Prognostic value of health-related quality of life in patients with metastatic pancreatic adenocarcinoma: a random forest methodology.

Abstract

Eastern Cooperative Oncology Group Performance Status (ECOG-PS) is currently an important parameter in the choice of treatment strategy for metastatic pancreatic adenocarcinoma (mPA) patients. However, previous research has shown that patients' self-reported health-related quality of life (HRQOL) scales provided additional prognostic information in homogeneous groups of patients with respect to ECOG-PS. The aim of this study was to identify HRQOL scales with independent prognostic value in mPA and to propose prognostic groups for these patients. We analysed data from 98 chemotherapy-naive patients with histologically proven mPA recruited from 2007 to 2011 in the FIRGEM phase II study which aimed to compare the effectiveness of two chemotherapy regimen. HRQOL data were assessed with the European Organization for Research and Treatment of Cancer QLQ-C30 questionnaire. A random survival forest methodology was used to impute missing data and to identify major prognostic factors for overall survival. Baseline HRQOL assessment was completed by 60% of patients (59/98). Twelve prognostic variables were identified. The three most important prognostic variables were fatigue, appetite loss, and role functioning, followed by three laboratory variables. The model's discriminative power assessed by Harrell's C statistic was 0.65. Fatigue score explained almost all the survival variability. HRQOL scores have prognostic value for mPA patients with good ECOG-PS. Moreover, the patient's fatigue, appetite loss, and self-perception of daily activities were more reliable prognostic indicators than clinical and laboratory variables. These HRQOL scores, especially the fatigue symptom, should be urgently included for prognostic assessment of mPA patients (with good ECOG-PS).