Quantitative risk assessments can provide deterministic estimates of risk criteria but involve significant assumptions and uncertainties. Uncertainty quantification methodologies enable propagation of input uncertainties through deterministic models. This propagation of uncertainty can be leveraged to assess the relative impact of each input uncertainty on the output risk uncertainty in a sensitivity analysis. Simple random sampling and Latin hypercube sampling are used to produce risk predictions with quantified uncertainty. Surrogate models such as linear regression, polynomial chaos expansion, and Gaussian processes are used and compared to quantify uncertainty metrics of interest. Sensitivity estimates are made for individual risk assessment inputs with multiple surrogate models and compared for an example hydrogen system. Applying uncertainty quantification methods to quantitative risk assessment calculations provides both a quantitative understanding of the uncertainty associated with risk predictions as well as an understanding of which uncertainty sources are driving that uncertainty.