A comparison of published head and neck stage groupings in laryngeal cancer using data from two countries.

The combination of T, N, and M classifications into stage groupings is meant to facilitate a number of activities including: the estimation of prognosis and the comparison of therapeutic interventions among similar groups of cases. We tested the UICC/AJCC fifth edition stage grouping and six other TNM-based groupings proposed for head and neck cancer for their ability to meet these expectations in laryngeal cancer using data from Ontario, Canada, and the area of Southern Norway surrounding Oslo. We defined four criteria to assess each grouping scheme: (1) the subgroups defined by T, N, and M comprising a given group within a grouping scheme have similar survival rates (hazard consistency); (2) the survival rates differ among the groups (hazard discrimination); (3) the prediction of cure is high (outcome prediction); and (4) the distribution of patients among the groups is balanced. We previously identified or derived a measure for each criterion, and the findings were summarized using a scoring system. The range of scores was from 0 (best) to 7 (worst). The data sets were population-based, with 861 cases from Ontario and 642 cases from Southern Norway. Clinical stage assignment was used and the outcome of interest was cause-specific survival. Summary scores across the seven schemes had similar ranges: 0.9 to 5.1 in Ontario and 1.8 to 5.7 in Southern Norway, but the ranking varied. Summing the scores across the two datasets, the TANIS-7 scheme (Head & Neck 1993;15:497-503) ranked first, and was ranked high in both datasets (first and second, respectively). The UICC/AJCC scheme ranked sixth out of seven schemes, and its ranking was fifth and seventh, respectively. UICC/AJCC stage groupings were defined without empirical investigation. When tested, this scheme did not perform best. Our results suggest that the usefulness of the TNM system could be enhanced by optimizing the design of stage groupings through empirical investigation.