Healthcare Data Analytics Annotated Bibliography.

[Incorrect format for annotated bibliography; the works are not considered citations; the works are the annotations; they will be used for citations and referencing your final paper at the end of the course.] Visual analytics in healthcare education: exploring novel ways to analyze and represent big data in undergraduate medical education Vaitsis, C., Nilsson, G., Zary, N. Visual analytics in healthcare education: exploring novel ways to analyze and represent big data in undergraduate medical education. PeerJ . 2014 November, 25; 2 (2): e683. The aim of the study, ”Visual analytics in healthcare education: exploring novel ways to analyze and represent big data in undergraduate medical education”, was to explore novel ways of analyzing complex medical data using visual analytics (VA).

Specifically, to distinguish various viewpoints influencing how instruction is led by understanding the collected educational data from the medical educational program so as to decide and appropriately apply techniques to analyze and recognize the significant angles inside them, to identify aspects using a pilot course from the undergraduate medical program using VA and to determine the value of applied VA within the data. Methods of analyzing the data include evaluation strategies and learning results so as to investigate VA as an apparatus for discovering methods for speaking to large data from undergrad medical training for development purposes. The software Cytoscape was used to build to identify network aspects and to visualize them. The method of investigation was very effective as for the results, there were eleven aspects identified. Further analysis of the identified aspects with the software Cytoscape presented three different approaches; “learning outcomes and teaching methods, examination and learning outcomes, and teaching methods, learning outcomes, examination results, and gap analysis.” (³) . The finding of this paper can be very helpful on how the medical education curriculum is managed.

This paper is relevant to my final project since it talks about how to improve undergraduate medical education when it comes to working with large data sets. My final project is going to be based on how to manage large sets of data, incorporating different methods and in which ways healthcare data can be useful. Exploring the path to big data analytics success in healthcare Wang, Y., Hajli, N. Exploring the path to big data analytics success in healthcare. Journal of Business Research . 2017 January; 70 : 287–299. The aim of the study is to answer the following research question: How can healthcare organizations capture business value from big data analytics? To explain how large data analytics capabilities can be developed and how it can benefit the healthcare organizations, the researchers designed a theoretical model and named it the big data analytics-enabled business value (BDAE-BV). They used the resource-based theory (RBT) to connect large data, through analytics-enabled IT capacities, to a big data analytics explicit advantages system. The discoveries would offer hypothetical and reasonable experiences on huge data analytics in the healthcare setting; this can enhance the comprehension of large data analytics’ business esteem creation and can likewise give direction to the healthcare professionals for their business case legitimations.

109 case descriptions were investigated during this study, which covered 63 healthcare organizations to identify the relation between the big data analytics capacities and and business value and the path-to-value chains for big data analytics success. The study provides a unique method by using the theoretical foundation of BDA-BV model, which is best described by figure 1, where it expands on each big data analytics architectural component, trailed by the meaning of big data analytics capacities, and the conceptualization of big data analytics’ business esteem. The study also claims that by constructing big data analytics-enabled business value models. They used inductive content analysis which is a three phase process that includes, preparation, organizing and reporting of the data in the healthcare context. As a result, they came up with three perspectives; “ the total number of occurrences of the constructs, the distribution of pairwise connections between the constructs of BDAE-BV model, and the distribution of path-to-value chains connecting all the constructs of BDAE-BV model”.

(⁴) This is a very effective and reliable method for the investigation as it explains how each of the three parts play a role in the investigation. In my opinion, this source can be very useful for my final project because it shows different ways of handling the data as they broke down the three big data analytics architectural components which show the number of occurance of case materials in each component. Predicting Healthcare Fraud in Medicaid: A Multidimensional Data Model and Analysis Techniques for Fraud Detection Thornton, D., Mueller, R., Schoutsen, P., van Hillegersberg, J. Predicting Healthcare Fraud in Medicaid: A Multidimensional Data Model and Analysis Techniques for Fraud Detection. Procedia Technology. 2013; 9 (C): 1252–1264. This article focuses on fraud detection using analysis techniques. This paper expands upon Sparrow’s fraud type arrangements and the Medicaid condition and to build up a Medicaid multidimensional composition and give a lot of multidimensional data models and investigation procedures that help to anticipate the probability of fraud exercises.

This article offers analysis techniques for multidimensional data models which can be useful to detect the different types of fraud types. The researchers structured the design of this article based on the guidelines of Hevner’s et al. (year)_article. [you are referring to another article for which ther e is no reference for the reader]. They made up a table of anti fraud framework design guide to provide primary mMedicaid. Their methods included classifying fraud, for which they designed a table indicating levels of healthcare fraud control. They reviewed some healthcare fraud detection literature to help them throughout the article. They first developed a Multidimensional Data Model and Analysis Techniques, then they created Data models addressing levels of fraud which is how they detected frauds using the views they created. (²) [citations are not require in an annotation; the entire annotation is about the source article. The method they used to detect fraud is definitely very effective as they used many other resources which help support their work and also helped them out to create their views.

This article’s main information is contained in the method part where they explain exactly what they did to detect the fraud using the views and the tables. This source can be a good example to use for my final paper because it shows how to handle data and how to detect fraud using a whole new technique. Fraud detection is going to be a huge part of my final project so this paper would be a good source to use to back up the methods and ideas I will use. Intelligent Healthcare Systems Assisted by Data Analytics and Mobile Computing Zhang, Y., Lu, H., Abbas, H. Mobile Intelligence Assisted by Data Analytics and Cognitive Computing. Wireless Communications and Mobile Computing . 2018; 2018: 2. This paper shows a detailed plan for creating intelligent healthcare systems with the help of data analytics and mobile computing. Additionally, some representative intelligent healthcare applications are examined to show that data analytics and mobile computing are accessible to improve the presentation of the healthcare services administrations. In the introduction they explained the design in detail and step by step on what mobile computing and data analytics make the following contributions: It proposes a bound together information assortment layer for coordinating the healthcare data from open sources and individual devices, it builds up a cloud-enabled and data driven healthcare storage and analytics, and it plans a healthcare application administration layer to give bound together application programming interface (API) and unifies interface. (⁵) Some of the related technologies they used for the methods are mobile computing, big data, cloud computing, wearable computing, internet of things, and cyber physical systems. As a result, they were able to provide more convenient and intelligent services and applications.

This paper displays the smart healthcare services frameworks assisted by mobile computing and data analytics in that comprising of the information assortment layer, the information the service layer, and the management layer. This paper presents some agent applications dependent on the proposed scheme, which have been demonstrated or exhibited to have the option to give professional and intelligent healthcare services. If we were to further study similar types of work in future, we can include some of the methods like cognitive computing, affective computing and deep learning to improve the quality of service. In my opinion, their method of investigation was very effective and it was a well framed article, they discussed some of the very strong and related topics to my final project throughout their paper. This will be a great source to back up my ideas on how to make the healthcare data easy to work with, especially by using data analytics. Available techniques in hadoop small file issue Masadeh, M. B, Azmi, M. S. Available techniques in hadoop small file issue. International Journal of Electrical and Computer Engineering. 2020 April, 1; 10(2): 2097-2101. In this paper, they discuss one of hadoop’s restrictions, that is influences the data processing execution, one of these points of confinement called “big data in small files” gathered when a large number of little documents drove into a hadoop bunch which will make the group to close down completely.

(¹) This paper additionally highlights some local and proposed answers for large information in little records, how they work to lessen the negative impacts on hadoop group, and include additional presentation on storing and accessing the system. According to the introduction, big data characteristics stand on 5v’s; volume, variety, velocity, veracity and value. For the methods, they used hadoop architecture, big data in small file definition, and small file issue. In the solutions, they talked about HAR file, which is used to pack small files into HDFS blocks. nHAR file, which only needs one index file for the read and it can be edited. They also pointed out improved HDFS, sequence file, map file and extended HDFS which are all big data in small file solutions. This article explains it very well on how to overcome problems and use some techniques to use in hadoop small files to make the job easy. According to the techniques the researchers used and the solutions they received, this paper can even be useful in a way more complex data as well.

Techniques they used in the article are very strong and can be a great source to include in my final paper. In conclusion, they recommended using HDFS since it has the potential to clear the small file issue but at the same time it could make the hadoop work more complex. According to me, only the complexity of hadoop would be the weakness of the paper but also on the other hand, it can clear the small file issue. Citations You should be using citations for an annotated bibliography. Healthcare Data Analytics Annotated Bibliography.

(¹)Masadeh, M. B, Azmi, M. S. Available techniques in hadoop small file issue. International Journal of Electrical and Computer Engineering. 2020 April, 1; 10(2): 2097-2101. (²)Thornton, D., Mueller, R., Schoutsen, P., van Hillegersberg, J. Predicting Healthcare Fraud in Medicaid: A Multidimensional Data Model and Analysis Techniques for Fraud Detection. Procedia Technology. 2013; 9 (C): 1252–1264. (³)Vaitsis, C., Nilsson, G., Zary, N. Visual analytics in healthcare education: exploring novel ways to analyze and represent big data in undergraduate medical education. PeerJ . 2014 November, 25; 2 (2): e683. (⁴)Wang, Y., Hajli, N. Exploring the path to big data analytics success in healthcare. Journal of Business Research . 2017 January; 70 : 287–299. (⁵)Zhang, Y., Lu, H., Abbas, H. Mobile Intelligence Assisted by Data Analytics and Cognitive Computing. Wireless Healthcare Data Analytics Annotated Bibliography.