Background: We previously demonstrated that a mathematical technique called recursive partitioning analysis (RPA), when applied to the Radiation Therapy Oncology Group Head and Neck Cancer database, created rules that formed subgroups ("classes") having unique outcomes. We sought to learn if the application of RPA-derived rules to a new head and neck database would create classes that were similarly associated with outcome and thereby validate this technique.
Methods: The rules derived from recursive partitioning analysis of the previous database were used to subgroup an independent, new head and neck cancer database (RTOG 85-27), created as part of a phase III trial of the hypoxic-cell radiosensitizer, Etanidazole. The resulting classes were compared with each other and with the classes formed from the previous database.
Results: The rules derived by RPA from our previous database correctly grouped the tumors in the new database into unique classes of similar outcome. RPA could successfully use either survival or local-regional control of disease as the measure of outcome. As judged by comparison of the 95% confidence intervals, the outcome of the classes in the new database is essentially indistinguishable from the outcome of the classes in the previous database.
Conclusion: RPA-derived rules provide a reliable method to assort head and neck tumors into unique classes that are predictive of outcome. These rules can be successfully applied to new databases that were not used in the creation of the rules and thereby validate the methodology.