hlfcmafan;llJolnnafof Bio-Medical ELSEVIER International Journal of Bio-Medical Computing 38 (1995) 155-165 Computing Evaluation of a decision support system in a medical environment Frangois M.H.M. Dupuits*, Arie Hasman Department of Medical Informatics, University of Limburg, P.O. Box 616, 6200 MD Maastricht, The Netherlands Received 26 July 1994;accepted 8 September 1994 Abstract This paper describes the impact of a decision support system on the quality of recorded diagnoses and the com- pleteness of medical records. The assumption is that for quality assessment purposesenough data have to be recorded in an electronic medical record so that diagnostic decisions can be justified. The hypotheses were tested that active decision support will lead to better quality recorded diagnosesand more complete medical records. Three groups of ten GPs were presentedwith 10 cases each. The GPs had to enter the data about thesecases in a GP information sys- tem. One group of GPs was not supported. The secondgroup was presentedwith the ICHPPC-II-Defined criteria that had to be fulfilled when a diagnosis was entered. In a third group, the GPs were asked those data that were needed to justify an entered diagnosis (active support). It could be shown that the last group of GPs entered better quality diagnoses than the other two groups. These latter groups also entered so little data that most of their diagnoses could not he justified. It is concluded from the study that only active decision support will lead to better diagnosesand a more complete medical record that can be used for quality assessment. Keywords: Decision support system; Family medicine; Quality assurance; ICPC; Code validation; Electronic medical record 1. Introduction Information systems are increasingly used by GPs. In The Netherlands, about 70% of GPs use an information system in their daily work. Ap- proximately half of this number of GPs not only have an administrative module at their disposal but also a medical module. An estimated lo- 15% of all Dutch GPs actually make use of an elec- tronic medical record in which they store demo- graphic and medical data of patients. In The * Corresponding author. Netherlands, medical data are registered in a problem-oriented way: use is made of the SOAP approach in which data are recorded as Subjective findings (S), Objective findings (0), Assessment of signs, symptoms, and diagnoses (A), or Plan (P). Moreover, the Dutch version of the International Classification of Primary Care (ICPC) is used for coding complaints, diagnoses and therapies [I]. A national project was initiated by the Dutch College of General Practitioners and several universities to promote a better (coded) registra- tion of medical patient data by GPs by improving the accessibility of the Dutch ICPC version. The 0020-7101/95/$09.50 0 1995 Elsevier Science Ireland Ltd. All rights reserved SSDI 0020-7101(94)01047-5