Informatics Nursing

DATA ANALYTICS CAPABILITIES

      Based on the text, Saint Clare’s Health System objective of providing high quality health treatment and giving more efficient care is a big success. They achieved this goal by digitizing more information resources by compiling data from existing paperwork and procedural activities. This provided intelligence about the effectiveness of treatment procedures. In addition, the resource data enhanced efficiency by mitigating lost information, increasing productivity of care providers and better identification of areas of improvement in care procedures.

             In order to achieve a long-term goal, they put in place additional interventions by involving all stakeholders. They invited request for proposal process to system vendors and open forum of internal hospital users and stakeholders to get a feel in technological functioning of the data-based strategy. Following was a formal and extensive training to ease the adoption of system as a part of their daily treatment activities. (Kudyba & Rader, 2010)

                             DECISION SUPPORT

             Decision support is the use of technology in computer programs and information needed to help one make conclusions especially within an organization. Various factors  helps in making these smart decisions and they include;

1. Big Data

             Big data refers to the large amount of information found online. This is the information garnered both internally and externally to your company and need to be analyzed and cleaned up in order to get the useful materials for your business. Just like a library, big data offers more answers than the questions you have giving you more insights related to your business hence broadening your vision. (Junk, 2015)

             Big data helps a company to find answers on cost and time reductions, new products development and also smart decision making. This will aid in accomplishing business-related tasks such as determining the root causes of failures, issues and defects, detect corrupt and dishonest behaviors before they ruin your company, generate vouchers to customers at the point of sale and also calculating all portfolios within a short period of time. (Junk, 2015)

• Data Mining

            Data mining involves examining all facts used before in order to recognize previously unknown pattern to generate new information. This enables one to find answers you were not looking for in the first place hence giving one a chance for better performance. (Junk, 2015)

 It is largely used by companies in order to determine the relationship between the internal factors such as price and manpower efficiency and also external factors such as competition, number of customers among others. This enables the company to get summarized details on its transactions therefore aiding in determining its effect on sales, customer satisfaction and also profits. (Palace, 1996)

• Analytics

It involves breaking down data and studying patterns over a period of time by comparing one sector to another. For, instance a business owner may want to know why one business branch is performing better than the other, Is it because of better service delivery from one branch compared to the other? It involves asking questions and looking for appropriate answers leading to smart decision making. (Junk, 2015)

              BENEFITS OF DATA MINING AND BIG DATA IN HEALTHCARE

         The immense use of electronic health records in healthcare facilities is a sign that healthcare providers have adopted big data and data mining system. This comes with many benefits to both patients and healthcare providers and also insurance companies. Patients can access affordable and better services since by using data mining programs it’s easier to identify and observe high risk patients and chronic diseases and easily take the right precautions. (King, 2015)

          Data mining and data analysis equip healthcare providers with best practices and most effective treatments hence reducing number of hospital admissions and number of claims. In addition, it helps in development of the best care standards and best clinical practices. Data mining provides the healthcare providers with information about the patients’ needs hence improving their relationship and also increasing patient satisfaction. (King, 2015)

            Data mining increase awareness on dishonest referrals and corrupt claims enabling insurance companies to detect medical insurance abuse and fraud. Reduction of insurance claims due to fraud means reduction in the cost of healthcare. (King, 2015)        

           In addition, data mining models helps in determining not just the past performance, the present activities of the healthcare organization but also future trends and patterns. (Kudyba & Rader, 2010)

                  DATA MINING AND BIG DATA IN SPAM BLOGOSPHERE

           Spam blogs are also known as splogs and are created to intentionally seek a significant impression by compromising the quality of the affiliate blog’s real value. They post false information to many blog sites, create fake blogs containing meaningless texts and use them to keep link farms which give them importance in participating farms or post stolen information from other blogs or new sources. In addition, they use comment features in blogs to advertise their blogs and websites.  Their immense invasion in social media is due to very few restrictions and also open standards which are easily achievable and affordable. Their main objective is to generate income cunningly by taking charge of content-based advertisements targeting visitors in the blog. (Agarwal& Liu, 2009)

          Elimination of spammers from the blogosphere will improve the quality of search data by providing clean, accurate and satisfying search results. Moreover, the space used to store blogs and comments from spammers will be largely reduced and used for other activities and subsequently reduce loss of network resources through fraud. (Agarwal& Liu,2009).

        According to Umbria Inc. (2006), spam blogs were between 10% and 20% in October 2005 of all blogs in the blogosphere. Umbria Inc. collects and analyzes blog information using a data mining approach and uses three major filters to attack the spam blog problem and continually improves on spam blog detection. The filters include;

1. Automated machine learning algorithms-  detect up to 80% of spam blogs
2. Blacklist approach- detect between 5 to 10% spam blogs and maintains list of  already  known spam blogs and is continually updated.  
3. Manual inspection and review- eliminates the remaining 1 to 5% of the remaining blog spam. It is done during Quality Assurance analysis which helps in improving in the elimination and detection of spam blogs in the previous steps.

                                         References

Agarwal, N. & Liu, H. (2009). Modeling and data mining in blogosphere (1st ed., p. 45). [San Rafael, Calif.]: Morgan & Claypool Publishers.

InMotion Hosting. (2006). Umbrialistens.com. Retrieved 26 November 2016, from http://www.umbrialistens.com

Junk, D. (2015). BIG DATA. Aptera blog. Retrieved from http://blog.apterainc.com/business-intelligence/business-intelligence-vs-analytics-vs-big-data-vs-data-mining

King, E. (2015). How Data Mining Is Helping Healthcare – Data Mining, Analytics and Predictive Modeling: Training & Consulting. Data Mining, Analytics and Predictive Modeling: Training & Consulting. Retrieved 25 November 2016, from https://the-modeling-agency.com/how-data-mining-is-helping-healthcare/

Kudyba, S. & Rader, M. (2010). Healthcare informatics (1st ed.). Boca Raton, FL: CRC Press.

Palace, B. (2016). Data mining. Spring: Anderson Graduate School of Management UCLA. Retrieved from http://www.anderson.ucla.edu/faculty/jason.frand/teacher/technologies/palace/index.htm