Sensitivity to input variability of the Adjuvant! Online breast cancer prognostic model

Abstract

Purpose: Adjuvant! Online (www.adjuvantonline.org) is a software model that predicts the benefit of adjuvant therapy for women with early-stage breast cancer. The model has been validated, is widely consulted, and has been shown to influence patient choices in the clinical setting. Adjuvant! requires the clinician to input patient age, tumor size, grade, hormone receptor status, number of positive lymph nodes, and comorbidity level. Because comorbidity is strongly and independently associated with survival, this study tested the hypothesis that Adjuvant! predictions would be sensitive to comorbidity inputs.

Methods: Investigators used single-variable deterministic sensitivity analysis to evaluate the effect of varying each input of the model independently for three representative case examples based on National Comprehensive Cancer Network guidelines (NCCN). The main outcome of interest was 10-year mortality prediction.

Results: The analyses show that Adjuvant!'s 10-year mortality predictions are most sensitive to patients' comorbidity levels and the extent of nodal involvement for the cases, particularly among older women. Comorbidity was the most influential input except in younger women, aged 40 years.

Conclusion: The Adjuvant! model is sensitive to patient comorbidity, and impact on the model outputs are significant enough that they are likely to affect physician recommendations and patients' treatment choices. For example, incorrect assessments of comorbidities could lead physicians to overtreat or undertreat a patient who is in a gray zone relative to the NCCN guidelines. These results point to the importance of accurately assessing comorbidities in patients with breast cancer when using Adjuvant! and highlight the need for a standardized process of comorbidity ascertainment.