Prakash Mahindrakar et al Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 3, Issue 6, Nov-Dec 2013, pp.937-941 www.ijera.com 937 | Page Data Mining In Healthcare: A Survey of Techniques and Algorithms with Its Limitations and Challenges Prakash Mahindrakar 1 , Dr. M. Hanumanthappa 2 1 Research Scholar, Department of Computer Science and Applications, Bangalore University, Bengaluru, India 2 Associate Professor, Department of Computer Science and Applications, Bangalore University, Bengaluru, India ABSTRACT The large amount of data in healthcare industry is a key resource to be processed and analyzed for knowledge extraction. The knowledge discovery is the process of making low-level data into high-level knowledge. Data mining is a core component of the KDD process. Data mining techniques are used in healthcare management which improve the quality and decrease the cost of healthcare services. Data mining algorithms are needed in almost every step in KDD process ranging from domain understanding to knowledge evaluation. It is necessary to identify and evaluate the most common data mining algorithms implemented in modern healthcare services. The need is for algorithms with very high accuracy as medical diagnosis is considered as a significant yet obscure task that needs to be carried out precisely and efficiently. Keywords - data mining, data mining algorithms in healthcare, KDD, knowledge discovery, healthcare I. INTRODUCTION The KDD is the process of making low-level data into high-level knowledge. Knowledge discovery has the Preprocessing, Data mining and Post processing phases. KDD is an iterative or cyclic process that involves sequence steps of processes and data mining is a core component of the KDD process. Data mining is a process of nontrivial extraction of implicit, previously unknown and potentially useful information from the data stored in a database [1]. Data mining involves choosing the data mining task, choosing the data mining algorithm(s) and use of data mining algorithms to generate patterns. A data mining system may generate thousands of patterns. A discovered pattern can correspond to prior knowledge or expectations. A pattern can refer to uninteresting attributes or attribute combinations. Patterns can be redundant. Healthcare industry today generates large amounts of complex data about patients, hospitals resources, disease diagnosis, electronic patient records, medical devices etc. These large amounts of data are a key resource to be processed and analyzed for knowledge extraction that enables support for cost- savings and decision making. Data mining brings a set of tools and techniques that can be applied to this data to discover hidden patterns that provide healthcare professionals an additional source of knowledge for making decisions. Data mining techniques are used in healthcare management for, Diagnosis and Treatment, Healthcare Resource Management, Customer Relationship Management and Fraud and Anomaly Detection. Data mining can help Physicians identify effective treatments and best practices, and Patients receive better and more affordable healthcare services. Data mining algorithms are needed in almost every step in KDD process ranging from domain understanding to knowledge evaluation. It is necessary to identify and evaluate the most common data mining algorithms implemented in modern healthcare services. Determining performance of data mining solutions require much time and effort. Data mining algorithms may give in better results for one type of problems while others may be suitable for different ones. The need is for algorithms with very high accuracy as medical diagnosis is considered as a significant yet obscure task that needs to be carried out precisely and efficiently. This paper is organized as follows: Section 2 discusses Knowledge discovery process and data mining. Section 3 discusses Data mining techniques. Section 4 discusses Data mining algorithms in healthcare services. Section 5 discusses Limitations and challenges of data mining algorithms in healthcare services and conclusion in section 6. II. KNOWLEDGE DISCOVERY PROCESS AND DATA MINING Knowledge discovery process involves identifying a valid, potentially useful structure in data. The KDD is the process of making low-level data into high-level knowledge. It is an iterative or cyclic process that involves the process steps of Selection, Pre-processing, Transformation, Data mining and Interpretation. Selection step retrieve data relevant to the analysis task. Selection and integration of the target data from possibly many different and heterogeneous sources. The target dataset which is created in this RESEARCH ARTICLE OPEN ACCESS