EXPERIMENTS IN CODING CLINICAL INFORMATION - AN ANALYSIS OF CLINICIANUSING A COMPUTERIZED CODING TOOL

We present data from a controlled experiment with a computerized brows ing and encoding tool. Eighteen practicing clinicians were asked to ex tract medical concepts from narrative exercise cases using two approac hes-traditional and computer-assisted use of ICD-9. Our results indica te that completeness of coding can be improved by up to 55% using a co mputerized coding tool; enforcing mandatory as opposed to optional mod ifier codes results in lower rates of incomplete coding (0 vs 55%), hi gher rates of correct coding (41 to 92%), and no change in the number of incorrect codings; and manual coding takes 100% longer than coding with the help of the computerized coding tool. Furthermore, clinicians need 59% more time for processing the whole set of codes than is sugg ested by the sum of individual codes. We conclude that the use of a co mputerized coding tool can save time and result in higher quality codi ng. However, de facto time spent on coding may be underestimated when looking at individual coding times instead of looking at the whole tas k of processing a clinical scenario. (C) 1995 Academic Press, Inc.