A Comprehensive Analysis of Healthcare Big Data Management, Analytics and Scientific Programming

Healthcare systems are transformed digitally with the help of medical technology, information systems, electronic medical records, wearable and smart devices, and handheld devices. The advancement in the medical big data, along with the availability of new computational models in the field of healthcare, has enabled the caretakers and researchers to extract relevant information and visualize the healthcare big data in a new spectrum. The role of medical big data becomes a challenging task in the form of storage, required information retrieval within a limited time, cost efficient solutions in terms care, and many others. Early decision making based healthcare system has massive potential for dropping the cost of care, refining quality of care, and reducing waste and error. Scientific programming play a significant role to overcome the existing issues and future problems involved in the management of large scale data in healthcare, such as by assisting in the processing of huge data volumes, complex system modelling, and sourcing derivations from healthcare data and simulations. Therefore, to address this problem efficiently a detailed study and analysis of the available literature work is required to facilitate the doctors and practitioners for making the decisions in identifying the disease and suggest treatment accordingly. The peer reviewed reputed journals are selected for the accumulated of published research work during the period ranges from 2015 – 2019 (a portion of 2020 is also included). A total of 127 relevant articles (conference papers, journal papers, book section, and survey papers) are selected for the assessment and analysis purposes. The proposed research work organizes and summarizes the existing published research work based on the research questions defined and keywords identified for the search process. This analysis on the existence research work will help the doctors and practitioners to make more authentic decisions, which ultimately will help to use the study as evidence for treating patients and suggest medicines accordingly.


I. INTRODUCTION
Healthcare systems are being digitally transformed by technological enhancements in medical information systems, electronic medical records, wearable and smart devices, and handheld devices. This increase in medical big data, alongside the development of computational techniques in the field The associate editor coordinating the review of this manuscript and approving it for publication was Dian Tjondronegoro . of healthcare, has enabled researchers and practitioners to extract and visualize medical big data in a new spectrum. In this modern technological age the information increases exponentially. Wearable devices continuously produce a vast amount of data that ultimately known as big data in layman's terms. Modification is required for the big data in the form of analytic based technique for proper management, visualization and extracting the hidden information within the big data. these modification are required due to scale, diversity, and complexity in the data [1]. Big data has gained a significant attention in several fields such as; healthcare applications, banking, internet of things (IoT) based applications, imaging, smart cities, smart transportation system and many others [2]. The data is stored in a standardized manner to easily store, access, and retrieve the required relevant information.
Smart IoT based applications such as wearable devices, electronic medical report (EMR) generators, smart mobile phone healthcare systems has transformed the conventional healthcare system to digital healthcare system. A vast amount of data is generated from these devices on daily basis. Exponential increase in the medical big data has attracted the research community to extract and visualise the new insights from the healthcare big data. Many big data sources are available in the healthcare market such as; registration data, biometric data, electronic health records, imaging, patient reports, the internet data, biomarker data, clinical data, and administrative data [3].
Davarzani et al. [4] performed analysis on 499 elderly patients with congestive heart failure. The reported ages were greater than or equal to 60 years. The samples are collected for these patients after a continues follow-up for the 19 months in his clinic. Relationship between frequently measurements of biomarkers and treatment effects of loop diuretics, spironolactone, β-blockers, and renin-angiotensin system inhibitors on risk of HF hospitalization was examined in the generation of hypothesis. A generic mathematical model is applied to find out the correlation in between the patient's recurrences of events. Kinkorová and Topolčan [5] descibed the key Horizon 2020 of biobanking projects, financing schemes and the future perspective. The EPMA announced the enduring strategies for the useful endorsement of predictive, preventive, and personalized (PPP) medicine. Over 45 countries is contributing toward the implementation and improvement of the promotion of PPP medicine [6]. Golubnitschaja et al. [7], [8] reported several issues associated with the healthcare services of pandemic scenario in the progression of frequent non-communicable diseases, poor economy of health care, lack of specialised education, overdue interventional approaches of reactive medicine, challenging ethical characteristics of some treatments along with insufficient communications among policymakers and professional groups.
Distinctive nature of the healthcare big data makes it unique from other types of data sources. The researchers face many challenges in the processing of big data. Some of the significant challenges are; an efficient recognition model is required to process the huge amount of healthcare data to identify feature and perform classification for the identification of disease, lack of data-sharing incentives, and illegal use (blackmailing) of healthcare big data [9]. Some structural mechanism is required to accumulate healthcare big data [10]. Due to involvement of expensive hardware components (instruments), personal and discomfort of the patient makes the healthcare big data is more expensive. Healthcare big data has numerous applications in the field of public health, dis-ease and safety surveillance, predictive modelling and clinical decision support, and many other research areas.
The researchers face many hurdles in extracting the enriched information from healthcare big data and applying for the diseases identification purposes. Some research work has been reported for reducing the cost of care, the time consumption, the quality of treatment, and the providence of the healthcare facilities at the door steps, but still no detailed research work in the healthcare big data is reported for feature identification, applications, and healthcare big data analytics.

A. PROBLEM DEFINITION
The literature cited reflects that a lot of work has been reported by many researcher around the world for healthcare big data analysis. This research focuses on extracting significant features of big data in the healthcare, applications of healthcare big data, and state of the art techniques proposed in the healthcare big data field which can ultimately be used for decision making in healthcare. The proposed research work organizes and summarizes the existing published research work based on the research questions defined and keywords identified for the search process. This analysis on the existence research work will help the doctors and practitioners to make more authentic decisions, which ultimately will help to use the study as evidence for treating patients and suggest medicines accordingly.

B. RESEARCH CONTRIBUTIONS
A total of 127 most relevant primary studies were included based on the inclusion or exclusion criteria, and quality assessment criteria. Main goal of the proposed systematic literature research work is to counter the given research questions; • What are the most significant big data features in the field of healthcare to be analysed?
• How many state of the art techniques developed in the field of big data in healthcare during the census 2015 -2019?
• For efficient big data management in the healthcare; the researchers proposed how many optimum solutions?
• What are the applications of the big data in scientific programming?
• What are the big data analytics in healthcare? This paper is organized as follows; proposed methodology for this SLR process is outlined in section 2. Section 3 explains the overall research process based on the guidelines provided by Kitchenham et al. [11]. The results and discussions are given briefly in section 4. Some threats to validity are in section 5 for the proposed research work followed by the conclusion in section 6.

II. METHODOLOGY
In this modern technological age the information increases exponentially. Wearable devices continuously produce a vast amount of data that ultimately known as big data in layman's VOLUME 8, 2020 terms. The big data is the data whose diversity, scale, and complexity need new structure, algorithm, technique and analytics for the management, visualization of the new insights from healthcare big data to further provide easy solution for it. For efficient and accurate disease detection this huge data must be processed and to be examined by the caretakers and by practitioners. Analysing this vast amount of data for disease detection, and prevention is a big challenge using the traditional techniques. To address this problem data mining techniques are applied to extract patterns and useful information for the investigation of diseases and its prevention [12].
Big data analytics has improved the quality of treatment by processing the healthcare big data and provides personalized medicines based on the analytical descriptions. The big data in healthcare can be classified into three major classes such as; large n and small p, small n and large p, and large n and large p, (n is the number of samples while p is the number of parameters) [13]. Big data has numerous features to be analysed especially in the field of healthcare. Some researchers used the features of blood sugar, pulse rate, Glasgow coma scale, respiratory rate, chronic nervous scale (CNS) are studied and analysed [14], [15]. Significant work has been reported for identifying different techniques to select big data features in the healthcare. A feature may uniquely identifies data and hence used to detect a specific disease. SLR was followed for the conduction of the proposed research due to the reason that it systematically collect, analyse and derive managing insights from the published material for the defined range of time and defined criteria while other methods (like survey) don't do so.

A. BIG DATA ROLE IN MEDICAL EDUCATION
In a layman terminologies ''big data'' means a huge amount of data. The researchers and teachers used big data in the medical curriculum for designing, analysis, planning, estimating, and ensure delivery of the teacher activities by enhancing healthcare education. Big data is commonly used in the medical education for improving the medical field. The visual analytic has many applications in combing the analysis of data and exploitation technique, human cognitive strength to perceive, information and knowledge representation, and identify visual patterns [16]. Medical data feature encapsulates all the basic information required for diagnosing a certain disease. Features are the static astute values presents in any big data systems. These data features are in conjunction with each other for a certain purpose. These data analytics help in identifying a disease for a specific patient based on its healthcare history. These data analytical values ultimately help the doctors and practitioners suggesting the accurate medicine for a certain disease for a particular patient.
The following sections discuss the proposed methodology followed by the conclusion section at the end.

B. RESEARCH PROCESS
Significant work has been reported in many research domains using SLR [17]. For objectively analysing a specific prob- lem SLR is the alternate way to explore it. Several features exists for the healthcare big data to be analysed critically. These analyses include regression, classification, association, data mining, clustering, and many others. Semantic analysis results in semantically see, deliver, and assess all the available and published material relevant to the research questions formulated to provide a broader knowledge to the research community about a specific domain [17]. Based on the protocol selected for conducting the SLR [11], the activities are classified into three major classes includes; design of protocol, conduct the SLR, and the report evidence.
The next section provides details about the data accumulation, conducting SLR process, and quality assessment of the final selected papers.

C. RESEARCH DEFINITION
The main goal of the proposed SLR work is to perform in-depth study of the available literature in the field of healthcare. In-depth knowledge includes the study of big data features, and data analytics for the patient based on the history recorded. This data analytics and features helps the doctors and practitioners to identify the disease a particular patient based on the features (symptoms) recorded and suggest medicines accordingly. The systematic literature review used in this research work aims to perform a systematic and concise analysis of the healthcare big data to provide a simple and descriptive measures for the dives tools used in the medical and healthcare industries.
A sequence of steps required to perform a fruitful SLR work with objectives. Figure 1 depicts the number of steps taken in performing an SLR work [17].

D. RESEARCH PLAN AND METHOD
For the proposed research work an SLR protocol is followed based on the guidelines suggested by Kitchenham [11]. Figure 2 depicts the number of steps carried out to perform the proposed SLR process. The first step is the formulation of research questions (5 research questions are selected), the selection of keywords for downloading the relevant papers from the selected digital libraries, the inclusion or exclusion criteria of the research articles (based on the contents provided in the paper), the quality assessment criteria based on the weighted numerical values assigned to each research question, and finally, the analysis of the data extracted from the included primary studies.
All these steps are discussed in detail below.

E. RESEARCH QUESTIONS
The research questions (RQ) selected for the proposed systematic literature review process are given below: RQ1. What are the most significant big data features in the field of healthcare to be analysed? Big data has numerous features to be analysed especially in the field of healthcare. Researchers used the features blood sugar, pulse rate, Glasgow coma scale, respiratory rate, chronic nervous scale are studied and analysed. In depth analysis of the healthcare features will be studied. RQ2. How many state-of-the-art techniques developed in the field of big data in healthcare during the census 2015 -2019? This research questions focuses on describing how many available research based approaches are developed for healthcare big data for the retrieval of relevant information. RQ3. For efficient big data management in the healthcare; the researchers proposed how many optimum solutions?
The effective solutions will be studied as part of this research question to. RQ4. What are the applications of the big data in scientific programming? Applications in the area o healthcare will be find from the existing literature to show the areas for further exploration. RQ5. What are the big data analytics in healthcare? Healthcare big data analytics goal is to model, predict and inference, classification, clustering, regression, and other generic approaches which will be exploited in this research question.

F. SEARCH PROCESS
For conducting an SLR process, a proper mechanism must be followed to ensure the accumulation of relevant studies from the selected digital libraries. A systematic mechanism is followed for accumulating the most relevant articles to the proposed field by formulating a set of most specific keywords. That was used for the search purposes in the selected peer review digital libraries for the retrieval of research articles (conference papers, journal papers, book section, survey papers, and many others). In the proposed SLR work, several keywords are formulated associated with big data features identification and analytics in the field of healthcare according to the research questions (given in section 2.3) were searched in the mentioned libraries shown in Figure 4. Figure 3 depicts the steps followed for the proposed study. Figure 4 represents the digital libraries followed for collection of the relevant primary studies based on the keywords formulated. These libraries were selected due to the reasons that it is the most commonly used libraries and are publishing quality materials.
The authors defined the keywords for searching the relevant articles in the libraries. These keywords were kept specific, and short words are chosen for the said task. Using a combination of words instead of using shorten keywords results in huge bulk of articles such as using (big data in healthcare or healthcare big data) results in 2042 links in  Library. This huge information shows that the analysis and assessment, inclusion or exclusion process of every individual paper is a hectic job. To address this problem and accumulate only the relevant papers for the inclusion/exclusion process, and for the analysis and assessment process, the keywords are kept very specific as shown in table 1. These keywords were selected by the authors based on the title of the proposed study and research questions.
The searching process limited to the years ranging from 2015 to 2019 (a section of 2020 is included). The search process results research articles in the form journal publications, books, conference, workshops papers, and many other available materials. Based on the keywords formulated all the selected digital repositories were search manually for the accumulation of the relevant articles. Bibliographic details are stored in the EndNote tool [18]. Overall search process is depicted in figure 5.
For accumulating the relevant articles from the selected libraries a separate folder was created in the root directory and a total of 19789 relevant titles were found. Firstly, each folder is sorted out manually and all the downloaded articles were named based on their titles. This process helped in removing duplicate articles that ultimately helps in saving time during the quality assessment phase. After manual filtering, a total of 527 articles were finalized based on the title. Then the articles were manually checked based on the abstract provided and a total of 339 relevant articles were finalized. Then these papers are finalized for the quality assessment process based on the contents provided in the research articles. A total  of 127 paper were finalized that were the most relevant papers to the proposed topic. The process of inclusion/exclusion of papers is a hectic job because all these steps were performed manually. Whole this process retackled is depicted in figure 6.
EndNote tool is used for managing the bibliographic details for the final selected papers (127 papers).

G. STUDY SELECTION
The search process was performed on the selected peer reviewed digital libraries to extract the most relevant papers to the research questions formulated. A large number of papers (19789 peepers) were accumulated from these libraries that need further refinement to make a final pool of the most relevant papers for the assessment phase. An inclusion and exclusion process is performed to the accumulated articles. The authors the following inclusion/exclusion criteria for the inclusion of the papers in the final pool:  • The papers provide a sound knowledge for the healthcare big data in terms of management, application, and scientific programming.
• The papers provide comprehensible details and context need to cover and answers the research questions defined in the research.

H. STUDY SELECTION PROCESS
In the systematic literature review works article selection is a crucial task, because at every stage the authors are confused whether an article should be skipped or included in the final pool of the selected relevant articles. This is the main step in SLR process, as it results in prominent assessment analysis. to perform the article selection phase we divided this step into three phases. Firstly, the relevant articles are selected based on the titles. A total of 527 relevant articles were finalized based on its titles. Secondly, these titled based selected papers were filtered again based on the abstract provided in the finalized articles. It results in 339 relevant articles. Third and the last stage is to filter the resultant articles (selected based on title and abstract) based on the contents provided in the relevant articles. It results in a total of 127 most relevant articles to the proposed field. All this process is done manually by the authors. The inclusion and exclusion criteria are shown in table 2. Table 3 represents the process of filtering the primary studies for the proposed SLR process. Figure 7 depicts the types of paper (conference paper, book section, journal paper, survey paper) after applying the exclusion and inclusion criteria [19]. Total number of papers by type and by year is depicted in Figure 7.
Year-wise distribution of the selected primary studies is shown in table 4. Figure 8 represents the total number of papers per years. It is depicted from figure 8 that after 2015 the number of paper increases gradually that reflects the applicability of the big data in the fields of healthcare and medical applications. Figure 9 represents the percentage contribution of every online library. VOLUME 8, 2020

I. QUALITY ASSESSMENT
After the inclusion and exclusion phase the quality assessment process is performed on the final selected articles based on the criteria defined as below. This process is iteratively implemented for all the selected papers for all the five research questions. QR1. The papers provide a sound knowledge about the big data features in the healthcare. QR2. The papers provide a detail of work reported during the period 2015 2019 (a portion of 2020 is included). QR3. The papers provide state of the art technique for efficient data management and controlling. QR4. The papers emphasize the applications of scientific programming in the field of healthcare big data. QR5. The papers describe medical big data analytics in healthcare. The authors analysed every papers manually and assessed each paper based on the criteria given below: • 0 -if the paper fails in answering a particular research question.
• 0.5 -if a question moderately/partially satisfied in the paper.
• 1 -if a question satisfactory discussed in the paper. All the selected primary studies are evaluated based on the assessment criteria defined for each question. Figure 10 shows the assessment results for every article.
After performing the assessment process and assigning weighted values to each article based on the research questions, all the assessment values are added to find out the most relevant papers to the proposed field. After performing this operation it was find out that the summed value of a paper is greater than or equal to 4 shows the most relevancy of the paper to the targeted field. The list of the most relevant papers is shown in figure 11 below.

J. DATA EXTRACTION
After performing the search process on the targeted online libraries, performing the quality assessment phase, and accumulation of the most relevant papers all the analysis are stored and inspected. The significant information retrieved from the assessment phase and inclusion/exclusion phase in the form of table or figures explained below; • Figure 7 depicts the total included research articles along with required information.
• Table 3 depicts the annual distribution of the articles ranges from 2015 -2019 (a part of 2020 is also included) • Figure 8 gives results for total number of papers on yearly basis.
• Table 5 gives information for the significant healthcare big data features.
• Table 6 provides information about the research work reported since 2015 in the field of healthcare big data.
• Table 7 shows state of the art techniques developed for healthcare big data processing and information retrieval.
• Table 8 depicts the applications of healthcare big data, and scientific programming.
• Table 9 shows the healthcare big data analytics and its applications.

III. RESULTS AND DISCUSSION
The EPMA made a joint venture of 45 countries to work for the implementation and improvement of the promotion of PPP medicine [6]. The European programme 'Horizon 2020' made a commitment to combine the status of the professionals of PPPM toward the new lifelong instruments for the progress of technology and science in health related medical services.
In the upcoming sub-sections each research question is discussed and the relevant articles are classified based on the research questions formulated. A description of every research article is provided based on the research question. A total of 127 relevant primary studies are selected according to the inclusion and exclusion criteria as depicted in Table 4.

A. CONCEPT AND DEFINITION OF MEDICAL BIG DATA
There is no context name suggested for the ''healthcare big data'', but for ease of use and interpretation purposes classified into 5V structure. Figure 11 shows a 5V structure of the big data.
During the last few years a drastic change has been recorded in the field of healthcare due to the occurrence of smart IoT based devices and global communication systems. In this digital age the information increases exponentially. Wearable devices continuously produce a vast amount of data that ultimately known as big data in layman's terms. The big data is the data whose diversity, scale, and complexity need new structure, algorithm, technique and analytics for the management, visualization and to pull-out hidden information. The idea of implementing big data analytics in the field of healthcare suggested for the retrieval of optimum information from complex data by applying different data mining and machine leering and neural network techniques [132]. These techniques ensure the quality of care, reducing care costs, and ensure minimal error rates in the care. McKinsey Global Institute [133] stated that, if the data is utilized efficiently, then the US health care can make an addition than $300 billion every year, of which 2/3 would be reducing expenses by about 8% in the healthcare. Multiple healthcare big data sources are available globally such as; health registration data, EMR data, patient reports of imaging, CT Scans, MRI, and X-Rays, biometrics, biomarkers data, clinical, and other administrative data [3]. The complication in healthcare results in misleading the doctor and practitioners in the prediction, prevention, and processing the healthcare big data for accurate purposes [6]. Big data has numerous features to be analysed especially in the field of healthcare. Some researchers used the features of blood sugar, pulse rate, Glasgow coma scale, respiratory rate, chronic nervous scale (CNS) are studied and analysed [14], [15]. This analysis process consists of classification, features mining, association, clustering, and regression. Table 5 summarizes the work done reported for the question 1. This research questions focuses on describing how many novel based approaches are developed for healthcare big data classification and for the retrieval of relevant information. Several diverse approaches are suggested by the researchers around the world for healthcare big data analysis, ensuring security and risk, storage requirements, and many others. Table 6 depicts the work reported during the years since 2015 -2019 (a section of 2020 is included). VOLUME 8, 2020  In layman terminologies the ''Bid Data'' means a huge amount of data. This huge data comes from many sources like industries, companies, aerospace services and research works, healthcare, smart cities, environmental changes, forecasting and many others, but in this research work the focus of research is the healthcare big data. This big data comes from imaging devices like (X-ray machine, MRI, CT-Scan machines and so on), IoT based applications, Electronic health reporting devices (EHR) devices and many other ICT based systems. These devices provide a huge amount of data on daily basis. Dealing with such a vast amount of data for extracting the most relevant information, and its   proper management is a difficult job. Different techniques are suggested by multiple researchers around the world for extracting the enriched information from this huge amount of data and its efficient management. This research question VOLUME 8, 2020  focuses on to extract the articles that have worked on the big data management (efficient use, control and retrieving abilities). Table 7 depicts the tools and techniques developed during the period ranges from 2015 -2019 (a part of 2020 is also included). Big data mining and analysis has unlimited applications in many fields of daily life such as; natural language processing, medical and healthcare applications, whether forecasting, climate change, aerospace research and many others. This research work mainly focuses on the healthcare big data and its applications in the healthcare. Table 8 represents some of the applications of the big data that are developed during the years ranging from 2015 -2019 (a part of 2020 is also included).

F. RQ5. WHAT ARE THE BIG DATA ANALYTICS IN HEALTHCARE?
In the field of healthcare the major goal of the big data analytics is to model, predict and inference, classification, clustering, regression, and other generic approaches to be exploited [13]. Supervised learning mechanism is followed for healthcare big data analytical modelling. For healthcare improvements the Rumsfeld et al. [3] classified the big data analytics into eight major classes that are; (i) mathematical model for risk avoidance and usage of resources; (ii) disease and treatment heterogeneity; (iii) surveillance of drug and device safety in healthcare; (iv) management of population; (v) measurement of performance and quality care; (vi) clinical decision support and precision medicine; (vii) public health; and (viii) application of research.
Machine learning techniques and big data analytics are applied in the healthcare fields for risk management, clinical decision support, chronic disease detection, and for precision medicine using genomic information [134]. The authors presented Lean Six Sigma application for improvements of patients' satisfaction, processing errors in healthcare payer firm using Six Sigma, and services of Lean Six Sigma for morphological analysis of research literature [135]- [137]. Table 9 depicts the research work reported using big data analytics in the fields of healthcare.

IV. LIMITATIONS OF THE RESEARCH
A few threats to the validity for the proposed research work are listed below: • A number of digital libraries exists for accumulating the research articles, but the proposed SLR work is limited to only five most extensively used libraries. This was decided to focus only on high quality peer reviewed articles.
• This research work is limited to specific number of years ranges from 2015 -2019 (a part of 2020 is also included), but the papers are published on daily basis continuously.
• Google Scholar is skipped. Main reason behind this decision was; it gives access to every journal and paper, and to save time and access only the reputed journal papers.
• A research article may be skipped that contains the word healthcare, but have no concern with this word for the implementation purposes.

V. CONCLUSION
Healthcare big data analysis and management has becomes a challenging task for the researchers. On-time decision making in the healthcare systems requires massive potential for refining the care quality, minimize the cost of care, and decrease error and waste. Therefore, to address this issue an ideal way is to study and report the existing literature that will help the doctors and practitioners to take better decisions in early healthcare. The detailed study will eventually summarise the results of the available literature published related to big data in cardiology. The current research is an endeavour toward comprehensive report on healthcare big data. The proposed study uses systematic literature protocol and guidelines as presented by Kitchenham et al. [11]. Data was collected from the work published during the year 2015 to 2019 (a portion of 2020 is also included) in the form of conference, journals, books, magazines and other online sources. A total of 127 most relevant papers to the healthcare big data are selected in the final pool for the quality assessment purposes.
This research work gives year-wise distribution of the included relevant articles ranging from 2015 to 2019 (a part of 2020 is also included). This paper outlines the significant features of the healthcare big data, state of the art techniques developed by multiple researchers for the identification of certain disease based on the feature map calculated for the healthcare big data, the applications of the healthcare big data, the proper management of the healthcare big data (management in the form of efficient storing, retrieving of certain information, updating and insertion of VOLUME 8, 2020  new data) and scientific programming, and the healthcare big data analytics. The exponential increase of the published research article on yearly basis concludes that the researchers show a keen interest in the field of healthcare big data analytics. This analysis on the existence research work will help the doctors and practitioners to make more authentic decisions, which ultimately will help to use the study as evidence for treating patients and suggest medicines accordingly.

IMPLICATIONS AND FUTURE DIRECTIONS
The proposed study have highlighted the most significant areas of research in healthcare big data and answered some research questions. Further, the implications and future directions for researchers and practitioners are to explore the area further to extract meaningful insights and information from the data for the researchers and practitioners to use in effective way in healthcare. This will require the effort of in-depth analysis of big data in healthcare. VOLUME   RODZIAH BINTI ATAN received the Ph.D. degree in software engineering from University Putra Malaysia, in 2005. She currently works with the Faculty of Computer Science and Information Technology, University Putra Malaysia. She is currently a Lecturer and handles classes for more than 1000 undergraduate students, and has had eight master's and seven Ph.D. degrees students graduated under her supervision. She specializes in the areas of software engineering, software process modeling, and cloud computing services. She has also published academic books and chapters in books, and has more than 100 journal publications and conference papers. Her current research interest is in the commercialization of research products, where she works in collaboration with industry and other institutions of higher learning. She has also held positions as a keynote speaker for an international conference and a colloquium, a panel assessor in a workshop, a subject matter expert, a local and international journal and conference Reviewer, and an industrial training head coordinator.
MUHAMMAD NAWAZ received the Ph.D. degree from the University of Brunel, in 2013, which is quite a reputable Institution in the U.K. He has strong background in Computing discipline which is evident from the master's and bachelor's degrees in the relevant discipline. He has over 20 years of professional teaching and administrative experience and he has taught various computing subjects at the undergraduate and graduate levels. It is worthwhile to note that he has taught some of the most hardcore subjects in the computing field-Advance Multimedia Technologies, Advance Image Processing, Computer Vision, Compiler Construction, Automata Theory, and Artificial Intelligence. He has more than ten publications in recognized journals by the HEC Pakistan. Besides journal publications, he has presented in major computing conferences around the world which ultimately indicates his participation in the research activities and collaboration at national and international level. VOLUME 8, 2020