Improving clinician's coded data entry through the use of an electronic patient record system: 3.5 years experience with a semiautomatic browsing and encoding tool in clinical routine.

This report presents data on clinicians' use of a browsing and encoding utility. Traditional and computerized discharge summaries during three phases of coding ICD-9 diagnoses were compared: phase I (no coding), phase II (manual coding), and phase III (computerized semiautomatic coding). Our data indicate that only 50% of all diagnoses in a discharge summary are encoded manually; using a computerized browsing and encoding utility this rate may increase by 64%; when forced to encode diagnoses manually users may "shift" as much as 84% of relevant diagnoses from the appropriate section to other sections, thereby "bypassing" the need to encode. This effect can be partially reversed by up to 41% with the computerized approach. Using a computerized encoding help can ensure completeness of encoding data (from 46 to 100%). We conclude that the use of a computerized browsing and encoding tool by clinicians can increase data quality and the volume of documented data. Mechanisms bypassing the need to code can be reversed.