias assessment tool.Results: We gathered 1650 articles through database searches. After the full-text assessment 31 articles were included. Neural networks and deep neural network variants were the most popular machine learning type. Of the five models that authors claimed were externally validated, we considered external validation only for four of them. Area under the curve (AUC) in internal validation of prognostic models varied from .94 to .97. AUC in diagnostic models varied from 0.84 to 0.99, and AUC in external validation of diagnostic models varied from 0.73 to 0.94. Our analysis finds all but two studies have a high risk of bias due to various reasons like a low number of participants and lack of external validation.Conclusion: Diagnostic and prognostic models for COVID-19 show good to excellent discriminative performance. However, these models are at high risk of bias because of various reasons like a low number of participants and lack of external validation. Future studies should address these concerns. Sharing data and experiences for the development, validation, and updating of COVID-19 related prediction models is needed.
前言:本研究旨在总结新型冠状病毒病(COVID-19)智能预测诊断模型的应用信息，以帮助早期和及时诊断该疾病。材料和方法:系统文献检索包括截至2020年4月20日在PubMed、Web of Science、IEEE、ProQuest、Scopus、bioRxiv和medRxiv数据库中发表的文章。搜索策略包括两组关键词:A)新型冠状病毒，B)机器学习。两位审稿人独立评估原始论文以确定纳入本综述的资格。使用预测模型偏倚风险评估工具对研究进行了严格的偏倚风险评估。结果:我们通过数据库检索收集了1650篇文章。经全文评估后，纳入31篇文章。神经网络和深度神经网络变体是最流行的机器学习类型。在作者声称经过外部验证的五个模型中，我们只考虑了其中四个模型的外部验证。预测模型内部验证的曲线下面积(AUC)从0.94到0.97不等。诊断模型的AUC范围为0.84 ~ 0.99，诊断模型外部验证的AUC范围为0.73 ~ 0.94。我们的分析发现，除了两项研究外，由于参与者数量少和缺乏外部验证等各种原因，所有研究都有很高的偏倚风险。结论:新型冠状病毒肺炎的诊断和预后模型具有较好的判别性能。然而，由于参与者数量少、缺乏外部验证等各种原因，这些模型存在较高的偏倚风险。未来的研究应该解决这些问题。需要共享数据和经验，以开发、验证和更新COVID-19相关预测模型。
{"title":"Applications of Artificial Intelligence and Machine Learning in Diagnosis and Prognosis of COVID-19 infection: A systematic review","authors":"M. Montazeri, Ali Afraz, M. Montazeri, Sadegh Nejatzadeh, F. Rahimi, Mohsen Taherian, Mohadeseh Montazeri, L. Ahmadian","doi":"10.30699/fhi.v10i1.321","DOIUrl":"https://doi.org/10.30699/fhi.v10i1.321","url":null,"abstract":"Introduction: Our aim in this study was to summarize information on the use of intelligent models for predicting and diagnosing the Coronavirus disease 2019 (COVID-19) to help early and timely diagnosis of the disease.Material and Methods: A systematic literature search included articles published until 20 April 2020 in PubMed, Web of Science, IEEE, ProQuest, Scopus, bioRxiv, and medRxiv databases. The search strategy consisted of two groups of keywords: A) Novel coronavirus, B) Machine learning. Two reviewers independently assessed original papers to determine eligibility for inclusion in this review. Studies were critically reviewed for risk of bias using prediction model risk of bias assessment tool.Results: We gathered 1650 articles through database searches. After the full-text assessment 31 articles were included. Neural networks and deep neural network variants were the most popular machine learning type. Of the five models that authors claimed were externally validated, we considered external validation only for four of them. Area under the curve (AUC) in internal validation of prognostic models varied from .94 to .97. AUC in diagnostic models varied from 0.84 to 0.99, and AUC in external validation of diagnostic models varied from 0.73 to 0.94. Our analysis finds all but two studies have a high risk of bias due to various reasons like a low number of participants and lack of external validation.Conclusion: Diagnostic and prognostic models for COVID-19 show good to excellent discriminative performance. However, these models are at high risk of bias because of various reasons like a low number of participants and lack of external validation. Future studies should address these concerns. Sharing data and experiences for the development, validation, and updating of COVID-19 related prediction models is needed. ","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131478002","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: Cancer is an incurable disease that affects people regardless of age, sex, race and social, economic and cultural status. Most cancer patients are treated with a combination of treatments based on the type of tumor, the extent of the disease, and their physical condition. Self-management programs empower people to deal with illness and improve their quality of life. Telemedicine in the form of mobile applications, websites and social networks is one of the effective tools to achieve this goal. The aim of this study was to investigate the impact of telemedicine and social media on self-care of cancer patients.Method: English related articles were searched based on keywords in the title and abstract using PubMed and Scopus databases (from 1963 to December 2020). Keywords included telemedicine, social networking, self-care and m-health. Inclusion criteria included all studies published in English that examined the impact of telemedicine and social media on cancer patients' self-care. Review articles and non-intervention articles were excluded from the study.Results: A total of 516 articles were selected by title. After reviewing the abstract, 80 articles remained to be reviewed. After evaluating the full text of these articles, 9 eligible articles were selected for final review. In terms of the type of cancer among these studies, prostate cancer had the largest share (33%). In line with the main purpose of this study, in 7 articles (77.8%) telemedicine had a significant positive effect on self-care of cancer patients and increased self-care. In one article (11.1%) this effect was negative and reduced self-care. In 1 article (11.1%) no effect was observed.Conclusion: According to the results of the present study, it seems that web-based interventions and mobile health in most articles have been effective in increasing patients' self-care. However, due to the increasing number of cancers as well as the increasing use of telemedicine in the field of chronic diseases and cancer, the need for further studies is felt in this field.
{"title":"The Effect of Telemedicine and Social Media on Cancer patients' Self-Care: A Systematic Review","authors":"Fariba Sadat Agha Seyyed Esmaeil Amiri, Fatemeh Bohlouly, Atefeh Khoshkangin, Negin Razmi, Kosar Ghaddaripouri, Mohammad Reza Mazaheri Habibi","doi":"10.30699/FHI.V10I1.316","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.316","url":null,"abstract":"Introduction: Cancer is an incurable disease that affects people regardless of age, sex, race and social, economic and cultural status. Most cancer patients are treated with a combination of treatments based on the type of tumor, the extent of the disease, and their physical condition. Self-management programs empower people to deal with illness and improve their quality of life. Telemedicine in the form of mobile applications, websites and social networks is one of the effective tools to achieve this goal. The aim of this study was to investigate the impact of telemedicine and social media on self-care of cancer patients.Method: English related articles were searched based on keywords in the title and abstract using PubMed and Scopus databases (from 1963 to December 2020). Keywords included telemedicine, social networking, self-care and m-health. Inclusion criteria included all studies published in English that examined the impact of telemedicine and social media on cancer patients' self-care. Review articles and non-intervention articles were excluded from the study.Results: A total of 516 articles were selected by title. After reviewing the abstract, 80 articles remained to be reviewed. After evaluating the full text of these articles, 9 eligible articles were selected for final review. In terms of the type of cancer among these studies, prostate cancer had the largest share (33%). In line with the main purpose of this study, in 7 articles (77.8%) telemedicine had a significant positive effect on self-care of cancer patients and increased self-care. In one article (11.1%) this effect was negative and reduced self-care. In 1 article (11.1%) no effect was observed.Conclusion: According to the results of the present study, it seems that web-based interventions and mobile health in most articles have been effective in increasing patients' self-care. However, due to the increasing number of cancers as well as the increasing use of telemedicine in the field of chronic diseases and cancer, the need for further studies is felt in this field.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131178097","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: Improvement of technology can increase the use of machine learning algorithms in predicting diseases. Early diagnosis of the disease can reduce mortality and morbidity at the community level.Material and Methods: In this paper, a clinical decision support system for the diagnosis of gestational diabetes is presented by combining artificial neural network and meta-heuristic algorithm. In this study, four meta-innovative algorithms of genetics, ant colony, particle Swarm optimization and cuckoo search were selected to be combined with artificial neural network. Then these four algorithms were compared with each other. The data set contains 768 records and 8 dependent variables. This data set has 200 missing records, so the number of study records was reduced to 568 records.Results: The data were divided into two sets of training and testing by 10-Fold method. Then, all four algorithms of neural-genetic network, ant-neural colony network, neural network-particle Swarm optimization and neural network-cuckoo search on the data The trainings were performed and then evaluated by the test set. And the accuracy of 95.02 was obtained. Also, the final output of the algorithm was examined with two similar tasks and it was shown that the proposed model worked better.Conclusion: In this study showed that the combination of two neural network and genetic algorithms can provide a suitable predictive model for disease diagnosis.
{"title":"Provide a Diagnostic Model Using a Combination of Two Neural Network Algorithms and a Genetic Algorithm","authors":"Farshad Minaei, Hassan Dosti, Ebrahim Salimi Turk, Amin Golabpour","doi":"10.30699/FHI.V10I1.303","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.303","url":null,"abstract":"Introduction: Improvement of technology can increase the use of machine learning algorithms in predicting diseases. Early diagnosis of the disease can reduce mortality and morbidity at the community level.Material and Methods: In this paper, a clinical decision support system for the diagnosis of gestational diabetes is presented by combining artificial neural network and meta-heuristic algorithm. In this study, four meta-innovative algorithms of genetics, ant colony, particle Swarm optimization and cuckoo search were selected to be combined with artificial neural network. Then these four algorithms were compared with each other. The data set contains 768 records and 8 dependent variables. This data set has 200 missing records, so the number of study records was reduced to 568 records.Results: The data were divided into two sets of training and testing by 10-Fold method. Then, all four algorithms of neural-genetic network, ant-neural colony network, neural network-particle Swarm optimization and neural network-cuckoo search on the data The trainings were performed and then evaluated by the test set. And the accuracy of 95.02 was obtained. Also, the final output of the algorithm was examined with two similar tasks and it was shown that the proposed model worked better.Conclusion: In this study showed that the combination of two neural network and genetic algorithms can provide a suitable predictive model for disease diagnosis.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127922387","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: Diagnostic point- of- care (POC) tests are considered as an approach to ease the diagnosis of diseases, deliver quicker patient care, and improve patient safety. The aim of this study was to review the diagnostic POC tests with an approach to data management.Material and Methods: In this review study, PubMed, Science Direct, Google Scholar, Scopus, and Wolters Kluwer databases were searched from 2000 to 2020 using a combination of related keywords. A total of 96 articles were retrieved of which 48 articles considered as relevant. The content of these articles were then analyzed with respect to the aim of the study. The inclusion criteria for the articles were: 1) they focused the POC test; 2) addressed data management aspects; 3) written in English. Articles that only addressed the POC tests from a clinical or technical perspective and with no indication of data management were excluded.Results: Rapid and timely collection and processing of test results, the capability of exchanging test results, and capabilities such as documentation and data quality control play a significant role in reducing the average length of stay in hospital, planning, decision-making, organizing, controlling clinical and managerial activities, and achieving the efficiency of services provided.Conclusion: In addition to applying diagnostic POC tests technologies, medical settings should have necessary approaches for managing data generated by these technologies to improve better use of data in service delivery.
{"title":"Diagnostic Point-of-Care Tests with an Approach to Data Management","authors":"F. Asadi, H. Moghaddasi, M. Anvari, R. Rabiei","doi":"10.30699/FHI.V10I1.322","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.322","url":null,"abstract":"Introduction: Diagnostic point- of- care (POC) tests are considered as an approach to ease the diagnosis of diseases, deliver quicker patient care, and improve patient safety. The aim of this study was to review the diagnostic POC tests with an approach to data management.Material and Methods: In this review study, PubMed, Science Direct, Google Scholar, Scopus, and Wolters Kluwer databases were searched from 2000 to 2020 using a combination of related keywords. A total of 96 articles were retrieved of which 48 articles considered as relevant. The content of these articles were then analyzed with respect to the aim of the study. The inclusion criteria for the articles were: 1) they focused the POC test; 2) addressed data management aspects; 3) written in English. Articles that only addressed the POC tests from a clinical or technical perspective and with no indication of data management were excluded.Results: Rapid and timely collection and processing of test results, the capability of exchanging test results, and capabilities such as documentation and data quality control play a significant role in reducing the average length of stay in hospital, planning, decision-making, organizing, controlling clinical and managerial activities, and achieving the efficiency of services provided.Conclusion: In addition to applying diagnostic POC tests technologies, medical settings should have necessary approaches for managing data generated by these technologies to improve better use of data in service delivery.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"133 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127433653","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}
Melika Babaei, Sharareh R. Niakan Kalhori, S. Sheybani, Hesam Karim
Introduction: Inadequate anesthetic, including under or over dosage, may lead to intraoperative awareness or prolonged recovery. Fuzzy expert systems can assist anesthesiologist to manage drug dosage in a right manner. Designing a fuzzy rule-based expert system to determine the Propofol anesthetic drug dosage was the main objective of this study.Material and Methods: This is a retrospective study. Fuzzy IF-THEN rules were defined based on evidences and experts’ linguistic rules for Propofol dose determination. Fuzzy toolbox in MATLAB software was used to design the system. Validation of system conducted with calculation of mean absolute error (MAE) and root mean squared error (RMSE). Also, difference mean between actual and predicted doses was tested with paired t-test in SPSS V.26 software. Data from 50 ENT (ears, nose, and throat) surgeries were used to validate the fuzzy system.Results: MAE for induction and maintenance doses was 0.128 and 1.95 respectively. RMSE for induction and maintenance doses was 0.228 and 3.383 respectively. Based on paired t-test result, there was no significant correlation between actual and predicted values (P>0.05).Conclusion: Obtained value from test and validation of system demonstrated a high performance and satisfying accuracy of the system. Therefore, this expert system can be used as a decision support system to determine initial dosage of anesthetic drugs. It can also be used for anesthesia students to learn drug administration.
{"title":"A Fuzzy Rule-Based Expert System to Determine Propofol Drug Dosage in Anesthesia","authors":"Melika Babaei, Sharareh R. Niakan Kalhori, S. Sheybani, Hesam Karim","doi":"10.30699/FHI.V10I1.304","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.304","url":null,"abstract":"Introduction: Inadequate anesthetic, including under or over dosage, may lead to intraoperative awareness or prolonged recovery. Fuzzy expert systems can assist anesthesiologist to manage drug dosage in a right manner. Designing a fuzzy rule-based expert system to determine the Propofol anesthetic drug dosage was the main objective of this study.Material and Methods: This is a retrospective study. Fuzzy IF-THEN rules were defined based on evidences and experts’ linguistic rules for Propofol dose determination. Fuzzy toolbox in MATLAB software was used to design the system. Validation of system conducted with calculation of mean absolute error (MAE) and root mean squared error (RMSE). Also, difference mean between actual and predicted doses was tested with paired t-test in SPSS V.26 software. Data from 50 ENT (ears, nose, and throat) surgeries were used to validate the fuzzy system.Results: MAE for induction and maintenance doses was 0.128 and 1.95 respectively. RMSE for induction and maintenance doses was 0.228 and 3.383 respectively. Based on paired t-test result, there was no significant correlation between actual and predicted values (P>0.05).Conclusion: Obtained value from test and validation of system demonstrated a high performance and satisfying accuracy of the system. Therefore, this expert system can be used as a decision support system to determine initial dosage of anesthetic drugs. It can also be used for anesthesia students to learn drug administration.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128575546","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}
F. Salehi, G. Moradi, Masoud Setodefar, Mohammad Reza Mazaheri Habibi
Introduction: Advances and increasing technology adoption in the field of health have made it possible to implement tools such as clinical dashboards to assist nursing staff in providing better, more effective and safer care. The aim of this study was to investigate the role of clinical dashboards in providing nursing care.Material and Methods: This was a review study. For this purpose, the keywords Nursing, Nursing care, Clinical Dashboard, Health Dashboard, Evaluation were searched in the database of PubMed, Google Scholar, science direct. Criteria for inclusion in this study were studies that examined the role of clinical dashboards in the field of nursing and were published between 1990 and 2020. The necessary information was extracted using a researcher-made checklist and analyzed and reported in a descriptive manner.Results: A total of 2749 articles were retrieved. After reviewing by title, abstract and keywords, 7 studies that had appropriate content validity were selected for the present study. The intensive care unit had the highest frequency of dashboard use in nursing processes (n=3, 42%). The findings of this study showed that improving the quality of care, reducing medical errors and increasing patient safety are the most important benefits of using clinical dashboards in the field of nursing. Improving nurses' awareness of important patient issues and supporting clinical decisions were next in line.Conclusion: Clinical dashboards in the field of nursing care can reduce errors and possible negligence in the treatment by integration patient information and providing a comprehensive visual view of important patient information and as a suitable tool for evidence-based clinical and nursing decision support.
{"title":"Investigating the Role of Clinical Dashboards in Improving Nursing Care: A Systematic Review","authors":"F. Salehi, G. Moradi, Masoud Setodefar, Mohammad Reza Mazaheri Habibi","doi":"10.30699/fhi.v10i1.308","DOIUrl":"https://doi.org/10.30699/fhi.v10i1.308","url":null,"abstract":"Introduction: Advances and increasing technology adoption in the field of health have made it possible to implement tools such as clinical dashboards to assist nursing staff in providing better, more effective and safer care. The aim of this study was to investigate the role of clinical dashboards in providing nursing care.Material and Methods: This was a review study. For this purpose, the keywords Nursing, Nursing care, Clinical Dashboard, Health Dashboard, Evaluation were searched in the database of PubMed, Google Scholar, science direct. Criteria for inclusion in this study were studies that examined the role of clinical dashboards in the field of nursing and were published between 1990 and 2020. The necessary information was extracted using a researcher-made checklist and analyzed and reported in a descriptive manner.Results: A total of 2749 articles were retrieved. After reviewing by title, abstract and keywords, 7 studies that had appropriate content validity were selected for the present study. The intensive care unit had the highest frequency of dashboard use in nursing processes (n=3, 42%). The findings of this study showed that improving the quality of care, reducing medical errors and increasing patient safety are the most important benefits of using clinical dashboards in the field of nursing. Improving nurses' awareness of important patient issues and supporting clinical decisions were next in line.Conclusion: Clinical dashboards in the field of nursing care can reduce errors and possible negligence in the treatment by integration patient information and providing a comprehensive visual view of important patient information and as a suitable tool for evidence-based clinical and nursing decision support.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"169 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133444098","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}
COVID-19 virus variants are rapidly spreading across the world. Successful tracing of contacts and early isolation after the onset of symptoms are vital, because, in this period, patients can infect other people having contact with them before isolation. One method for identifying, tracing, screening, and monitoring the potential patients can be self-reporting of information by these individuals. The present letter suggested importance of recording self-reported information in the management of COVID-19 virus variants using technology-based devices.
{"title":"The Importance of Recording Self-Reported Information in the Management of COVID-19 Virus Variants: A Technology-Based Approach","authors":"Farzad Salmanizadeh, A. Ameri","doi":"10.30699/fhi.v10i1.315","DOIUrl":"https://doi.org/10.30699/fhi.v10i1.315","url":null,"abstract":"COVID-19 virus variants are rapidly spreading across the world. Successful tracing of contacts and early isolation after the onset of symptoms are vital, because, in this period, patients can infect other people having contact with them before isolation. One method for identifying, tracing, screening, and monitoring the potential patients can be self-reporting of information by these individuals. The present letter suggested importance of recording self-reported information in the management of COVID-19 virus variants using technology-based devices.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116643311","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: Early detection breast cancer Causes it most curable cancer in among other types of cancer, early detection and accurate examination for breast cancer ensures an extended survival rate of the patients. Risk factors are an important parameter in breast cancer has an important effect on breast cancer. Data mining techniques have a growing reputation in the medical field because of high predictive capability and useful classification. These methods can help practitioners to develop tools that allow detecting the early stages of breast cancer.Material and Methods: The database used in this paper is provided by Motamed Cancer Institute, ACECR Tehran, Iran. It contains of 7834 records of breast cancer patients clinical and risk factors data. There were 4008 patients (52.4%) with breast cancers (malignant) and the remaining 3617 patients (47.6%) without breast cancers (benign). Support vector machine, multi-layer perceptron, decision tree, K nearest neighbor, random forest, naïve Bayesian models were developed using 20 fields (risk factor) of the database because database feature was restrictions. Used 10-fold crossover for models evaluate. Ultimately, the comparison of the models was made based on sensitivity, specificity and accuracy indicators.Results: Naïve Bayesian and artificial neural network are better models for the prediction of breast cancer risks. Naïve Bayesian had accuracy of 93%, specificity of 93.32%, sensitivity of 95056%, ROC of 0.95 and artificial neural network had accuracy of 93.23%, specificity of 91.98%, sensitivity of 92.69%, and ROC of 0.8.Conclusion: Strangely the different artificial intelligent calculations utilized in this examination yielded close precision subsequently these techniques could be utilized as option prescient instruments in the bosom malignancy risk considers. The significant prognostic components affecting risk pace of bosom disease distinguished in this investigation, which were approved by risk, are helpful and could be converted into choice help devices in the clinical area.
{"title":"Performance Analysis of Data Mining Techniques for the Prediction Breast Cancer Risk on Big Data","authors":"Solmaz Sohrabei, Alireza Atashi","doi":"10.30699/FHI.V10I1.296","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.296","url":null,"abstract":"Introduction: Early detection breast cancer Causes it most curable cancer in among other types of cancer, early detection and accurate examination for breast cancer ensures an extended survival rate of the patients. Risk factors are an important parameter in breast cancer has an important effect on breast cancer. Data mining techniques have a growing reputation in the medical field because of high predictive capability and useful classification. These methods can help practitioners to develop tools that allow detecting the early stages of breast cancer.Material and Methods: The database used in this paper is provided by Motamed Cancer Institute, ACECR Tehran, Iran. It contains of 7834 records of breast cancer patients clinical and risk factors data. There were 4008 patients (52.4%) with breast cancers (malignant) and the remaining 3617 patients (47.6%) without breast cancers (benign). Support vector machine, multi-layer perceptron, decision tree, K nearest neighbor, random forest, naïve Bayesian models were developed using 20 fields (risk factor) of the database because database feature was restrictions. Used 10-fold crossover for models evaluate. Ultimately, the comparison of the models was made based on sensitivity, specificity and accuracy indicators.Results: Naïve Bayesian and artificial neural network are better models for the prediction of breast cancer risks. Naïve Bayesian had accuracy of 93%, specificity of 93.32%, sensitivity of 95056%, ROC of 0.95 and artificial neural network had accuracy of 93.23%, specificity of 91.98%, sensitivity of 92.69%, and ROC of 0.8.Conclusion: Strangely the different artificial intelligent calculations utilized in this examination yielded close precision subsequently these techniques could be utilized as option prescient instruments in the bosom malignancy risk considers. The significant prognostic components affecting risk pace of bosom disease distinguished in this investigation, which were approved by risk, are helpful and could be converted into choice help devices in the clinical area.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130425869","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}
Information dashboards were one of the best ways to manage Covid disease. The concept of information dashboards and their important benefits are explained in the present study.
{"title":"The Role of Information Dashboards as a Business Intelligence Tool for Managing the Corona Virus Pandemic","authors":"Razieh Farrahi, Ehsan Nabovati, Z. Ebnehoseini","doi":"10.30699/FHI.V10I1.307","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.307","url":null,"abstract":"Information dashboards were one of the best ways to manage Covid disease. The concept of information dashboards and their important benefits are explained in the present study.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122162368","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: Earthquakes, one of the most important natural disasters of the earth, have always caused irreparable damage to human settlements in short time. One of the most important issues that we face after an earthquake is the transfer of earthquake victims and traumatized civilians to safe places and medical centers. The city of Mashhad with different geographical faults and the presence of enormous religious, cultural, historical and industrial assets make Mashhad the most dangerous city in terms of earthquake hazards. In the 9th district of this city, the existence of worn-out structures along the narrow passages and the importance to save time in providing relief proves the need to locate temporary accommodation centers and allocate the injured to safe places.Material and Methods:The process of optimizing the accommodation of people includes 2 main steps 1) Determining candidate locations for temporary accommodation 2) Optimal allocation of population blocks (origin).The weight of criteria was calculated using the pairwise comparison method. Then suitable places for deployment are identified. Criterion in the form of giving a specific weight to each, in order to prepare the final map, is of importance. Accordingly, the opinions of experts in the field of urban crisis management have been utilized. Subsequently, using GAMS software and 7 super-innovative algorithms such as SA, PSO, ICA, ACO, ABC, FA, LAFA.Results:The average process time and cost of 7 algorithms out of ten random problems with 1000 repetitions, and an average of 10 execution times show, that the 3 algorithms ACO, ABC and LAFA have lower cost and process time than the other meta-innovative algorithms. Therefore, we use the above three algorithms to solve the case studyConclusion: Finally, the LAFA optimization algorithm had obtained a better and more appropriate result due to its execution time and cost being less than the other two algorithms.
{"title":"Mathematical Modeling of the Problem of Locating Temporary Accommodation Centers and Assigning Victims After a Possible Earthquake to Safe Places and Solving Using Meta-Heuristic Algorithms","authors":"Farideh Mardaninejad, M. Nastaran","doi":"10.30699/FHI.V10I1.293","DOIUrl":"https://doi.org/10.30699/FHI.V10I1.293","url":null,"abstract":"Introduction: Earthquakes, one of the most important natural disasters of the earth, have always caused irreparable damage to human settlements in short time. One of the most important issues that we face after an earthquake is the transfer of earthquake victims and traumatized civilians to safe places and medical centers. The city of Mashhad with different geographical faults and the presence of enormous religious, cultural, historical and industrial assets make Mashhad the most dangerous city in terms of earthquake hazards. In the 9th district of this city, the existence of worn-out structures along the narrow passages and the importance to save time in providing relief proves the need to locate temporary accommodation centers and allocate the injured to safe places.Material and Methods:The process of optimizing the accommodation of people includes 2 main steps 1) Determining candidate locations for temporary accommodation 2) Optimal allocation of population blocks (origin).The weight of criteria was calculated using the pairwise comparison method. Then suitable places for deployment are identified. Criterion in the form of giving a specific weight to each, in order to prepare the final map, is of importance. Accordingly, the opinions of experts in the field of urban crisis management have been utilized. Subsequently, using GAMS software and 7 super-innovative algorithms such as SA, PSO, ICA, ACO, ABC, FA, LAFA.Results:The average process time and cost of 7 algorithms out of ten random problems with 1000 repetitions, and an average of 10 execution times show, that the 3 algorithms ACO, ABC and LAFA have lower cost and process time than the other meta-innovative algorithms. Therefore, we use the above three algorithms to solve the case studyConclusion: Finally, the LAFA optimization algorithm had obtained a better and more appropriate result due to its execution time and cost being less than the other two algorithms.","PeriodicalId":154611,"journal":{"name":"Frontiers in Health Informatics","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124205983","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：