Objectives. The paper focuses on the problem of adequately coding pathology
reports using SNOMED. Both the agreement between pathologists in coding an
d the quality of a system that supports pathologists in coding pathology re
ports were evaluated.
Methods: Six sets of three pathologists each received a different set of 40
pathology reports. Five different SNOMED code lines accompanied each patho
logy report. Three pathologists evaluated the correctness of each of these
code lines. Kappa values and values for the reliability coefficients were d
etermined to gain insight in the variance observed when coding pathology re
ports. The system that is evaluated compares a newly entered report, repres
ented as a multi-dimensional word vector, with reports in a library, repres
ented in the some way. The reports in the library are already coded. The sy
stem presents the code lines belonging to the five library reports most sim
ilar to the newly entered one to the pathologist in this way supporting the
pathologist in determining the correct codes. A high similarity between tw
o reports is indicated by a large value of the inproduct of the vector of t
he newly entered report and the vector of a report in the library.
Results: Agreement between pathologists in coding was fair (average kappa o
f 0.44). The reliability coefficient varied from 0.81 to 0.89 for the six s
ets of pathology reports. The system gave correct suggestions in 50% of the
reports. In another 30% it was helpful for the pathologists.
Conclusions. On the basis of the level of the reliability coefficients it c
ould be concluded that three pathologists are indeed sufficient for obtaini
ng a gold standard for evaluating the system. The method used for comparing
reports is not strong enough to allow fully automatic coding. It could be
shown that the system induces a more uniform coding by pathologists. An eva
luation of the incorrect suggestions of the system indicates that the perfo
rmance of the system can still be improved.