Supporting Data and Analysis Code for AI-Assisted Prediction and Optimization of Handheld Coaxial Bioprinting

This record contains the supporting data and analysis code for the manuscript entitled “AI-Assisted Prediction and Optimization of Handheld Coaxial Bioprinting.” The study presents a multi-stage AI-assisted framework linking controlled data acquisition, rheology-informed material representation, filament width prediction, printability classification, and integrated process mapping for flow-rate-controlled handheld coaxial bioprinting. The deposited files include frequency-sweep modulus data, flow-curve viscosity data, filament-width and printability measurements, rheological feature data derived from generalized Maxwell and Carreau–Yasuda model fitting, Maxwell-mode selection results, interpolation-curve data, rheology figure source data, machine-learning result tables, classifier ROC-curve data, and the associated Jupyter notebook. These data support the analysis of the effects of GelMA concentration and outer feedrate on filament width and printability and the identification of candidate conditions satisfying the target filament-width range and a high predicted printability probability.