Structured Expert Elicitation to Inform Long-Term Survival Extrapolations in Advanced Renal Cell Carcinoma.

BACKGROUND

In the absence of long-term data, structured expert elicitation gathers expert judgments and associated uncertainties to assess the clinical plausibility of long-term extrapolations.

OBJECTIVE

The objective of this study was to obtain expert estimates of expected long-term outcomes for advanced renal cell carcinoma treatments to inform cost-effectiveness analysis for National Institute for Health and Care Excellence (NICE)'s pathways pilot.

METHODS

Using materials from the structured expert elicitation resources (STEER) repository, aligned with the Medical Research Council (MRC) protocol, the exercise was planned and conducted. Aiming for 5-10 oncologists from diverse UK geographies and settings, experts estimated progression-free survival (PFS) at three landmark timepoints for 21 disease-risk-prior treatment combinations and overall survival for best supportive care. Within an 8-week timeframe, we piloted with one clinician, conducted online training, collected responses via an online survey using the roulette method and mathematically aggregated results through linear opinion pooling.

RESULTS

Nine experts participated (question response rate: 95%). For first-line intermediate/poor-risk patients, clinicians projected similar PFS for three immune oncology/tyrosine kinase inhibitor (TKI) combinations from 5 years onward and comparable PFS for two TKI monotherapies. Nivolumab + ipilimumab was anticipated to achieve the highest PFS amongst first-line therapies. Expert reasoning incorporated treatment class, clinical experience, and awareness of trial data optimism. Expert estimates were generally somewhat optimistic compared with observed UK real-world evidence and pessimistic compared with observed trial data.

CONCLUSIONS

Structured expert elicitation is a pragmatic, efficient approach for informing long-term survival extrapolations in the context of a rapidly evolving treatment pathway. We demonstrated that expert elicitation is possible even for complex decision problems in a relatively short timeframe.