An explainable machine learning-based probabilistic framework for the design of scaffolds in bone tissue engineering

Abstract

Recently, 3D-printed biodegradable scaffolds have shown great potential for bone repair in critical-size fractures. The differentiation of the cells on a scaffold is impacted among other factors by the surface deformation of the scaffold due to mechanical loading and the wall shear stresses imposed by the interstitial fluid flow. These factors are in turn significantly affected by the material properties, the geometry of the scaffold, as well as the loading and flow conditions. In this work, a numerical framework is proposed to study the influence of these factors on the expected osteochondral cell differentiation. The considered scaffold is rectangular with a 0/90 lay-down pattern and a four-layered strut made of polylactic acid with a 5% steel particle content. The distribution of the different types of cells on the scaffold surface is estimated through a scalar stimulus, calculated by using a mechanobioregulatory model. To reduce the simulation time for the computation of the cell stimulus, a probabilistic, machine learning (ML) based reduced order model (ROM) is proposed. Then, a sensitivity analysis is 1 performed using the Shapley additive explanations, to examine the contribution of the various parameters to the framework cell stimulus predictions. In a final step, a multiobjective optimization procedure is implemented using genetic algorithms and the ROMs, aiming to identify the material parameters and loading conditions that maximize the percentage of surface area populated by bone cells while minimizing the area occupied by necrotic cells. The results of the performed analysis highlight the potential of using ROMs for the scaffold design, by dramatically reducing the simulation time while enabling the efficient implementation of sensitivity analysis and optimization procedures.

Computational Modelling and Simulation of Scaffolds for Bone Tissue Engineering

“…Computational modelling utilises mathematical models to study the complex processes of a physical system using high-end computational resources. This technique involves modifying inputs and boundary conditions within computer simulations to facilitate the exploration and analysis of different scenarios and outcomes in the models [14][15][16]. The advantage of simulation is that one can evaluate the designed scaffolds before fabrication, ex vivo testing and in vivo implantation to save time and cost while obtaining valuable information about scaffold designs [17,18].…”