Scribd
Upload
65 views2 pages

WS06

The document discusses how data mining can help with healthcare management by analyzing large amounts of healthcare data. It provides an introduction to using data mining for tasks like disease diagnosis, treatment decisions, fraud detection, and healthcare resource management. The tutorial aims to explain the benefits of data mining for healthcare management and discuss directions for future research in this area.

Uploaded by

sumathihrk
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
65 views2 pages

WS06

The document discusses how data mining can help with healthcare management by analyzing large amounts of healthcare data. It provides an introduction to using data mining for tasks like disease diagnosis, treatment decisions, fraud detection, and healthcare resource management. The tutorial aims to explain the benefits of data mining for healthcare management and discuss directions for future research in this area.

Uploaded by

sumathihrk
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Data Mining for Healthcare Management

Prasanna Desikan+ Jaideep Srivastava*

Abstract The tutorial on Data Mining for Healthcare Management will provide an up-to-date introduction to the increasingly important field of data mining in healthcare management, as well as an overview of research directions in this field. This tutorial will help researchers and practitioners from industrial organizations understand how data mining can help them leverage the potential of large amounts of healthcare data that have been collected. 1 Introduction and Motivation Data Mining for Healthcare Management (DMHM) has been instrumental in detecting patterns of diagnosis, decisions, and treatments in healthcare. Data mining has aided in several aspects of healthcare management, including disease diagnosis, decision-making for treatments, medical fraud prevention and detection, fault detection of medical devices, healthcare quality improvement strategies. Data mining was initially a success in the healthcare industry as it was used to detect fraudulent claims processing. However, since then large collections of transactional data and also data due to mergers and acquisitions have enabled businesses to reduce costs by analyzing and extracting hidden patterns. Researchers from both academia and industry have recognized the potential of data mining and its impact on improved healthcare through discovering patterns and trends in large amounts of complex data generated by healthcare transactions. Data mining essentially helps businesses discover insights that enable improved cost efficiency while maintaining a high quality of care. _____________
+

Cardiology, Rhythm and Vascular (CRV), Boston Scientific, MN Department of Computer Science, U of M, MN

Email: [email protected]
*

Email: [email protected]

2 Directions in Healthcare Management The key directions in applying data mining for Healthcare management have been broadly classified into the following categories [1]. Diagnosis and Treatment: Research studies have suggested that unaided human analysis of data for decision making is unintentionally flawed. Applying data mining to even small data sets can provide protection against error-prone unaided human inference and could consequently support improved treatment decisions. Data mining could be particularly useful in medicine when there is no dispositive evidence favoring a particular treatment option. Other key areas where data mining has been proved as an effective tool are disease diagnosis, detection and prediction. Healthcare Resource Management: The goal here is to effectively manage resource allocation by identifying high risk areas and predicting the need for and usage of various resources. For example, a key problem in healthcare is measuring the flow of patients through hospitals and other healthcare facilities. If the inpatient length of stay (LOS) can be predicted efficiently, the planning and management of hospital resources can be greatly enhanced. Customer Relationship Management: The principles of applying of data mining for customer relationship management in other industries are also applicable to the healthcare industry. The identification of usage and purchase patterns and the eventual satisfaction they result in can be used to improve overall customer satisfaction. The customers could be patients, pharmacists, physicians or clinics. In many cases prediction of purchasing and usage behavior can aid in designing proactive initiatives to reduce overall cost and increase customer satisfaction. Fraud and Anomaly Detection: Data mining has been used very successfully in aiding the prevention and early detection of medical insurance fraud. The

ability to detect anomalous behavior based on purchase, usage and other transactional behavior information has made data mining a key tool in variety of organizations to detect fraudulent claims, inappropriate prescriptions and other abnormal behavioral patterns. Another key area where data mining based fraud detection is useful is the detection and prediction of faults in medical devices. 3 Goals and Objectives This tutorial will help participants to understand the following: Why is healthcare management becoming increasingly popular in the computer science domain? What is healthcare management all about? What are the challenges with healthcare management and where does data mining fit in the big picture? What research efforts are being directed towards application of data mining in healthcare management? What are the potential difficulties faced by data mining techniques for healthcare management? What are the available datasets that researchers can work with? What are potential applications of healthcare management based data mining techniques specifically how can they help organizations improve management and monitor the health of the organization? What are the directions for future research in this exciting new field? 4 Tutorial Organization The tutorial will begin with an introduction to healthcare management and the motivation to study this field and its impact on current research and market trends. It will then present the case for why data mining can be used as an effective tool to aid healthcare management by analyzing large amounts of data. Finally, the directions of data mining in healthcare management will be discussed. The core of the tutorial focuses on an overview of the research topics in this area. It discusses the types of available data, the challenges involved, a

generic framework, and prominent models. A sample case study is presented to demonstrate how a certain application challenge can be addressed and the value of using data mining as a tool. Finally, a summary of the research and future directions in this domain is provided to guide researchers and practitioners in conducting theoretical and applied research in this emerging field. 5 Conclusion This tutorial will help participants to understand the key practical and research issues related to applying data mining to healthcare management. References [1] H.C. Koh and G. Tan, Data mining applications in healthcare, Journal of Healthcare Information Management.,19(2):64-72, 2005.

You might also like