Premium
Validation of the RTOG recursive partitioning classification for head and neck tumors
Author(s) -
Cooper Jay S.,
Berkey Brian,
Marcial Victor,
Fu Karen K.,
Lee D. J.
Publication year - 2001
Publication title -
head and neck
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.012
H-Index - 127
eISSN - 1097-0347
pISSN - 1043-3074
DOI - 10.1002/hed.1094
Subject(s) - recursive partitioning , outcome (game theory) , database , computer science , head and neck , head and neck cancer , radiation therapy , data mining , medicine , machine learning , mathematics , surgery , mathematical economics
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. Head Neck 23: 669–677, 2001.