<p>Despite the increasing use of extracorporeal membrane oxygenation (ECMO) and the critical responsibilities of ICU nurses during circuit priming, their cognitive workload in this high-stakes task remains poorly understood. This study aimed to conduct a quantitative assessment of cognitive workload among ICU nurses during ECMO circuit priming. A Queuing Network-Model Human Processor (QN-MHP) simulation model was developed to quantitatively assess cognitive workload during ECMO circuit priming. And, thirty Chinese ICU nurses performed an ECMO priming task, with their subjective cognitive workload quantitatively assessed via NASA Task Load Index (NASA-TLX) questionnaires for permit direct comparison against model predictions. Simulation results from the QN-MHP model revealed that among the 18 subtasks of the ECMO circuit priming, 88.9% were classified as high cognitive workload tasks. The model-predicted task reaction times demonstrated no significant difference compared with experimentally observed data (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(U = 5,p = 0.673 &gt; 0.05\)</EquationSource> </InlineEquation>). Model simulations identified predominant activation in the cognitive (&gt; 20%) and motor control (&gt; 60%) subnetworks, exceeding all other subsystems (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(p &lt; 0.001\)</EquationSource> </InlineEquation>). Significant differences were identified across workload dimensions: predicted values for mental workload, performance load, and effort load were significantly higher than those for physical load and frustration level (<InlineEquation ID="IEq3"> <EquationSource Format="TEX">\(p &lt; 0.001\)</EquationSource> </InlineEquation>). Regression analysis across the six dimensions yielded R² values ranging from 0.736 to 0.815, further confirming a significant correlation between model-predicted cognitive workload values and NASA-TLX scale measurements. The results demonstrate that the QN-MHP model provides a validated framework for quantifying nurses’ cognitive workload during ECMO priming. Distinct from conventional post-hoc scale-based assessment methods, this model enables the effective prediction of cognitive load in ECMO care. These findings provide evidence-based guidance for optimizing ECMO training protocols and redesigning equipment interfaces to reduce cognitive friction in high-demand sub-tasks, thereby potentially improving ICU emergency care and patient safety.</p>