Published on in Vol 22, No 2 (2020): February

Preprints (earlier versions) of this paper are available at, first published .
Tracking Knowledge Evolution in Cloud Health Care Research: Knowledge Map and Common Word Analysis

Tracking Knowledge Evolution in Cloud Health Care Research: Knowledge Map and Common Word Analysis

Tracking Knowledge Evolution in Cloud Health Care Research: Knowledge Map and Common Word Analysis

Original Paper

1The School of Management, Hefei University of Technology, Hefei, China

2The Seidman College of Business, Grand Valley State University, Grand Rapids, MI, United States

3The 1st Affiliated Hospital, Anhui University of Traditional Chinese Medicine, Hefei, China

4College of Business Administration, Central Michigan University, Mount Pleasant, MI, United States

Corresponding Author:

Xuejie Yang, PhD

The School of Management

Hefei University of Technology

193 Tunxi Road

Hefei, 230009


Phone: 86 17344097960


Background: With the continuous development of the internet and the explosive growth in data, big data technology has emerged. With its ongoing development and application, cloud computing technology provides better data storage and analysis. The development of cloud health care provides a more convenient and effective solution for health. Studying the evolution of knowledge and research hotspots in the field of cloud health care is increasingly important for medical informatics. Scholars in the medical informatics community need to understand the extent of the evolution of and possible trends in cloud health care research to inform their future research.

Objective: Drawing on the cloud health care literature, this study aimed to describe the development and evolution of research themes in cloud health care through a knowledge map and common word analysis.

Methods: A total of 2878 articles about cloud health care was retrieved from the Web of Science database. We used cybermetrics to analyze and visualize the keywords in these articles. We created a knowledge map to show the evolution of cloud health care research. We used co-word analysis to identify the hotspots and their evolution in cloud health care research.

Results: The evolution and development of cloud health care services are described. In 2007-2009 (Phase I), most scholars used cloud computing in the medical field mainly to reduce costs, and grid computing and cloud computing were the primary technologies. In 2010-2012 (Phase II), the security of cloud systems became of interest to scholars. In 2013-2015 (Phase III), medical informatization enabled big data for health services. In 2016-2017 (Phase IV), machine learning and mobile technologies were introduced to the medical field.

Conclusions: Cloud health care research has been rapidly developing worldwide, and technologies used in cloud health research are simultaneously diverging and becoming smarter. Cloud–based mobile health, cloud–based smart health, and the security of cloud health data and systems are three possible trends in the future development of the cloud health care field.

J Med Internet Res 2020;22(2):e15142



“Cloud” is a metaphor for the internet in the information age. Through a computer network, cloud computing provides scalable, distributed computing solutions that greatly alleviate problems related with a lack of computing power in various fields [1]. Largely considered as the next revolution in information technology (IT), cloud computing has become one of the most researched topics among IT scholars since 2007. The concept of cloud computing was introduced to the IT research community in China in 2008, after which it quickly became popular. The nation’s Twelfth Five-Year Plan recognized cloud computing’s strategic position in the IT industry [2]. In the meantime, major internet companies such as Google, IBM, Amazon, and Microsoft have invested considerable resources to develop and promote their cloud computing services. Driven by both national policies and industry advances, scientific research on cloud computing has experienced tremendous growth. The number of scientific articles related to cloud computing has increased from 982 in 2007 to more than 20,000 as of December 2017 (based on the Web of Science database). In addition to the development of technology, the idea of “cloud” has been applied to a variety of applications such as cloud health care, cloud education, and cloud life.

In the area of health care, cloud computing has played an increasingly important role in providing storage and computing power for the massive volumes of data [3]. In the age of big data, the development of the Internet of Things (IoT) and sensor networks has spurred the growth of medical and health data. At the same time, IT has been universally used to support diagnosis as well as medical and health information management thanks to its potential strategic and financial impacts. In this trend, a new application of cloud computing in health care has been created and given the name “cloud health care.” Cloud health care refers to health services that improve the delivery of diagnosis and treatment by more efficiently utilizing medical resources through technologies such as cloud computing and IoT [4].

Researchers and practitioners worldwide have extensively explored cloud health care. There are many studies in health care that are based on cloud computing. For example, He et al [5] developed a robust, reliable, and efficient cloud platform architecture. It can meet a high number of concurrent requests from ubiquitous health care services because of the pervasive and on-demand, service-oriented nature of cloud computing. Wang et al [6] designed and evaluated a mobile health information system based on cloud computing and wireless sensor networks; they adopted the gray theory and Markov model to predict the moving path of objects jointly. Fong and Chung [7] suggested the use of mobile cloud computing for a health care system. Mobile devices were used as terminals that allowed medical professionals and family members to easily access medical data. Antypas et al [8] showed a positive effect of an internet- and mobile phone–targeted intervention on physical activity for patients with cardiovascular disease. Cheung [9] analyzed data from patients who participated in the National Health and Nutrition Survey via mobile medical testing centers. In July 2011, Zhongxing Telecommunication Equipment Corporation, a leading Chinese telecommunication company, launched the Healthy Cloud Healthcare program. It uses wireless medical equipment to collect human health data in real time and uploads the data to the cloud service system. The system can maintain electronic medical records for individuals. Users can access data through mobile wireless devices such as mobile phones. In this way, they can not only understand their health conditions at any time and from any location but also maintain timely interactions with their physicians through the platform.

Despite the abundant body of literature on cloud health care, little effort has been made to curate and refine the knowledge from the literature. First, there is a lack of understanding of the evolution of global knowledge on cloud health care. Second, research hotspots in cloud health care have not been identified. Third, the future trends in cloud health care are not understood. After a decade of exploration, it is important to understand the current status of cloud health care research and how it will develop in the future. Therefore, drawing on the cloud health care literature, this study aimed to identify the development and evolution of research themes in cloud health care through a knowledge map and common word analysis.

This article contributes to the cloud computing medical research community by summarizing research achievements and identifying new frontiers of research. Literature about science and technology represents one of the most comprehensive and concrete manifestations of scientific research results. It is an important tool for researchers to exchange ideas and communicate research findings. Electronic journal databases have made it possible and convenient to find and collect a large amount of literature [10]. In-depth analysis of science and technology literature is a common approach to understanding the state of research in a field. Both quantitative and qualitative analyses of the literature in the field of cloud health care can help describe the discipline’s research status and accomplishments, help researchers understand the extent of research development in cloud health care to inform future studies, and provide an important reference for further contributions to the field. From a practical point of view, these analyses also support health care practitioners in translating research findings into industry solutions, potentially reducing medical costs and increasing the utilization of medical resources.

The rest of the paper is organized as follows: presentation of data and research methods and tools; reporting of the findings from the knowledge evolutionary analysis, co-word analysis, and sudden word analysis of the cloud health care literature; and a discussion of the implications to cloud health care research.

Data Collection and Preprocessing

The Web of Science, developed by US Thomson Scientific, includes three cited libraries: Science Citation Index, Social Sciences Citation Index, and Arts & Humanities Citation Index. It also includes two chemical databases: Current Chemical Reactions and Index Chemicus [11]. It contains not only articles published in academic journals but also other types of publications such as conference proceedings and patents. Using the database, one can retrieve relevant literature titles and summaries, the references used in each paper, and the context in which each paper was cited [12].

This study used the following as data sources: Science Citation Index Expanded, Conference Proceedings Citation Index-Science, Current Chemical Reactions Expanded, and Index Chemicus. On August 14, 2017, we retrieved relevant articles published between 2007 and 2017. In this paper, the following two search types were used with the “AND” relationship in the advanced search method: TS = (hospital * OR heart * OR blood * OR disease * OR medical * OR #) (“#” represents the 20 keywords related to the health sector) and TS = (“cloud comput *” OR “SaaS” OR “PaaS” OR “IaaS” OR ##), where “##” represents more than 11 keywords related to cloud computing. The search returned 2878 articles; the types included “proceedings paper,” “article,” and nine other types. According to the search results, articles related to cloud health care were scarce before 2010. At the beginning of 2010, the number of related articles began to rapidly increase. By 2016, the number of articles had increased by nearly 10 times that in 2010 (Figure 1). Therefore, cloud health care has become a hot topic in recent years.

To establish a sequential word network, the bibliographic information was divided into four periods: 2007-2009 (Phase I), 2010-2012 (Phase II), 2013-2015 (Phase III), and 2016-2017 (Phase IV). Terms synonymous with different forms of the term were replaced. For example, “Internet of Things” uniformly replaced “IoT” and “internet of things.” Subsequently, a symmetric co-occurrence matrix was generated by counting the co-occurrences of the two keywords. The data in the diagonal cell was treated as the key word frequency, and the value of the non-diagonal cell was the common word frequency [13].

Figure 1. The number of articles related to cloud health care, by year.
View this figure

Data Analysis Methods and Tools

This study used keywords to analyze the relevant research articles about cloud health care. Keywords are the core concepts in the study of natural language forms. Keywords can be used to distinguish the contexts and methods of research articles. Therefore, multiple time series of keywords extracted from research papers in a certain field can reveal the development and trend of research in that field [14]. For statistical modeling and data visualization purposes, we used the Statistical Analysis Toolkit 3.2 (SATI; Liu Qiyuan and Ye Ying, China), Network Evolvement and Trend Detection System 1.5 (NEViewer; Wuhan University, Wuhan, China), UCINET 6.186 [15], Python 2.7 (Amsterdam, Netherlands), and NetDraw 2.084 [16].

To visualize the evolution of keywords in cloud health care, we used NEViewer [17]. The data structure used in NEViewer is a sequential word network. The Python program was used to store the co-word network of each period as an nwb format file, and thematic evolution was probed after loading the file in NEViewer. NEViewer shows the macroscopic evolutionary process and microscopic evolution details of the online community in a novel way using an alluvial graph and a color rendering network diagram, which is used by many scholars.

In this study, we used SATI to extract keywords and get a 100-by-100 co-occurrence matrix of high-frequency words in each phase. The co-occurrence matrix was ​​the basis for further analysis. SATI is an article title statistical analysis tool with four functions: title format conversion, field information extraction, entry frequency statistics, and knowledge matrix construction [18]. Subsequently, we used UCINET and NetDraw to draw and analyze keyword co-occurrences. UCINET is a powerful social networking analytics software that does not include graphical visualization but allows data to be exported and processed to software such as NetDraw, Pajek, Mage, and KrackPlot [19]. UCINET can handle the raw data matrix format. Therefore, the co-occurrence matrix was ​​generated based on SATI 3.2. Then, the co-occurrence matrix was ​​introduced into UCINET for analysis. Finally, we used NetDraw to produce a knowledge map to visualize the interrelationship of the keywords, making it easy to learn and analyze.

Knowledge Evolution Analysis

NEViewer functions include topic clustering and community division. It can be applied to the analysis of evolutionary processes of many complex networks such as social network evolution, knowledge network evolution, enterprise network evolution, and human network evolution. The processed file was imported into NEViewer for Blondel community detection processing, and the evolving situation of foreign hotspot communities in various periods is shown in Figure 2. The rectangular color block represents the community, the curved color patches between the 2 time segments represent the evolution process, and the height of the color patches represents the community node size [20]. Using these theme communities, we can visualize the evolution of hotspots, show the hotspots, and show the changing themes in cloud health care research.

Figure 2 shows the 4 major hotspot communities categorized by the 4 phases. It also shows a map of changes and the evolution of the hotspot communities. The rectangular color block area indicates the criticality of the elements it contains and the amount of research performed about the subjects in the community; a larger area signifies greater criticality and more research. In Phase I, the top 5 keywords ranked by community size were “Cloud Computing,” “software as a service (SaaS),” “Sustainability,” “Cloud,” and “mining.” In Phase II, the top 5 keywords were “Cloud Computing,” “Cloud,” “SaaS,” “Digital Imaging and Communications in Medicine (DICOM),” and “Internet.” In Phase III, the top 5 keywords, from highest to lowest in terms of community size, were “Cloud Computing,” “Cloud,” “Security,” “Mobile health,” and “mobile.” In Phase IV, the top 5 keywords ranked by community size were “Cloud Computing,” “Cloud,” “Security,” “Hadoop,” and “Analytics.”

The evolution of the knowledge network includes the generation, disappearance, division, and merger of knowledge. The evolutionary manifold of NEViewer can vividly show the process of extinction, differentiation, and integration of hotspot community evolution. Using “Cloud Computing” as an example, from Phase I to Phase II, “mining” differentiated into “Cloud Computing” and “Internet.” From Phase II to Phase III, “Cloud Computing” differentiated into “Security” and “Mobile health.” Mobile health became a new research hotspot in Phase III. From Phase III to Phase IV, “Cloud Computing” differentiated into “Cloud” and “Security” as well as “Hadoop” and “Analytics,” among others. This shows that the research scope of cloud computing in the medical field is constantly expanding and deepening. Meanwhile, “Mobile health” merged with “Cloud Computing” and “Cloud.” In addition, from Phase I to Phase II, “Cloud Computing” differentiated into “Internet of Things” and “mobile cloud computing.” From Phase II to Phase III, “Internet of Things” merged with “mobile.” From Phase III to Phase IV, “mobile” merged again with “Cloud Computing.” Therefore, the evolution and development of the cloud health care field was firmly centered on cloud computing.

Figure 2. Cloud health care knowledge evolution map.
View this figure

Co-Word Analysis

As a refined way to express a subject in academic publications, the correlation between keywords can reveal the inherent relationship of knowledge in the academic field, to a certain extent. Co-word analysis is similar to co-citation or co-occurrence analysis [21] and is considered a reasonable method to describe the relationship between concepts, perspectives, and problems [22]. In co-word analysis, it is assumed that the keywords extracted from an article can represent a specific research direction, research topic, or topic of a field. If two keywords appear together in one article, then the two topics they represent are related. The higher the co-word frequency, the stronger the relationship between keywords, which further indicates that the two keywords are related to a specific research topic [23].

We constructed co-word matrices by keywords and their co-occurrence relationships and then mapped them to a co-word network. The distance between the nodes in the network reflects the relationship between the topic content. The co-word network, when combined with time, can reflect the evolutionary trend of the scientific literature and the development process of the entire discipline. The co-occurrence and evolution analyses of the keywords can highlight updates in scientific research topics and capture the patterns of knowledge production.

Co-word analysis has been applied in various fields of research. This paper explores the main research directions and hotspots in the cloud health care field in the four phases from 2007 to 2017 through common word analysis and discusses the trends for future development.

Co-Word Analysis for Phase I (2007-2009)

The size of the node characterizes betweenness of the keywords. The larger the nodes, the more the keywords are related to each other and the more likely it is to expand to the keywords of other research topics [24]. As shown in Table 1 and Figure 3, “Cloud Computing,” “SaaS,” and “grid computing” had significantly strong betweenness in Phase I. In addition to “Cloud Computing,” “grid computing” primarily linked the cloud and medical research community. Currently, grid computing technology provides a just-in-time service for users by sharing and collaborating on all the resources (ie, computing, storage, communications, information resources, and knowledge resources) on the internet [25]. In addition, “telemedicine” had a strong central agency. It shows that telemedicine first appeared in the field of cloud health care treatment as a type of medical technology. Telemedicine is a medical technology that integrates medicine, computer technology, and communication technology. In 2006, the United Kingdom invested more than 170 million British pounds in telemedicine research [26]. The development of telemedicine marks the convergence of the health care industry and cloud computing. In this phase, the frequencies of co-occurring words are relatively low, which shows that cloud health care treatment was in its infancy.

Watson et al [27] developed a common electronic science platform in the cloud that supports metadata sharing, integration, and analysis. Scientists built on this systematic study to understand how the brain works, an area representing both opportunities and challenges in biology, medicine, and computer science. Sundararaman et al [28] presented a SaaS-based application, Hridaya, that, in conjunction with devices such as personal digital assistants and mobile phones, allows patients to report their health to a doctor on a schedule. Subsequently, doctors can monitor patients to improve recovery and survival. Bauer and Mohtashemi [29] proposed a parallel Monte Carlo model using cloud computing as a method to not only meet real-time monitoring constraints in the medical field but also reduce or eliminate the costs associated with real-time disease monitoring systems. Meir and Rubinsky [30] introduced a new paradigm of medical technologies focusing on wireless technologies and cloud computing that were designed to overcome the growing cost of medical technology. This new paradigm also allows untrained medical staff to perform imaging and generate more accurate diagnoses to more effectively save patients’ lives.

Medical technology is indispensable to modern medicine. However, in the case of an influx of data, it becomes very expensive and complex and therefore inaccessible. Therefore, in Phase I, most scholars applied cloud computing to the medical field mainly to solve high-cost problems. In recent years, cloud computing has accelerated the construction of medical information resources, realized the sharing of information resources, improved the service level of medical institutions, and reduced the cost of building medical information systems.

Table 1. Betweenness of the top 10 keywords in Phase I.
Cloud computing14469
Grid computing2863
Figure 3. Keyword co-occurrence map for 2007-2009.
View this figure

Co-Word Analysis for Phase II (2010-2012)

If a node in a network has strong relationships with other nodes, it has high centrality and is very important in the network. In Phase II, “Cloud Computing” had the highest level of betweenness and occupied an important position, becoming the largest bridge among the other research hotspots. In addition, the levels of betweenness of “Cloud” and “Healthcare” were also strong. The emergence of “Healthcare” shows that the research topics in the field of medicine were extensively explored and that other emerging research points are likely to be expanded through those topics. Studying the high-frequency keywords in a certain field helps to determine the context development, hotspots, and trends. As shown in Table 2 and Figure 4, “Cloud Computing” had a high frequency, one that was far greater than that of the other popular keywords “Healthcare,” “Security,” “Cloud,” “SaaS,” and “Personal Health Record.”

Table 2. Betweenness of the top 15 keywords in Phase II.
Cloud computing3462144
Personal health record419
High-performance computing233
Figure 4. Keyword co-occurrence map for 2010-2012.
View this figure

During this period, radiology led the promotion of technology development, such as cloud computing, in the medical field, which might be attributed to the relatively rich IT-related knowledge of radiologists. Krestin et al [31] reported that radiologists were the first to promote integrated diagnostics through IT solutions and cloud computing. Satoh et al [32] developed a new remote radiology network system based on information security solutions to improve the speed and accuracy of diagnoses and to enhance the protection of personal information. Koufi et al [33] embedded context-aware access control into eRadiology workflows and worked with personal health record systems that were already implemented in cloud computing infrastructures. The resulting security system ensured precise and tight access control.

In view of this, compared with Phase I, in which scholars focused on expanding data volumes and high costs using grid computing, cloud computing, and other technologies, Phase II saw scholars paying attention to system security issues. Implementing cloud computing in the day-to-day medical operations has many benefits. However, health care organizations and employees have encountered resistance to this modern technology due to patient data privacy and security issues. To take full advantage of the power of cloud computing, comprehensive and secure solutions for cloud processing are needed. Nguyen et al [34] introduced a cloud service system model and a security mechanism based on key management with secure multicast. Feldman et al [35] designed and developed a novel method to protect personal medical information in a remote and physically unsustainable environment.

Co-Word Analysis for Phase III (2013-2015)

In Phase III, “Cloud Computing” had the strongest betweenness, followed by “Cloud,” “Healthcare,” “Internet of Things,” “big data,” “Security,” and “eHealth.” As shown in Figure 5, the betweenness of “Cloud Computing” remained at the top of the list. However, its drop from the previous higher ranking might be related to the emergence of bridges such as “Internet of Things” and “big data” in this phase, which weakened the role of “Cloud computing” as a liaison.

Figure 5. Keyword co-occurrence map for 2013-2015.
View this figure

With the rapid development of computer science and IT, health care informatization has been widely implemented, generating massive volumes of data in health care and health management. The development and application of big data in health care play an important role in promoting medical and health services and the development of healthy industries [36]. In the era of big data, cloud computing is the core of IoT. At the same time, it can promote the intelligent convergence of the IoT and the internet. IoT refers to an open and comprehensive network of intelligent objects that have the capacity to auto-organize; share information, data, and resources; and react and act to situations and changes in the environment [37]. It was estimated that 1 billion devices would be connected to the internet by 2020 [38]. In the field of health care, IoT has played an increasingly important role and is widely used [39]. A wide range of applications have been developed based on the IoT. Cubo et al [40] designed and implemented a cloud–based IoT platform to help health care professionals seamlessly monitor the health of many patients and data in real-time. From the perspective of health care systems engineering, Fernandez and Pallis [41] analyzed the opportunities for and challenges of one health IoT platform to strengthen its medical services, clinical care, and remote monitoring. Skraba et al [42] developed a prototype speech-controlled, cloud-based wheelchair platform for disabled persons.

More specifically, scholars have proposed algorithms and architectures to address efficiency and security issues. Nakagawa et al [43] proposed m-cloud, a distributed computing mechanism with multiple cloud resources. It not only increases resiliency, scalability, and efficiency but also reduces the risk of revealing private information. Kim [44] proposed a polynomial-time algorithm to download energy-saving dynamic packets from medical cloud storage to medical IoT equipment. Suciu et al [45] proposed an architecture for eHealth applications that integrate big data, IoT, and the cloud. Mital et al [46] developed a framework of cloud computing–based smart community services and the emerging cloud computing ecosystems. This research has wide-ranging implications on the future of the IoT and can be extended to elderly health and support, energy-efficient systems, and smart cities. In the future, smart cities, smart homes, wearables, and mobile computing will become frontiers in the development of the IoT [47].

eHealth is an emerging area at the intersection of medical informatics, public health, and commerce. It involves health services and information provided or enhanced through the internet and related technologies. With the rapid development in such fields as cloud computing and big data, more extensive research attention will occur for eHealth. At present, the widespread application of electronic health records has led to the rapid accumulation of medical data. Big data analytics can extract this knowledge to improve the quality of health care, which is also an important reason for the rise of “big data” as a keyword in the co-word network [48]. In addition, since the emergence of “Security” in Phase II, it has received sustained attention from scholars. With the continuing popularization of cloud computing, the importance of security is attracting more attention. Especially in the medical field, security has also become the most important concern for patients.

Table 3 lists the top 15 keywords and their characteristics in Phase III. The high-frequency keywords included “Cloud Computing,” “Cloud,” “Healthcare,” “Internet of Things,” “Security,” “big data,” and “eHealth”. These keywords represent hotspots in the cloud computing and medical areas. Compared with previous periods, the frequency of keywords greatly increased, demonstrating that scholars gradually increased and deepened their research on cloud health care services during this period.

Table 3. Betweenness of the top 15 keywords in Phase III.
Cloud computing1921447
Internet of Things24767
Big data14058
Personal health record2428
Mobile cloud computing2423

Co-Word Analysis for Phase IV (2016-2017)

As shown in Table 4 and Figure 6, in Phase IV, the most betweenness centralities were “Cloud Computing,” “Cloud,” “Internet of Things,” “Healthcare,” “big data,” “eHealth,” “computing,” “Security,” and “machine learning.” Compared with Phase III, “Internet of Things,” “big data,” and “eHealth” increased as keywords, and “machine learning,” “mobile,” and “Mobile health” emerged as hotspots.

In this phase, machine learning gradually drew health care scholars’ attention. As an example, natural language processing has been used to structure electronic health records [49]. Classification and prediction methods have also been used for computer-aided diagnosis. Santillana et al [50] proposed a machine learning model for real-time influenza estimation. Gupta et al [51] assembled three models of Naive Bayes, AdaBoost, and boosted tree methods to improve the accuracy of heart disease prediction. Gu et al [52] presented a case-based reasoning system for breast cancer–related diagnoses. In addition, algorithms such as decision trees and neural networks are used for image classification and disease classification [53,54]. We summarized the relevant literature in Table 5. Machine learning algorithms have been widely used in the medical field during Phase IV. However, from the perspective of efficiency, the algorithm accuracy needs improvement. In the future, suitable machine learning methods will be used to increase efficiency.

Table 4. Betweenness of the top 15 keywords in Phase IV.
Cloud computing2167252
Internet of Things31377
Big data20652
Machine learning8714
Electronic health record7113
Mobile health2615
Figure 6. Keyword co-occurrence map for 2016-2017.
View this figure
Table 5. Summary of the relevant literature regarding machine learning in cloud health care.
To introduce a double-reading entry system for extracting clinical data from unstructured medical records and creating a semistructured electronic health record databaseNatural language processingThis reproducibility study with magnetic resonance images from 100 patients had an overall high reproducibility of 98%.Luo et al [49]
To build a machine learning model named AutoRegressive Electronic Health Record Support Vector Machine (ARES) to provide real-time influenza estimatesSupport vector machineARES can estimate national influenza-like illness activity with an almost tenfold reduction in the average error.Santillana et al [50]
To provide a practical, comprehensive workflow for typical machine learning problems seen in medical image analysisBinary classification, multi-class learning, regressionThe benchmark was conducted on 14 public data sets and 4 local medical image data sets using a single common flow. It ensured better (similar to 8% improvement) or at least similar generalization capability with respect to existing methods.Roychowdhury et al [52]
To find optimal image-based feature sets that reduce computational time complexity while maximizing overall classification accuracyDecision treeIt significantly enhanced the borderline classification performances in automated screening systems.Roychowdhury et al [53]
To distinguish between the gait features of a person with Friedreich\'s ataxia and a person with healthy gait characteristicsNeural network (multilayer perception)A considerable degree of classification accuracy was achieved. The attributes of the gyroscope signals (roll and yaw) attained classification accuracies of 74% and 63%, respectively.LeMoyne et al [54]
To predict heart diseaseNaive Bayes, AdaBoost, boosted treeThe assembled model increased the overall accuracy to 87.91%.Gupta et al [51]

In Europe, the United States, and other countries, the mobile health business has moved into the service phase. For example, portable sensing terminals that measure parameters such as electrocardiograms, blood glucose levels, and blood pressure have provided convenient methods for both doctors and patients. With the rise of the mobile internet, medical health applications such as Chunyu Doctor, Baidu, and Pomelo are increasingly used by the general public. As a result, mobile health and mobile medical services have become hotspots among scholars worldwide. Witbrodt and Sunderam [55] proposed a patient-centric mobile medical cloud platform for real-time data collection and monitoring. They also proposed a cloud storage solution for mobile data flows. The acquisition of modern medical information, especially in rural areas of developing countries, is crucial for effective health care. For instance, Miah et al [56] designed and evaluated an innovative mobile decision support system to address such issues as health decision support and information dissemination for farmers.

To further understand the research hotspots throughout all the studied years, we analyzed and summarized the keywords of 2007-2017. Table 6 provides the overall distribution of the co-occurrence of the keywords through the central table of intermediaries. The top 5 keywords in the intermediary were “Cloud Computing,” “Cloud,” “Healthcare,” “Internet of Things,” and “Security.” This is largely consistent with the popular words in recent years. Table 7 summarizes the keywords and main findings of each phase.

Table 6. Betweenness of the top 15 keywords in 2007-2017.
Cloud Computing1127852
Internet of Things236148
Big data145111
Mobile cloud computing7939
Electronic health record5344
Table 7. Keywords and main findings of each phase.
I (2007-2009)Cloud Computing, SaaS, grid computing, Sustainability, Cloud, telemedicine, service, mining, scheduling, computingMost scholars applied cloud computing to the medical field mainly to reduce cost, and most of the technologies were based on grid computing and cloud computing.
II (2010-2012)Cloud Computing, Healthcare, Cloud, docking, radiology, Security, SaaS, Personal Health Record, Networks, eHealth, Simulation, telemedicine, Bioinformatics, computing, high-performance computingScholars began to focus on cloud-based security issues, including patient data privacy and security.
III (2013-2015)Cloud Computing, Cloud, Healthcare, Internet of Things, big data, Security, eHealth, computing, telemedicine, privacy, MapReduce, ontology, health, Personal Health Record, mobile cloud computingWith the rapid development of computer science and information technology, health care informatization was widely used. Mass data sets formed big data in health care. The Internet of Things rapidly developed.
IV (2016-2017)Cloud Computing, Cloud, Internet of Things, Healthcare, big data, eHealth, computing, Security, machine learning, Privacy, Electronic health record, mobile, Sensors, Authentication, Mobile healthMachine learning and mobile technology were introduced into the medical field.

Sudden Word Analysis

The identification and tracking of research frontiers can inform researchers of the evolution of research topics, forecast the development of research, and identify problems that need to be further explored [57]. Chen believes that a research frontier is an emerging theoretical trend and research theme that can be expressed by the sudden increase in technical terminology (ie, sudden words) [58]. In this study, the first 100 keywords of each phase were compared. When certain keywords did not exist in the previous phase but appeared in the current phase, they were considered as the emergent words of the current phase. In this study, sudden words were identified using the Python program for Phases II, III, and IV (Table 8).

In Phase II, most of the sudden words were also high-frequency keywords in that period. This indicates rapid development of the cloud health care field during this phase. Emerging keywords such as “Electronic health record,” “Personal Health Record,” and “DICOM” suggest that storage technology was used to solve the problem of data expansion that came with the adoption of personal health records and digital medical images. For example, Fernández-Cardeñosa et al [59] proposed two solutions for electronic health record systems based on cloud computing. Radwan et al [60] also presented a cloud-based platform that provides developers, health care providers, and organizations with a framework for retrieving and managing medical records and personal health records.

Table 8. Sudden words by study phase.
Phase II (2010-2012)Phase III (2013-2015)Phase IV (2016-2017)
Electronic health record10Big data58Machine learning14
Personal health record9Mobile health17Fog computing13
DICOM8Mobile computing16Smart cities8
Virtualization7Ontology14Searchable encryption7
MapReduce6Monitoring13Virtual reality6
e-Health6Data mining13Software6
Medical imaging6Data security11Anonymity6
Interoperability4Cloud platform10Data sharing6
Access control4Mobile cloud10Analytics6
Bioinformatics4Body sensor networks9Privacy preserving5
IaaSc4Optimization9Medical image5
Internet of Things4Analysis9Distributed systems5
Cloud security3Image processing9Biosensors5

aPACS: picture archiving and communication systems.

bPaaS: platform as a service.

cIaaS: infrastructure as a service.

In Phase III, “big data” was the most frequent sudden word. As aforementioned, the use of big data and other technologies increased in the medical industry during this phase. In addition, “Mobile health,” “mobile computing,” and “mobile cloud” started to emerge. Mobile internet is the product of a combination of mobile communications and the internet. Mobile internet technology is a new technology for high-speed wireless connectivity to mobile devices such as laptops, tablets, and smartphones [61]. Since 2010, the mobile internet has started to change people’s lives and behaviors. With the advancement of mobile internet technology, new terms such as mobile computing technology and mobile health have emerged. Mobile health is the use of mobile internet communication technology to provide health care services such as physical examinations, health care, disease assessments, medical treatment, and rehabilitation. Based on this analysis, mobile health is likely to be an ongoing development trend in the medical industry.

In Phase IV, keywords such as “machine learning,” “fog computing,” and “smart cities” started to appear. As already mentioned, in this phase, machine learning began to be of interest to medical scholars. Machine learning technologies provide effective support for medical data mining to improve the efficiency and quality of data recording and application. The concept of fog computing was first proposed in 2011. Fog computing is a distributed computing infrastructure for the IoT that extends computing power and data analytics applications to the “edge of the network.” It enables customers to gain instant insights through connectivity by analyzing and managing data locally. Tayeb et al [62] summarized the latest research on IoT, cloud computing, and fog computing. These technologies are changing the way we live and work. In 2010, IBM formally proposed the vision of a smart city. A smart city uses information and communication technology to sense, analyze, and integrate the core system of urban operations to respond intelligently to various needs and create a better urban life for mankind. Medical services play a crucial role in the transformation from traditional cities to smart cities. Sajjad et al [63] proposed a method of leukocyte classification and segmentation in microblood smears that not only improves diagnostic accuracy and reduces diagnostic time but also promotes the development of resource-conscious health services in smart cities. Smart cities are bound to become the reality of future cities around the world. With the development of smart cities, the emergence of the proprietary medical term, Wise Information Technology of 120, is bound to lead the future development of the medical industry.

In this study, we conducted a bibliometric analysis using NEVeiwer, SATI, UCINET, and NetDraw of 2878 articles collected from the Web of Science database. The results show that the evolution and development of cloud health care services are closely linked with “Cloud Computing.” The primary keywords were “Cloud Computing,” “Cloud,” “Healthcare,” “Internet of Things,” “Security,” “eHealth,” “big data,” “computing,” “Privacy,” and “mobile cloud computing.” Through the keyword analysis, we summarized the major research hotspots and directions in each phase. In Phase I, most scholars used cloud computing mainly to save costs in the medical field, and the technologies in use were primarily grid computing and cloud computing. In Phase II, scholars began to pay attention to the security of cloud systems, including patient data privacy and security issues. In Phase III, health and medical informatization created big data for health and medical services, and the IoT also developed rapidly. In Phase IV, machine learning and mobile technologies were introduced to the medical field. This study provides not only important references to understand the development of science to inform future research and identify research questions in the field in general but also information to guide practitioners in terms of technological changes and developments in the medical industry. While cloud computing, IoT, and big data have become technical hotspots in this field, electronic health, mobile health, and smart health have developed as main branches.

Emerging information technologies can provide technical support and solve many of the current problems faced by the health care industry as medical data become more heterogeneous, big, and noisy. Through the knowledge evolution analysis, keyword co-occurrence analysis, and sudden word analysis, we identified three trends for the future development of the cloud health care field.

First, cloud computing in health care mainly focuses on saving costs and improving computing efficiency. Some scholars have applied distributed storage and computing to health care systems, demonstrating that cloud computing can enhance the performance of health care systems and increase the satisfaction with smart health care applications and services [43,64,65]. The main issues of cloud computing are focused on distributed storage algorithms, resource-indexing techniques in distributed storage, Hadoop–based distributed storage and computing applications, and distributed computing models. In addition, virtualization of the cloud can reduce the management costs of large data centers and internet-based solutions. It also provides complete user flexibility as well as IT management and control capabilities. Optimized scheduling of resources in the cloud, standardization of cloud computing, and cloud computing security will also be widely used in medical service cloud platforms.

Second, the results show that research hotspots such as “Mobile health,” “mobile computing,” and “mobile cloud” emerged in the second phase. Mobile cloud computing is the combination of mobile internet and cloud computing. The mobile applications of today place higher demands on battery capacity, computing power, storage capacity, and mobile terminal security. Therefore, mobile cloud computing has grown rapidly to meet these needs. Mobile cloud computing technology has been used in health applications to address issues such as limited storage and processing capabilities of mobile devices, interoperability, and availability of electronic medical records [66,67]. In addition, accurate positioning and motion recognition technologies and guaranteed consistent, efficient cloud data will become hotspots in the field of mobile health.

Finally, security and privacy issues always accompany data. With the continuing popularization of emerging technologies, security in the medical field has drawn increasing attention. To ensure the security of cloud health data and the system, there are many challenges to overcome, including big data computing ethics, secure computing in a distributed programming framework, trustworthiness in remote data computing, multigranular access control, and trustworthiness of data sources and data channels.

This study has some limitations. Because cloud health care is an emerging field, the amount of data available for retrieval was relatively limited, which might have impacted the analysis. Second, only keyword evolution was analyzed, and we did not consider other aspects of the evolutionary analysis. These should be addressed in future studies.


The dataset collection and analysis of this research were partially supported by the National Natural Science Foundation of China (NSFC) under grant numbers 71771075 and 71771077.

Authors' Contributions

DG conceived and designed the study. XW performed data collection and analysis. XY and JG wrote the first full draft. DG and CL edited and completed the paper. SD and JW reviewed and completed the final edit of the manuscript.

Conflicts of Interest

None declared.

  1. Yan Q, Yu FR. Distributed denial of service attacks in software-defined networking with cloud computing. IEEE Commun. Mag 2015 Apr;53(4):52-59. [CrossRef]
  2. Patel A, Taghavi M, Bakhtiyari K, Júnior J. Taxonomy and proposed architecture of intrusion detection and prevention systems for cloud computing. Cyberspace Safety and Security: Springer; 2012:441-458.
  3. Roy N, Dubey A, Gokhale A. Efficient Autoscaling in the Cloud Using Predictive Models for Workload Forecasting. 2011 Jul Presented at: 2011 IEEE 4th International Conference on Cloud Computing; July 4-9, 2011; United States. [CrossRef]
  4. Haskew J, Rø G, Saito K, Turner K, Odhiambo G, Wamae A, et al. Implementation of a cloud-based electronic medical record for maternal and child health in rural Kenya. Int J Med Inform 2015 May;84(5):349-354. [CrossRef] [Medline]
  5. He C, Fan X, Li Y. Toward Ubiquitous Healthcare Services With a Novel Efficient Cloud Platform. IEEE Trans. Biomed. Eng 2013 Jan;60(1):230-234. [CrossRef]
  6. Wang S, Chen YL, Kuo AM, Chen H, Shiu YS. Design and evaluation of a cloud-based Mobile Health Information Recommendation system on wireless sensor networks. Computers & Electrical Engineering 2016 Jan;49:221-235. [CrossRef]
  7. Fong E, Chung W. Mobile Cloud-Computing-Based Healthcare Service by Noncontact ECG Monitoring. Sensors 2013;13(12):16451-16473. [CrossRef]
  8. Antypas K, Wangberg SC. An Internet- and Mobile-Based Tailored Intervention to Enhance Maintenance of Physical Activity After Cardiac Rehabilitation: Short-Term Results of a Randomized Controlled Trial. J Med Internet Res 2014 Mar 11;16(3):e77. [CrossRef]
  9. Cheung MR. Lack of health insurance increases all cause and all cancer mortality in adults: an analysis of National Health and Nutrition Examination Survey (NHANES III) data. Asian Pac J Cancer Prev 2013 Apr 30;14(4):2259-2263 [FREE Full text] [CrossRef] [Medline]
  10. Herrera M, Roberts DC, Gulbahce N. Mapping the Evolution of Scientific Fields. PLoS ONE 2010 May 4;5(5):e10355. [CrossRef]
  11. No HJ, An Y, Park Y. A structured approach to explore knowledge flows through technology-based business methods by integrating patent citation analysis and text mining. Technological Forecasting and Social Change 2015 Aug;97:181-192. [CrossRef]
  12. Backhaus K, Lügger K, Koch M. The structure and evolution of business-to-business marketing: A citation and co-citation analysis. Industrial Marketing Management 2011 Aug;40(6):940-951. [CrossRef]
  13. Hu C, Hu J, Deng S, Liu Y. A co-word analysis of library and information science in China. Scientometrics 2013 Jul 2;97(2):369-382. [CrossRef]
  14. Whittaker J. Creativity and Conformity in Science: Titles, Keywords and Co-word Analysis. Soc Stud Sci 2016 Jun 29;19(3):473-496. [CrossRef]
  15. Borgatti SP, Everett MG, Freeman LC. Ucinet for Windows: Software for Social Network Analysis. Harvard, MA: Analytic Technologies; 2002.
  16. Borgatti SP. NetDraw Software for Network Visualization. Lexington, KY: Analytic Technologies; 2002.
  17. Altman ER, Govindarajan R, Gao GR. Scheduling and mapping. SIGPLAN Not 1995 Jun 01;30(6):139-150. [CrossRef]
  18. Ying LQY. A Study on Mining Bibliographic Records by Designed Software SATI: Case Study on Library and Information Science J. Journal of Information Resources Management 2012;1:50-58.
  19. Yan GE. The Application of Software UCINET in the Study of University Library's Micro Blog Relationship. Journal of Library & Information Science 2016:3-6.
  20. Wang X, Cheng Q, Lu W. Analyzing evolution of research topics with NEViewer: a new method based on dynamic co-word networks. Scientometrics 2014 Jun 22;101(2):1253-1271. [CrossRef]
  21. Small H. Co-citation in the scientific literature: A new measure of the relationship between two documents. J. Am. Soc. Inf. Sci 1973 Jul;24(4):265-269. [CrossRef]
  22. Callon M, Courtial JP, Laville F. Co-word analysis as a tool for describing the network of interactions between basic and technological research: The case of polymer chemsitry. Scientometrics 1991 Sep;22(1):155-205. [CrossRef]
  23. Cambrosio A, Limoges C, Courtial JP, Laville F. Historical scientometrics? Mapping over 70 years of biological safety research with coword analysis. Scientometrics 1993 Jun;27(2):119-143. [CrossRef]
  24. Gu D, Li J, Li X, Liang C. Visualizing the knowledge structure and evolution of big data research in healthcare informatics. Int J Med Inform 2017 Feb;98:22-32 [FREE Full text] [CrossRef] [Medline]
  25. Foster I, Zhao Y, Raicu I, Lu S. Cloud computing and grid computing 360-degree compared. : IEEE; 2008 Presented at: 2008 Grid Computing Environments Workshop; November 12-16, 2008; Austin, TX. [CrossRef]
  26. Barlow J, Hendy J. Adopting integrated mainstream telecare services. Chronic disease management and remote patient monitoring 2009;15(1):8.
  27. Watson P, Lord P, Gibson F, Periorellis P, Pitsilis G. Cloud Computing for e-Science with CARMEN. In: 2nd Iberian Grid Infrastructure Conference Proceedings. 2008 Presented at: 2nd Iberian Grid Infrastructure Conference Proceedings; May 15, 2008; Porto, Portugal.
  28. Sundararaman K, Parthasarathi J, Rao S, Rao G. Hridaya A tele-medicine initiative for cardiovascular disease through convergence of grid, Web 2.0 and SaaS. : IEEE; 2008 Presented at: 2008 Second International Conference on Pervasive Computing Technologies for Healthcare; Jan 30 - Feb 1, 2008; Tampere, Finland. [CrossRef]
  29. Bauer D, Mohtashemi M. An application of parallel Monte Carlo modeling for real-time disease surveillance. 2008 Presented at: 2008 Winter Simulation Conference; December 7-10, 2008; Miami, FL. [CrossRef]
  30. Meir A, Rubinsky B. Distributed Network, Wireless and Cloud Computing Enabled 3-D Ultrasound; a New Medical Technology Paradigm. PLoS ONE 2009 Nov 19;4(11):e7974. [CrossRef]
  31. Krestin GP, Grenier PA, Hricak H, Jackson VP, Khong PL, Miller JC, et al. Integrated diagnostics: proceedings from the 9th biennial symposium of the International Society for Strategic Studies in Radiology. Eur Radiol 2012 Nov 15;22(11):2283-2294 [FREE Full text] [CrossRef] [Medline]
  32. Satoh H, Niki N, Eguchi K, Ohmatsu H, Kusumoto M, Kaneko M. Teleradiology network system using the web medical image conference system with a new information security solution. In: Proceedings Volume 8319, Medical Imaging 2012: Advanced PACS-based Imaging Informatics and Therapeutic Applications. 2012 Presented at: SPIE Medical Imaging; February 2012; San Diego, CA. [CrossRef]
  33. Koufi V, Malamateniou F, Vassilacopoulos G. Authorization in Cloud e-Radiology Services. In: Proceedings of the International Conference on Knowledge Management and Information Sharing.: SCITEPRESS; 2010 Presented at: KMIS-2010; October 25-28, 2010; Valencia, Spain p. 273-279. [CrossRef]
  34. Nguyen T, Islam M, Al-Saffar A, Park JY, Huh EN. Secure collaborative cloud design for global USN services. In: Pan JS, Chen SM, Nguyen NT, editors. ICCCI 2010. Berlin Heidelberg: Springer-Verlag; 2010:178-187.
  35. Feldman H, Reti S, Kaldany E, Safran C. Deployment of a highly secure clinical data repository in an insecure international environment. Stud Health Technol Inform 2010;160(Pt 2):869-873. [Medline]
  36. Jiang P, Winkley J, Zhao C, Munnoch R, Min G, Yang LT. An Intelligent Information Forwarder for Healthcare Big Data Systems With Distributed Wearable Sensors. IEEE Systems Journal 2016 Sep;10(3):1147-1159. [CrossRef]
  37. Madakam S, Ramaswamy R, Tripathi S. Internet of Things (IoT): A Literature Review. JCC 2015;03(05):164-173. [CrossRef]
  38. Van den Abeele F, Hoebeke J, Teklemariam GK, Moerman I, Demeester P. Sensor Function Virtualization to Support Distributed Intelligence in the Internet of Things. Wireless Pers Commun 2015 Mar 12;81(4):1415-1436. [CrossRef]
  39. Oprian D. Thirty-ninth Annual Meeting February 12–16, 1995 Moscone Center San Francisco, California. In: Biophysical Journal. 1995 Feb Presented at: Moscone Center San Francisco, California: Monday Symposia and Posters, Part II; 1995.02.12-16; San Francisco p. A1-A21. [CrossRef]
  40. Cubo J, Nieto A, Pimentel E. A Cloud-Based Internet of Things Platform for Ambient Assisted Living. Sensors 2014 Aug 04;14(8):14070-14105. [CrossRef]
  41. Fernandez F, Pallis G. Opportunities and challenges of the Internet of Things for healthcare: Systems engineering perspective. : IEEE; 2014 Presented at: 2014 4th International Conference on Wireless Mobile Communication and Healthcare - Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH); November 3-5, 2014; Athens, Greece. [CrossRef]
  42. Škraba A, Stojanović R, Zupan A, Koložvari A, Kofjač D. Speech-controlled cloud-based wheelchair platform for disabled persons. Microprocessors and Microsystems 2015 Nov;39(8):819-828. [CrossRef]
  43. Nakagawa I, Hiji M, Kikuchi Y, Fukumoto M, Shimojo S. m-cloud -- Distributed Statistical Computation Using Multiple Cloud Computers. : IEEE; 2014 Presented at: 2014 IEEE 38th International Computer Software and Applications Conference Workshops; July 21-25, 2014; Vasteras, Sweden. [CrossRef]
  44. Kim J. Energy-Efficient Dynamic Packet Downloading for Medical IoT Platforms. IEEE Trans Ind Inf 2015 Dec;11(6):1653-1659. [CrossRef]
  45. Suciu G, Suciu V, Martian A, Craciunescu R, Vulpe A, Marcu I, et al. Big Data, Internet of Things and Cloud Convergence – An Architecture for Secure E-Health Applications. J Med Syst 2015 Sep 7;39(11):141. [CrossRef]
  46. Mital M, Pani AK, Damodaran S, Ramesh R. Cloud based management and control system for smart communities: A practical case study. Computers in Industry 2015 Dec;74:162-172. [CrossRef]
  47. Jara AJ, Bocchi Y, Genoud D. Determining human dynamics through the Internet of Things. : IEEE; 2013 Presented at: 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT); November 17-20, 2013; Atlanta, GA p. 301-305. [CrossRef]
  48. Wu PY, Cheng CW, Kaddi CD, Venugopalan J, Hoffman R, Wang MD. –Omic and Electronic Health Record Big Data Analytics for Precision Medicine. IEEE Trans Biomed Eng 2017 Feb;64(2):263-273. [CrossRef]
  49. Luo L, Li L, Hu J, Wang X, Hou B, Zhang T, et al. A hybrid solution for extracting structured medical information from unstructured data in medical records via a double-reading/entry system. BMC Med Inform Decis Mak 2016 Aug 30;16(1):114. [CrossRef]
  50. Santillana M, Nguyen AT, Louie T, Zink A, Gray J, Sung I, et al. Cloud-based Electronic Health Records for Real-time, Region-specific Influenza Surveillance. Sci Rep 2016 May 11;6(1):25732. [CrossRef]
  51. Gupta N, Ahuja N, Malhotra S, Bala A, Kaur G. Intelligent heart disease prediction in cloud environment through ensembling. Expert Systems 2017 Apr 25;34(3):e12207. [CrossRef]
  52. Gu D, Liang C, Zhao H. A case-based reasoning system based on weighted heterogeneous value distance metric for breast cancer diagnosis. Artificial Intelligence in Medicine 2017 Mar;77:31-47. [CrossRef]
  53. Roychowdhury S. Classification of large-scale fundus image data sets: a cloud-computing framework. Classification of large-scale fundus image data sets: IEEE; 2016 Presented at: 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); August 16-20, 2016; Orlando, FL. [CrossRef]
  54. LeMoyne R, Heerinckx F, Aranca T, De Jager R, Zesiewicz T, Saal HJ. Wearable body and wireless inertial sensors for machine learning classification of gait for people with Friedreich's ataxia. : IEEE; 2016 Presented at: 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN); June 14-17, 2016; San Francisco, CA. [CrossRef]
  55. Witbrodt B, Sunderam V. A Patient Centered Cloud Platform for Mobile-Health Enabled Clinical Research. 2016 Presented at: 2016 IEEE First International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE); June 27-29, 2016; Washington, DC. [CrossRef]
  56. Miah SJ, Hasan N, Hasan R, Gammack J. Healthcare support for underserved communities using a mobile social media platform. Information Systems 2017 Jun;66:1-12. [CrossRef]
  57. Li J, Liao Z. Visualization Analysis of Emergency Logistics Research Based on the CiteSpace III. In: Proceedings of the International Conference on Management, Computer and Education Informatization.: Atlantis Press; 2015 Jun Presented at: International Conference on Management, Computer and Education Informatization (MCEI 2015); September 25-27, 2015; Shenyang, China p. 211-215. [CrossRef]
  58. Li X, Ma E, Qu H. Knowledge mapping of hospitality research − A visual analysis using CiteSpace. International Journal of Hospitality Management 2017 Jan;60:77-93. [CrossRef]
  59. Fernández-Cardeñosa G, de la Torre-Díez I, López-Coronado M, Rodrigues JJPC. Analysis of Cloud-Based Solutions on EHRs Systems in Different Scenarios. J Med Syst 2012 Apr 11;36(6):3777-3782. [CrossRef]
  60. Radwan AS, Abdel-Hamid AA, Hanafy Y. Cloud-based service for secure electronic medical record exchange. 2012 Presented at: 22nd International Conference on Computer Theory and Applications (ICCTA); October 13-15, 2012; Alexandria, Egypt. [CrossRef]
  61. Bertschek I, Niebel T. Mobile and more productive? Firm-level evidence on the productivity effects of mobile internet use. Telecommunications Policy 2016 Sep;40(9):888-898. [CrossRef]
  62. Tayeb S, Latifi S, Kim Y. A survey on IoT communication and computation frameworks: An industrial perspective. 2017 Presented at: 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC); January 9-11, 2017; Las Vegas, NV. [CrossRef]
  63. Sajjad M, Khan S, Jan Z, Muhammad K, Moon H, Kwak JT, et al. Leukocytes Classification and Segmentation in Microscopic Blood Smear: A Resource-Aware Healthcare Service in Smart Cities. IEEE Access 2017;5:3475-3489. [CrossRef]
  64. Zhang Y, Qiu M, Tsai C, Hassan MM, Alamri A. Health-CPS: Healthcare Cyber-Physical System Assisted by Cloud and Big Data. IEEE Systems Journal 2017 Mar;11(1):88-95. [CrossRef]
  65. Zhang Y, O’Connor SM, van der Linden GW, Prakash A, Lynch JP. SenStore: A Scalable Cyberinfrastructure Platform for Implementation of Data-to-Decision Frameworks for Infrastructure Health Management. J. Comput. Civ. Eng 2016 Sep;30(5):04016012. [CrossRef]
  66. Tawalbeh L, Bakheder W, Mehmood R, Song H. Cloudlet-based Mobile Cloud Computing for Healthcare Applications. 2017 Presented at: Global Communications Conference; December 4-8, 2017; Singapore. [CrossRef]
  67. Pal D, Senchury G, Khethavath P. Secure and privacy preserving mobile healthcare data exchange using cloud service. 2016 Sep Presented at: International Symposium on Security in Computing and Communication; 2016; Singapore. [CrossRef]

DICOM: Digital Imaging and Communications in Medicine
IoT: Internet of Things
IT: information technology
NEViewer: Network Evolvement and Trend Detection System
SaaS: software as a service
SATI: Statistical Analysis Toolkit

Edited by G Eysenbach; submitted 24.06.19; peer-reviewed by W Erdley, J Zhou; comments to author 29.07.19; revised version received 28.10.19; accepted 15.12.19; published 25.02.20


©Dongxiao Gu, Xuejie Yang, Shuyuan Deng, Changyong Liang, Xiaoyu Wang, Jiao Wu, Jingjing Guo. Originally published in the Journal of Medical Internet Research (, 25.02.2020.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on, as well as this copyright and license information must be included.