A claims-based algorithm for identifying keratinocyte carcinoma (KC) with high sensitivity and specificity offers a reliable mechanism for ascertaining KC for epidemiological research in the absence of cancer registry data, a recent study found. These findings also demonstrate the value of recursive partitioning in deriving valid claims-based algorithms. Researchers conducted an 18-year retrospective study using population-based administrative databases linked to 602,371 pathology episodes from a community laboratory for adults. They found:

• Among total pathology episodes, 131,562 (21.8%) had a diagnosis of KC.

• The final derived algorithm outperformed the 5 simple pre-specified algorithms and performed well in both community and hospital data sets in terms of sensitivity (82.6% and 84.9%, respectively), specificity (93.0% and 99.0%, respectively), positive predictive value (76.7% and 69.2, respectively), and negative predictive value (95.0% and 99.6%, respectively).

• Algorithm performance did not vary substantially during the 18-year period.