Data Mining in Health Care Industry
Data Mining in Health Care Industry
Data mining is the process of analyzing information in large set of databases and transform it into an understandable structure for further use, it can help researchers to gain both narrative and deep insights of exceptional understanding of large biomedical datasets. Manually analyzing, classifying, and summarizing the data is impossible because of the large amount of data available. Data mining can display new biomedical and healthcare knowledge for clinical decision making. It has great potential in the healthcare industry by enabling systems to use data and analysis to identify inefficiencies and best practices to improve care and reduce costs. Researchers believe that opportunities to improve care and reduce costs concurrently could apply to as much as 30% of overall healthcare spending. The goal is to discuss different techniques in data mining that are used to solve complex problems of prediction in Medical diagnosis along with their advantages and disadvantages.
Data Mining is the process of getting useful information in the large database or you can say data mining is the nontrivial process of knowing valid, novel, potentially useful, the ultimately understandable information from data (Tan & Michael, 2005). Rapid advances in data collection and storage technology have enabled healthcare industries to accumulate vast amounts of data. However, extracting useful information has proven extremely challenging, so data mining is the technique that blends traditional data analysis methods with sophisticated algorithms for processing large amounts of data for extracting meaningful information from that vast data (Komal, 2017). Data mining also provides capabilities to predict the outcome of future observations, such as predicting whether a newly arrived patient has what kind of disease in the past. Data Mining is also revealed as a necessary process where best methods are used to extract the data patterns by passing through miscellaneous data mining processes.
Data mining is an integral part of discovering knowledge in large databases (KDD), which is the process of converting vast data into useful or meaningful information (Desouza, 2002). In healthcare, mining data is becoming more desirable, and is more essential now-a-days. For example, the existence of medical insurance fraud and abuse has led many healthcare insurers to attempt to reduce their losses by means of data mining tools to help them find and track offenders (Christy, 1997). Fraud detection using data mining applications is prevalent in the commercial world, e.g. in the detection of the fraudulent credit card transaction (Biafore, 1999).
Clinical determinations are often focusing on the physician’s sense and experience based on the knowledge that comes from huge databases of hospitals. Data are in datasets and need techniques to discover them and use in clinical decisions (Farhad & Hakimi, 2012). This information must be evaluated for medical researches to be used in health centers.
Farhad, G. & Hakimi, S. (2012). Applications for Decision Tree Algorithm for Data Mining in Healthcare Operations. Retrieved from https://pdfs.semanticscholar.org/39b5/0ca364be9b851ff49c206bfd5d164085bc95.pdf
Christy, T. (1997). Analytical tools help health firms fight fraud. Insurance & Technology, (pp. 2-26), Vol. 22.
Biafore, S. (1999). Predictive Solutions bring more power to decision makers. Health Management Technology, (pp. 12-14), Vol. 20.
Komal, S. (2017). Data Mining Techniques in Healthcare. Retrieved from http://www.ijcstjournal.org/volume-5/issue-6/IJCST-V5I6P11.pdf
Desouza, K. (2003). Data Mining in Healthcare Information Systems. Retrieved from https://www.researchgate.net/publication/221178905_Data_Mining_in_Healthcare_Information_Systems_Case_Study_of_a_Veterans_Administration_Spinal_Cord_Injury_Population
Tan, P. & Michael, S. (2005) Introduction to Data Mining. New York: Pearson Publications Inc.