Search

A national data warehouse that links public and private data could be used to monitor trends in healthcare costs, utilization, quality of care, and adherence to quality guidelines and changes in treatment protocols. The development of the data warehouse, however, would require overcoming a number of political and technical challenges to gain access to private insurance data. This article outlines recommendations from a national conference sponsored by the Agency for Healthcare Research and Quality (AHRQ) on the private sector's role in quality monitoring and provides an operational outline for the development of a national private sector health data warehouse.

Automating clinical and administrative processes via an electronic patient record (EPR) gives clinicians the point-of-care tools they need to deliver better patient care. However, to improve clinical practice as a whole and then evaluate it, healthcare must go beyond basic automation and convert EPR data into aggregated, multidimensional information. Unfortunately, few EPR systems have the established, powerful analytical clinical data warehouses (CDWs) required for this conversion. This article describes how an organization can support best practice by leveraging a CDW that is fully integrated into its EPR and clinical decision support (CDS) system. The article (1) discusses the requirements for comprehensive CDS, including on-line analytical processing (OLAP) of data at both transactional and aggregate levels, (2) suggests that the transactional data acquired by an OLTP EPR system must be remodeled to support retrospective, population-based, aggregate analysis of those data, and (3) concludes that this aggregate analysis is best provided by a separate CDW system.

As healthcare costs continue to rise, along with the urgency to control these costs, timely analyses of operational data stored in data warehouses have become critical. Although healthcare organizations have begun to amass large volumes of raw data within data warehouses, many have yet to capitalize on that valuable information. Many clinical and financial events are recorded each day, yet few of these data are leveraged to increase organizational awareness and performance. Because the development and implementation of a data warehouse requires significant time and capital, as well as highly skilled labor, the need to more fully leverage this considerable investment demands techniques that facilitate detailed data exploration, analysis, and the subsequent communication of findings. This article describes how the effective display of complex relationships in data can be used to discover areas of variance in large, changing data warehouses.

Disease management programs offer the benefits of lower disease occurrence, improved patient care, and lower healthcare costs. In such programs, the key mechanism used to identify individuals at risk for targeted diseases is the data warehouse. This article surveys recent warehousing techniques from HMOs to map out critical issues relating to the preparation, design, and implementation of a successful data warehouse. Discussions of scope, data cleansing, and storage management are included in depicting warehouse preparation and design; data implementation options are contrasted. Examples are provided of data warehouse execution in disease management programs that identify members with preexisting illnesses, as well as those exhibiting high-risk conditions. The proper deployment of successful data warehouses in disease management programs benefits both the organization and the member. Organizations benefit from decreased medical costs; members benefit through an improved quality of life through disease-specific care.

Data warehouses, data marts, and data mining have been hot topics in the 1990s, offering the promise of a vault of corporate data ripe for decision making. As is true with all promising technologies, the key issue is how to get started. Implementation of a corporate data warehouse involves a lot more than spending a huge amount of money on hardware, software, and consultants. Successful implementation of a data warehouse involves a corporate treasure hunt--identifying and cataloging data. It involves data ownership, data integrity, and business process analysis to determine what the data are, who owns them, how reliable they are, and how they are processed. Finally, implementation of the warehouse drives the issue of how good the decisions are that are based on the information in the warehouse. This article presents a case study of how one healthcare facility dealt with the challenges of implementing a data warehouse.

Healthcare provider organizations are faced with a rising number of financial pressures. Both administrators and physicians need help analyzing large numbers of clinical and financial data when making decisions. To assist them, Rush-Presbyterian-St. Luke's Medical Center and Hitachi America, Ltd. (HAL), Inc., have partnered to build an enterprise data warehouse and perform a series of case study analyses. This article focuses on one analysis, which was performed by a team of physicians and computer science researchers, using a commercially available on-line analytical processing (OLAP) tool in conjunction with proprietary data mining techniques developed by HAL researchers. The initial objective of the analysis was to discover how to use data mining techniques to make business decisions that can influence cost, revenue, and operational efficiency while maintaining a high level of care. Another objective was to understand how to apply these techniques appropriately and to find a repeatable method for analyzing data and finding business insights. The process used to identify opportunities and effect changes is described.

In this article we describe the evolution and architecture of a data mart developed to address the modeling and analysis needs of healthcare operations analysts. More specifically, the data mart is used in projects relating to demand analysis, forecasting, capacity planning, and service system design for a healthcare system consisting of a large tertiary care hospital and a smaller community hospital. The primary focus of the mart is on the detailed movement of inpatients through each hospital, although most component data tables include outpatient information such as emergency center visits, surgical cases, cardiac catheterization cases, and short-stay visits. We show that the data mart goes well beyond consolidating data from different sources by including a number of complex, precalculated fields, data structures, and function libraries that are specific to the needs of operations analysts. We discuss several outstanding and challenging design issues that should be of interest to the data warehouse vendor community.

The clinical data repository (CDR) is a frequently updated relational data warehouse that provides users with direct access to detailed, flexible, and rapid retrospective views of clinical, administrative, and financial patient data for the University of Virginia Health System. This article presents a case study of the CDR, detailing its five-year history and focusing on the unique role of data warehousing in an academic medical center. Specifically, the CDR must support multiple missions, including research and education, in addition to administration and management. Users include not only analysts and administrators but clinicians, researchers, and students.

Hill Physicians Medical Group (and its medical management firm, PriMed Management) early on recognized the need for a data warehouse. Management demanded that data from many sources be integrated, cleansed, and formatted. As a first step, an operational data store (ODS) was built and populated with data from the main transactional system; encounter data were added. The ODS has served its purpose well and has whetted management's appetite for more information and faster, more reliable access, all in one location. PriMed hired Annams Systems Consulting (Annams) for this effort. A team was formed, made up of consultants from Annams and members of PriMed's information services (IS) team. The "classical" approach is being taken: enhancing the ODS, which is largely normalized in structure, and integrating data from various sources, along with enforcing business rules. The team is designing and implementing data marts and a "star schema" style of data modeling--a useful tool for management to evaluate results before investing further.