Experiments in coding clinical information: an analysis of clinicians using a computerized coding tool.

We present data from a controlled experiment with computerized browsing and encoding tool. Eighteen practicing clinicians were asked to extract medical concepts from narrative exercise cases using two approaches--traditional and computer-assisted use of ICD-9. Our results indicate that completeness of coding can be improved by up to 55% using a computerized coding tool; enforcing mandatory as opposed to optional modifier codes results in lower rates of incomplete coding (0 vs 55%), higher 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 suggested by the sum of individual codes. We conclude that use of a computerized coding tool can save time and result in higher quality coding However, de facto time spent on coding may be underestimated when looking at individual coding times instead of looking at the whole task of processing a clinical scenario.