Studying Students' Knowledge of the Benefits, Challenges, and Applications of Big Data Analytics in Healthcare

The purpose of this study was to evaluate the students' familiarity from different universities of Mashhad with the benefits, applications and challenges of Big Data analysis. This is a cross-sectional study that was conducted on students of different fields, including Medical Engineering, Medical Informatics, Medical Records and Health Information Management in Mashhad-Iran. A questionnaire was designed. The designed questionnaire evaluated the opinion of students regarding benefits, challenges and applications of Big Data analytics. 200 students participated and participants' opinions were evaluated descriptively and analytically. Most students were between 20 and 30 years old. 43.5% had no work experience. Current and previous field of study of most of the students were HIT, HIM, and Medical Records. Most of the participants in this study were undergraduates. 61.5% were economically active, 54.5% were exposed to Big Data. The mean scores of participants in benefits, applications, and challenges section were 3.71, 3.68, and 3.71, respectively, and process management was significant in different age groups (p=0.046), information, modelling, research, and health informatics across different fields of studies were significant (p=0.015, 0.033, 0.001, 0.024) Information and research were significantly different between groups (p=0.043 and 0.019), research in groups with / without economic activity was significant (p= 0.017) and information in exposed / non-exposed to Big Data groups was significant (p=0.02). Despite the importance and benefits of Big Data analytics, students' lack of familiarity with the necessity and importance is significant. The field of study and level of study does not appear to have an effect on the degree of knowledge of individuals regarding Big Data analysis. The design of technical training courses in this field may increase the level of knowledge of individuals regarding Big Data analysis.


Introduction
Today, with the advent of various technologies, a huge amount of data that is known as Big Data in being generated especially in healthcare. Big data analytics has become a hot topic and has been the focus of many academic communities and the subject of many students' research (Achariya & ahmed, 2016, Alharthi et al., 2017. This type of data has features such as high volume and diversity and due to these features, they cannot be managed and analysed using conventional hardware and software. Analytics for analysing Big Data are known as Big Data Analytics and have many benefits including useful data pattern discovery and important features extraction , Nazari et al., 2021. This analysis has many applications in various medical and insurance industries (Archenaa & Anita, 2015). In addition to the many benefits of these analytics, there are challenges that if ignored, the results will change, such as a lack of expert staff, lack of familiarity with the tools and methods required, data type, security issues, budget and etc (Gharachorloo et al., 2021, Manogaran et al., 2017. Understanding the benefits, challenges, and applications of this area can be helpful in conducting useful and efficient research (Belle et al., 2015. Due to the importance of Big Data analysis in various industries and the fact that students and their research are related to industry and applied research, this field in Iran is in the early stages of research and unfamiliar with the concepts is severely felt. The purpose of this study is to investigate students' familiarity with the different Benefits, applications, and challenges of Big Data.

Method
This cross-sectional study was designed for 200 students of Ferdowsi University and Mashhad University of Medical Sciences. Mashhad is the largest city in eastern Iran with a population of about three million, located on the border with Afghanistan and Turkmenistan on the Silk Road. Mashhad has two major universities, Ferdowsi and Medical Sciences, which students in engineering and basic sciences study at Ferdowsi University and students in medical sciences such as medical Records, Health Information Management and Medical Informatics study at Mashhad University of Medical Sciences.
A questionnaire was designed to assess the level of the knowledge of students in Mashhad universities about the benefits, applications and challenges of Big Data analysis. The questionnaire contains close-end questions with a five-point Likert scale. The basic items of the questionnaire were based on literature searches in Google Scholar, Science Direct and EMBASE databases and were designed and validated by the Delphi method with the participation of 10 experts from various fields (Medical Informatics, Biostatistics, HIT and Computer Science). The questionnaire was designed in the form of 3 general items of benefits, applications and challenges. Benefits included information with 5 questions, modelling with 3 questions, data with 5 questions, and process management with 6 questions. Application questions consisted of health service delivery with 17 questions, research with 4 questions, health, information with 16 questions, essential medicine with 15 questions, health financial with one question, leadership and governance with 6 questions and challenge included 9 questions. The questions are listed in Table 1:

Results
For this study, 200 students participated and the results are shown in Table 2. Most students were between 20 and 30 years old. 63% of them were male and 43.5% had no work experience. Current and previous field of study of most of the students were HIT, HIM, and Medical Records. Most of the participants in this study were undergraduates. 61.5% were economically active. 54.5% were exposed to Big Data. The mean scores of participants in benefits, applications, and challenges section were 3.71, 3.68, and 3.71, respectively (SAS-challenge, SAS-advantage and SAS-application). Examination of SASchallenge, SAS-advantage, and SAS-application by variables of age, gender, field of study, Prior field, work experience, with / without activity, exposure / non-exposure to Big Data can be seen on Table 3. One-way ANOVA test was used to compare the mean of SAS-challenge, SAS-advantage and SASapplication in different age groups with no significant difference in different age groups in these factors. P-Value was 0.228, 0.317, and 0.139 respectively. According to Table 4, the Independent t-test was used to compare the mean of SAS-challenge, SASadvantage and SAS-application in different gender groups with no significant difference in different age groups in these factors. In Table 5, the results of the One-way ANOVA test were showed which compare the mean of SAS-challenge, SAS-advantage and SAS-application in different fields, but the mean of SAS-application and SAS-advantage were not significant .The mean of SAS-challenge was significant in different disciplines. The mean of SASchallenge in medical informatics was higher than other majors (Fig. 1). One-way ANOVA test was used to compare the mean of SAS-challenge, SAS-advantage, and SASapplication at different levels of study that the mean of SAS-application, SAS-advantage, and SAS-challenge were not, according to Table 6. Significant P-Value were 0.142, 0.313, and 0.006 respectively. The one-way ANOVA test was used to compare the mean of SAS-challenge, SAS-advantage and SASapplication between the previous fields of study, but according to Table 7, the mean of SAS-application, SAS-advantage and SAS-challenge were not significant. On Table 8, One-way ANOVA test was used to compare the mean of SAS-challenge, SAS-advantage and SAS-application between different work experiences that the mean of SAS-application, SAS-advantage and SAS-challenge were not significant. P-Value were 0.404, 0.673, and 0.673 respectively. On Table 9, the Independent t-test was used to compare the mean of SAS-challenge, SAS-advantage and SAS-application in the groups with / without economic activity in these factors. P-Value were 0.532, 0.155, and 0.361 respectively. According to Table 10, the Independent t-test was used to compare the mean of SAS-advantage, SASchallenge and SAS-application in the groups with / without exposure to Big Data that there is no significant difference between the groups with / without exposure to Big Data in these factors. P-Value were 0.157, 0.08, and 0.116 respectively. In order to examine the SAS-advantage, SAS-challenge and SAS-application subdomains, the previous analysis of each sub-domain is repeated in terms of variables such as age, gender, field of study, degree, and so on. One-way ANOVA test was used to compare the mean of SAS-advantage, SAS-challenge and SASapplication domains by age groups that process management, according to Table 11, became significant. P-Value were 0.855, 0.861, 0.145, 0.046, 0.172, 0.072, 0.831, 0.315, 0.784, and 0.680, respectively. According to Table 12, the Independent t-test was used to compare the mean of SAS-advantage, SASchallenge and SAS-application in gender groups with no significant difference in gender in these factors. P-Value were 0.738, 0.525, 0.383, 0.230, 0.592, 0.642, 0.463, 0.761, and 0.234, respectively.  On Table 13. One-way ANOVA test was used to compare the mean of SAS-advantage, SAS-challenge, and SAS-application domains by field of study, that the mean of SAS-advantage, SAS-challenge, and SASchallenge in information, modelling, research, and health informatics were significant. P-Value were 0.015, 0.033, 0.726, 0.935, 0.532, 0.001, 0.024, 0.119, 0.922 and 0.500 respectively ( Fig. 2 and Fig. 3).  On Table 14, One-way ANOVA test was used to compare the mean of SAS-advantage, SAS-challenge and SAS-application domains by different levels of study that the mean of SAS-advantage, SAS-challenge and SAS-application in information and research were significant that was more significant at PhD level. P-Value were 0.043, 0.064, 0.589, 0.717, 0.427, 0.019, 0.654, 0.269, 0.880, and 0.807, respectively.  According to Table 15, One-way ANOVA test was used to compare the mean of SAS-advantage, SASchallenge and SAS-application domains by different previous fields of study that the mean of SAS-advantage, SAS-challenge and SAS-application was not significant. P-Value were 0.202, 0.469, 0.772, 0.610, 0.916, 0.122, 0.501, 0.537, 0.420 and 0.749 respectively.

Conclusion
Today, with the advent of technologies and the production of huge amounts of data, Big Data analytics have received much attention especially in healthcare. Understanding this field and recognizing its benefits, applications and challenges provide useful background for conducting efficient research. Therefore, the purpose of this study was to evaluate the students' familiarity from different universities of Mashhad with the benefits, applications and challenges of Big Data analysis. Most students were between 20 and 30 years old. Most of them were male and had no work experience. Current and previous field of study of most of the students were HIT, HIM, and Medical Records. Most of the participants in this study were undergraduates. Most of them were economically active and were exposed to Big Data. The mean scores of participants in benefits, applications, and challenges section were 3.71, 3.68, and 3.71, respectively. Considering that the participants in this study are students from the top universities in the country and have done some Big Data research, it is assumed that Mashhad students have a better level of knowledge in the field of Big Data analysis. Yet there should be more opportunities for students, even organizations' staff to get to know the field more. Training in this field is essential for many disciplines, also conferences could be effective in introducing this field. Students can also provide more familiarity and usage of functional analytics by conducting new researches in this field. In the section of challenges, benefits and application analytics, process management was significantly in different age groups, research, modelling and information and health informatics across different fields of studies were significant. Information and research were significantly different between different levels of studies. Research in groups with / without economic activity was significant and information in exposure / non exposure to Big Data groups was significant. Despite the importance and benefits of Big Data analytics, students' lack of familiarity with the necessity and importance of these analytics in industries and research is significant. The field of study and level of study does not appear to have an effect on the degree of knowledge of individuals regarding Big Data analysis. In future studies, it is suggested that students, practitioners, and other disciplines in different cities and countries evaluate the specific benefits and applications of Big Data analytics and compare the results. Because it will be possible to study in different places and different perspectives. In other businesses, checking their familiarity with Big Data analytics can be helpful in applying management and advertising policies. Big data analytics can play a constructive role in all industries, and today it is widespread in most industries and businesses. Because of the growing trend of data generation, Big Data analytics will become a necessity for all industries and areas in coming years.

Availability of data and materials
These data are available.

Funding
The author(s) received no financial support for the research, authorship, and/or publication of this article.