Machine learning to explain printability induced by rheology additives

With the continuous growth of extrusion bioprinting techniques, ink formulations based on rheology modifiers are becoming increasingly popular, as they enable 3D printing of non-printable biologically-favored materials. However, benchmarking and characterization of such systems are inherently complicated due to the variety of rheology modifiers and differences in mechanisms of inducing printability. This study tries to explain induced printability in formulations by incorporating machine learning algorithms that describe the underlying basis for decision-making in classifying a printable formulation. For this purpose, a library of rheological data and printability scores for 180 different formulations of hyaluronic acid solutions with varying molecular weights and concentrations and three rheology modifiers were produced. A feature screening methodology was applied to collect and separate the impactful features, which consisted of physically interpretable and easily measurable properties of formulations. In the final step, all relevant features influencing the model’s output were analyzed by advanced yet explainable statistical methods. The outcome provides a guideline for designing new formulations based on data-driven correlations from multiple systems.