Integrating patient reported measures as predictive parameters into decisionmaking about palliative chemotherapy: a pilot study

Background: Systemic treatment has proven to improve physical symptoms in patients with advanced cancer. Relationship between quality of life (QoL) or symptom burden (SYB) and treatment efficacy (tumour response and survival) is poorly described. Therefore, we evaluated the predictive value of pretreatment QoL and SYB on treatment outcomes. Methods: Eligible patients had metastatic gastrointestinal cancers and were about to receive 1st/2nd line palliative chemotherapy. 47 patients were consecutively enrolled. QoL and SYB were assessed by EORTC QLQ-C30 and MSKCC MSAS questionnaires before treatment and after first response evaluation after 8-12 weeks. Logistic regression analysis of QoL and SYB for prediction of objective treatment efficacy was performed. Patients were categorized according to response rate (RR) based on RECIST1.1 and progression free survival (PFS). PFS was categorized by a ratio (individual PFS/expected PFS) in above median (ratio = 1) or below median PFS (ratio <1). QoL and SYB were analysed for RR groups (partial response, stable or progressive disease) and PFS ratio (PFSR). Results: Objective response to chemotherapy and increase in PFS were associated with better pretreatment QoL and less SYB. Patients with future objective treatment efficacy (PFSR = 1) evidenced clinically relevant better role/emotional/cognitive/social functioning and less fatigue and appetite loss at baseline in comparison to PFSR <1 (>10 points difference). Lowest scores in all functioning scales at treatment start were seen in patients with future PFSR <1. Global health status (EORTC), PSYCH subscale and global distress index (MSAS) predicted PFSR, even if adjusted for gender, age, cancer type, ECOG and line of treatment (p < 0.05). Interestingly, improved QoL and SYB (subjective benefit) were noted even in patients with worse pretreatment status and no objective tumour response. Conclusion: Future non-responders seem to show distinct QoL patterns before chemotherapy. This may facilitate early detection of patients deriving less or even no benefit from treatment regarding prolongation of survival. Even in patients with primarily progressive disease QoL and SYB may improve during treatment. Integration of QoL and SYB assessment into decision-making about palliative chemotherapy seem to be an important approach to improve patient outcome and should be further evaluated.