The deadliest form of skin cancer is melanoma, and if detected in time, it is curable. Detection of melanoma using biopsy is a painful and time-consuming task. Alternate means are being used by medical experts to diagnose melanoma by extracting features from skin lesion images. Medical image diagnosis requires intelligent systems. Many intelligent systems based on image processing and machine learning have been proposed by researchers in the past to detect different kinds of diseases that are successfully used by healthcare organisations worldwide. Intelligent systems to detect melanoma from skin lesion images are also evolving with the aim of improving the accuracy of melanoma detection. Feature extraction plays a critical role. In this paper, a model is proposed in which features are extracted using convolutional neural network (CNN) with transfer learning and a hierarchical classifier consisting of random forest (RF), k-nearest neighbor (KNN), and adaboost is used to detect melanoma using the extracted features. Experimental results show the effectiveness of the proposed model.
{"title":"Using Transfer Learning and Hierarchical Classifier to Diagnose Melanoma From Dermoscopic Images","authors":"Priti Bansal, Sumit Kumar, Ritesh Srivastava, Saksham Agarwal","doi":"10.4018/ijhisi.20210401.oa4","DOIUrl":"https://doi.org/10.4018/ijhisi.20210401.oa4","url":null,"abstract":"The deadliest form of skin cancer is melanoma, and if detected in time, it is curable. Detection of melanoma using biopsy is a painful and time-consuming task. Alternate means are being used by medical experts to diagnose melanoma by extracting features from skin lesion images. Medical image diagnosis requires intelligent systems. Many intelligent systems based on image processing and machine learning have been proposed by researchers in the past to detect different kinds of diseases that are successfully used by healthcare organisations worldwide. Intelligent systems to detect melanoma from skin lesion images are also evolving with the aim of improving the accuracy of melanoma detection. Feature extraction plays a critical role. In this paper, a model is proposed in which features are extracted using convolutional neural network (CNN) with transfer learning and a hierarchical classifier consisting of random forest (RF), k-nearest neighbor (KNN), and adaboost is used to detect melanoma using the extracted features. Experimental results show the effectiveness of the proposed model.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"416 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120938746","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}
Pub Date : 2021-04-01DOI: 10.4018/ijhisi.20210401.oa2
Deepti Singh, B. Kumar, Samayveer Singh, S. Chand
The role of wireless medical sensor networks (WMSNs) is very significant in healthcare applications of IoT. Online report generation and sharing the reports reduce the time and make the treatment of patients very fast. Here, the safety of patient data plays a crucial role. As there is a restriction of resources in sensor nodes, the design of authentication scheme for WMSNs is not an easy task in healthcare applications. Healthcare professionals are using their mobile to collect data from patients' bodies. To use WMSNs in healthcare applications, cryptanalysis of Li et al. is done and found that it suffers from various attacks. Hence, a new efficient privacy-preserving user authenticated scheme using elliptic curve cryptography (ECC) is proposed. The security analysis of scheme is performed using random oracle model, in addition to BAN logic. AVISPA is used for simulation to prove that the proposed scheme can resist passive and active attacks. Finally, the performance comparison of schemes shows that the proposed scheme performs better.
{"title":"A Secure IoT-Based Mutual Authentication for Healthcare Applications in Wireless Sensor Networks Using ECC","authors":"Deepti Singh, B. Kumar, Samayveer Singh, S. Chand","doi":"10.4018/ijhisi.20210401.oa2","DOIUrl":"https://doi.org/10.4018/ijhisi.20210401.oa2","url":null,"abstract":"The role of wireless medical sensor networks (WMSNs) is very significant in healthcare applications of IoT. Online report generation and sharing the reports reduce the time and make the treatment of patients very fast. Here, the safety of patient data plays a crucial role. As there is a restriction of resources in sensor nodes, the design of authentication scheme for WMSNs is not an easy task in healthcare applications. Healthcare professionals are using their mobile to collect data from patients' bodies. To use WMSNs in healthcare applications, cryptanalysis of Li et al. is done and found that it suffers from various attacks. Hence, a new efficient privacy-preserving user authenticated scheme using elliptic curve cryptography (ECC) is proposed. The security analysis of scheme is performed using random oracle model, in addition to BAN logic. AVISPA is used for simulation to prove that the proposed scheme can resist passive and active attacks. Finally, the performance comparison of schemes shows that the proposed scheme performs better.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134329217","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}
Pub Date : 2021-04-01DOI: 10.4018/ijhisi.20210401.oa3
P. KauserAhmed, D. Acharjya
Vast volumes of raw data are generated from the digital world each day. Acquiring useful information and chief features from this data is challenging, and it has become a prime area of current research. Another crucial area is knowledge inferencing. Much research has been carried out in both directions. Swarm intelligence is used for feature selection whereas for knowledge inferencing either fuzzy or rough computing is widely used. Hybridization of intelligent and swarm intelligence techniques are booming recently. In this research work, the authors hybridize both artificial bee colony and rough set. At the initial phase, they employ an artificial bee colony to find the chief features. Further, these main features are analyzed using rough set generating rules. The proposed model indeed helps to diagnose a disease carefully. An empirical analysis is carried out on hepatitis dataset. In addition, a comparative study is also presented. The analysis shows the viability of the proposed model.
{"title":"Knowledge Inferencing Using Artificial Bee Colony and Rough Set for Diagnosis of Hepatitis Disease","authors":"P. KauserAhmed, D. Acharjya","doi":"10.4018/ijhisi.20210401.oa3","DOIUrl":"https://doi.org/10.4018/ijhisi.20210401.oa3","url":null,"abstract":"Vast volumes of raw data are generated from the digital world each day. Acquiring useful information and chief features from this data is challenging, and it has become a prime area of current research. Another crucial area is knowledge inferencing. Much research has been carried out in both directions. Swarm intelligence is used for feature selection whereas for knowledge inferencing either fuzzy or rough computing is widely used. Hybridization of intelligent and swarm intelligence techniques are booming recently. In this research work, the authors hybridize both artificial bee colony and rough set. At the initial phase, they employ an artificial bee colony to find the chief features. Further, these main features are analyzed using rough set generating rules. The proposed model indeed helps to diagnose a disease carefully. An empirical analysis is carried out on hepatitis dataset. In addition, a comparative study is also presented. The analysis shows the viability of the proposed model.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121067793","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}
Pub Date : 2021-04-01DOI: 10.4018/ijhisi.20210401.oa5
Ksit Bengaluru Vijayalaxmi Mekali, India Girijamma
Early detection of all types of lung nodules with different characters in medical modality images using computer-aided detection is the best acceptable remedy to save the lives of lung cancer sufferers. But accuracy of different types of nodule detection rates is based on chosen segmented procedures for parenchyma and nodules. Separation of pleural from juxta-pleural nodules (JPNs) is difficult as intensity of pleural and attached nodule is similar. This research paper proposes a fully automated method to detect and segment JPNs. In the proposed method, lung parenchyma is segmented using iterative thresholding algorithm. To improve the nodules detection rate separation of connected lung lobes, an algorithm is proposed to separate connected left and right lung lobes. The new method segments JPNs based on lung boundary pixels extraction, concave points extraction, and separation of attached pleural from nodule. Validation of the proposed method was performed on LIDC-CT images. The experimental result confirms that the developed method segments the JPNs with less computational time and high accuracy.
{"title":"Fully Automatic Detection and Segmentation Approach for Juxta-Pleural Nodules From CT Images","authors":"Ksit Bengaluru Vijayalaxmi Mekali, India Girijamma","doi":"10.4018/ijhisi.20210401.oa5","DOIUrl":"https://doi.org/10.4018/ijhisi.20210401.oa5","url":null,"abstract":"Early detection of all types of lung nodules with different characters in medical modality images using computer-aided detection is the best acceptable remedy to save the lives of lung cancer sufferers. But accuracy of different types of nodule detection rates is based on chosen segmented procedures for parenchyma and nodules. Separation of pleural from juxta-pleural nodules (JPNs) is difficult as intensity of pleural and attached nodule is similar. This research paper proposes a fully automated method to detect and segment JPNs. In the proposed method, lung parenchyma is segmented using iterative thresholding algorithm. To improve the nodules detection rate separation of connected lung lobes, an algorithm is proposed to separate connected left and right lung lobes. The new method segments JPNs based on lung boundary pixels extraction, concave points extraction, and separation of attached pleural from nodule. Validation of the proposed method was performed on LIDC-CT images. The experimental result confirms that the developed method segments the JPNs with less computational time and high accuracy.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124618260","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}
Pub Date : 2021-01-01DOI: 10.4018/ijhisi.2021010101
S. Walczak, Emad Mikhail
This chapter explores valuating the efficacy of using artificial neural networks (ANNs) for predicting the estimated blood loss (EBL) and also transfusion requirements of myomectomy patients. All 146 myomectomy surgeries performed over a 6-year period from a single site are captured. Records were removed for various reasons, leaving 96 cases. Backpropagation and radial basis function ANN models were developed to predict EBL and perioperative transfusion needs along with a regression model. The single hidden layer backpropagation ANN models performed the best for both prediction problems. EBL was predicted on average within 127.33 ml of measured blood loss, and transfusions were predicted with 71.4% sensitivity and 85.4% specificity. A combined ANN ensemble model using the output of the EBL ANN as an input variable to the transfusion prediction ANN was developed and resulted in 100% sensitivity and 62.9% specificity. The preoperative identification of large EBL or transfusion need can assist caregivers in better planning for possible post-operative morbidity and mortality.
{"title":"Predicting Estimated Blood Loss and Transfusions in Gynecologic Surgery Using Artificial Neural Networks","authors":"S. Walczak, Emad Mikhail","doi":"10.4018/ijhisi.2021010101","DOIUrl":"https://doi.org/10.4018/ijhisi.2021010101","url":null,"abstract":"This chapter explores valuating the efficacy of using artificial neural networks (ANNs) for predicting the estimated blood loss (EBL) and also transfusion requirements of myomectomy patients. All 146 myomectomy surgeries performed over a 6-year period from a single site are captured. Records were removed for various reasons, leaving 96 cases. Backpropagation and radial basis function ANN models were developed to predict EBL and perioperative transfusion needs along with a regression model. The single hidden layer backpropagation ANN models performed the best for both prediction problems. EBL was predicted on average within 127.33 ml of measured blood loss, and transfusions were predicted with 71.4% sensitivity and 85.4% specificity. A combined ANN ensemble model using the output of the EBL ANN as an input variable to the transfusion prediction ANN was developed and resulted in 100% sensitivity and 62.9% specificity. The preoperative identification of large EBL or transfusion need can assist caregivers in better planning for possible post-operative morbidity and mortality.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133217651","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}
Pub Date : 2020-10-01DOI: 10.4018/IJHISI.2020100104
L. Fabisiak, Karina Szczypor-Piasecka
Patients with advanced hip osteoarthritis are likely to suffer from biomechanical disorders. As many criteria inform how such patients are being qualified for alloplasty procedures, this article proposes a multi-criteria decisional framework in qualifying patients for treatment while undergoing diagnostic analysis for hip replacement surgery. In order to assess the patient's health condition, the competence of physicians and physiotherapists must first be checked. After creating the expert preference model and decision tree, the AHP method was applied followed by the Electre Tri method in the next stage of verification. Integrating these analytic procedures, a group of patients can be quickly evaluated and meaningfully profiled. Specifically, these patients can be classified in respect of their condition determined during hospitalisation as per the severity of degenerative disease and on the basis of their subjective feelings and diagnostics. The proposed methodology promises to allow optimal treatment to be assigned while enabling the appropriate classification and verification within group of patients targeted for hip replacement surgery.
{"title":"Diagnostic Analysis of Patients Qualified for Hip Replacement Using Multi-Criteria Methods: Clinical Decision Support System","authors":"L. Fabisiak, Karina Szczypor-Piasecka","doi":"10.4018/IJHISI.2020100104","DOIUrl":"https://doi.org/10.4018/IJHISI.2020100104","url":null,"abstract":"Patients with advanced hip osteoarthritis are likely to suffer from biomechanical disorders. As many criteria inform how such patients are being qualified for alloplasty procedures, this article proposes a multi-criteria decisional framework in qualifying patients for treatment while undergoing diagnostic analysis for hip replacement surgery. In order to assess the patient's health condition, the competence of physicians and physiotherapists must first be checked. After creating the expert preference model and decision tree, the AHP method was applied followed by the Electre Tri method in the next stage of verification. Integrating these analytic procedures, a group of patients can be quickly evaluated and meaningfully profiled. Specifically, these patients can be classified in respect of their condition determined during hospitalisation as per the severity of degenerative disease and on the basis of their subjective feelings and diagnostics. The proposed methodology promises to allow optimal treatment to be assigned while enabling the appropriate classification and verification within group of patients targeted for hip replacement surgery.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129743603","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}
Pub Date : 2020-10-01DOI: 10.4018/IJHISI.2020100105
Joseph Kasten
Blockchain, since its 2008 conceptual inception, has largely been contextualized in crypto currencies. Today, blockchain technology has matured to a level that allows the exploration of its application to other and diverse domains, including the management of cancer registries. When collecting and handling data relating to cancer diagnosis and treatment as mandated by law in many municipalities, the process is both time-consuming and requires significant coordination among multiple levels of data collecting jurisdictions. This often leads to inconsistent data vis-à-vis the various levels of data storage. This paper calls for using a blockchain-based mechanism to alert the data users on possible inconsistencies prior to applying the collected data in cancer research. A system framework drawing on the design science research methodology is found to result in increased data quality so as to improve cancer research outcome accuracies.
{"title":"Blockchain Application to the Cancer Registry Database","authors":"Joseph Kasten","doi":"10.4018/IJHISI.2020100105","DOIUrl":"https://doi.org/10.4018/IJHISI.2020100105","url":null,"abstract":"Blockchain, since its 2008 conceptual inception, has largely been contextualized in crypto currencies. Today, blockchain technology has matured to a level that allows the exploration of its application to other and diverse domains, including the management of cancer registries. When collecting and handling data relating to cancer diagnosis and treatment as mandated by law in many municipalities, the process is both time-consuming and requires significant coordination among multiple levels of data collecting jurisdictions. This often leads to inconsistent data vis-à-vis the various levels of data storage. This paper calls for using a blockchain-based mechanism to alert the data users on possible inconsistencies prior to applying the collected data in cancer research. A system framework drawing on the design science research methodology is found to result in increased data quality so as to improve cancer research outcome accuracies.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128519656","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}
Pub Date : 2020-10-01DOI: 10.4018/IJHISI.2020100103
Kai-Xiang Zhuang, I-Ching Hsu
Globally, aging is now a societal trend and challenge in many developed and developing countries. A key medical strategy that a fast-paced aging society must consider is the provision of quality long-term care (LTC) services. Even so, the lack of LTC caregivers is a persistent global problem. Herein, attention is called to the increasing need for identifying appropriate LTC caregivers and delivering client-specific LTC services to the elderly via emerging and integrative technologies. This paper argues for the use of an intelligent cloud computing long-term care platform (ICCLCP) that integrates statistical analysis, machine learning, and Semantic Web technologies into a cloud-computing environment to facilitate LTC services delivery. The Term frequency-inverse document frequency is a numerical statistic adopted to automatically assess the professionalism of each LTC caregiver's services. The machine learning method adopts naïve Bayes classifier to estimate the LTC services needed for the elderly. These two items of LTC information are integrated with the Semantic Web to provide an intelligent LTC framework. The deployed ICCLCP will then aid the elderly in the recommendation of LTC caregivers, thereby making the best use of available resources for LTC services.
{"title":"Knowledge Fusion Based on Cloud Computing Environment for Long-Term Care","authors":"Kai-Xiang Zhuang, I-Ching Hsu","doi":"10.4018/IJHISI.2020100103","DOIUrl":"https://doi.org/10.4018/IJHISI.2020100103","url":null,"abstract":"Globally, aging is now a societal trend and challenge in many developed and developing countries. A key medical strategy that a fast-paced aging society must consider is the provision of quality long-term care (LTC) services. Even so, the lack of LTC caregivers is a persistent global problem. Herein, attention is called to the increasing need for identifying appropriate LTC caregivers and delivering client-specific LTC services to the elderly via emerging and integrative technologies. This paper argues for the use of an intelligent cloud computing long-term care platform (ICCLCP) that integrates statistical analysis, machine learning, and Semantic Web technologies into a cloud-computing environment to facilitate LTC services delivery. The Term frequency-inverse document frequency is a numerical statistic adopted to automatically assess the professionalism of each LTC caregiver's services. The machine learning method adopts naïve Bayes classifier to estimate the LTC services needed for the elderly. These two items of LTC information are integrated with the Semantic Web to provide an intelligent LTC framework. The deployed ICCLCP will then aid the elderly in the recommendation of LTC caregivers, thereby making the best use of available resources for LTC services.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121019925","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}
Pub Date : 2020-10-01DOI: 10.4018/IJHISI.2020100102
Daniel M. Sousa, André Vasconcelos
A no-show occurs when a client has an appointment of some sort with another entity, and voluntarily or not, the client does not show up to that appointment. A patient missing an appointment will mean that the clinic's and health professional's time slot will be wasted. The goal of this research is to find a solution that minimizes no-shows, detecting when a patient is not going to come to the appointment and finding an appropriate replacement. The authors propose a hybrid solution which combines two different behavior prediction techniques: population-based behavior and individual-based behavior. The algorithm starts by computing a no-show probability based on the population's behavior using a logistic regression model. After that, using Bayesian inference, that probability is personalized for each patient. After computing the no-show probabilities for every candidate patient, the algorithm checks if any of them are interested on taking the appointment. The proposed algorithm was assessed using lab data and healthcare provider data.
{"title":"Last Minute Medical Appointments No-Show Management","authors":"Daniel M. Sousa, André Vasconcelos","doi":"10.4018/IJHISI.2020100102","DOIUrl":"https://doi.org/10.4018/IJHISI.2020100102","url":null,"abstract":"A no-show occurs when a client has an appointment of some sort with another entity, and voluntarily or not, the client does not show up to that appointment. A patient missing an appointment will mean that the clinic's and health professional's time slot will be wasted. The goal of this research is to find a solution that minimizes no-shows, detecting when a patient is not going to come to the appointment and finding an appropriate replacement. The authors propose a hybrid solution which combines two different behavior prediction techniques: population-based behavior and individual-based behavior. The algorithm starts by computing a no-show probability based on the population's behavior using a logistic regression model. After that, using Bayesian inference, that probability is personalized for each patient. After computing the no-show probabilities for every candidate patient, the algorithm checks if any of them are interested on taking the appointment. The proposed algorithm was assessed using lab data and healthcare provider data.","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346430","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}
Pub Date : 2020-10-01DOI: 10.4018/IJHISI.2020100101
Haijing Hao, S. Levkoff, Weiguang Wang, Qiyi Zhang, Hongtu Chen, Dan Zhu
{"title":"Studying Online Support for Caregivers of Patients With Alzheimer's Disease in China: A Text-Mining Approach to Online Forum in China","authors":"Haijing Hao, S. Levkoff, Weiguang Wang, Qiyi Zhang, Hongtu Chen, Dan Zhu","doi":"10.4018/IJHISI.2020100101","DOIUrl":"https://doi.org/10.4018/IJHISI.2020100101","url":null,"abstract":"<jats:p />","PeriodicalId":101861,"journal":{"name":"Int. J. Heal. Inf. Syst. Informatics","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129482056","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：