GENERIC DATA MODELING FOR CLINICAL REPOSITORIES

Objective: To construct a large-scale clinical repository that accurat ely captures a detailed understanding of the data vital to the process of health care and that provides highly efficient access to patient i nformation for the users of a clinical information system. Design: Con ventional approaches to data modeling encourage the development of a h ighly specific data schema in order to capture as much information as possible about a given domain. In contrast, current database technolog y functions most effectively for clinical databases when a generic dat a schema is used. The technique of ''generic data modeling'' is presen ted as a method of reconciling these opposing views of clinical data, using formal operations to transform a detailed schema into a generic one. Results: A complex schema consisting of hundreds of entities and representing a rich set of constraints about the patient care domain i s transformed into a generic schema consisting of roughly two dozen ta bles. The resulting database design is efficient for patient-oriented queries and is highly flexible in adapting to the changing information needs of a health care institution, particularly changes involving th e collection of new data elements. Conclusion: Conventional approaches to data modeling can be used to develop rich, complex models of clini cal data that are useful for understanding and managing the process of patient care. Generic data modeling techniques can successfully trans form a detailed design into an efficient generic design that is flexib le enough to meet the needs of an operational clinical information sys tem.