Experience with an automated cancer protocol surveillance system.

At an active cancer center, patients may be on a large number of different treatment protocols. Each of these protocols has its own examination, test, and treatment modification requirements. It is often difficult for the clinician to keep track of the protocol requirements on all of his patients, so elements of the protocol may be inadvertently omitted.

Experience with the simulated patient-physician encounter.

The development of computer-based simulations of the patient-physician encounter has made it possible to give students the opportunity to manage a case without jeopardizing a real patient's life. At the University of Wisconsin Medical School simulated patients have been an integral part of the third-year teaching program for the past five years. They have been used to permit the students to gain clinical experience, as part of a series of structured teaching conferences, and in a medical testing program.

Archival storage of clinical laboratory data.

This paper describes a data-base system for the maintenance of cumulative clinical data. A unique aspect of this data base is its ability dynamically to alter its two-level format to create an alternative three-level hierarchical structure in order to optimize retrieval efficiency. The relative advantages of these two types of data-base structures are discussed and examples of their use in clinical resrarch are presented.

A simulated patient-physician encounter using a talking computer.

Computer-based clinical simulations provide a means for evaluating the information-gathering and patient-management competencies of physicians. The need for expensive computer terminals has restricted physician use of these simulations. This computer-based program permits physicians to complete computer-based encounters using a standard touch-tone telephone.

Microcomputer voice-response telephone entry for balanced clinical trial randomization.

Simple randomization of patients to treatment regimens in clinical trials can result in inbalance among stratum categories. Procedures that produce balance may lack randomness. Systems that are not deterministic yet produce balance are often extremely complex and are not easily performed by randomization clerks.