Predicting degradation rate of genipin cross-linked gelatin scaffolds with machine learning

Genipin can improve weak mechanical properties and control high degradation rate of gelatin, as a cross-linker of gelatin which is widely used in tissue engineering. In this study, genipin cross-linked gelatin biodegradable porous scaffolds with different weight percentages of gelatin and genipin were prepared for tissue regeneration and measurement of their various properties including morphological characteristics, mechanical properties, swelling, degree of crosslinking and degradation rate. Results indicated that the sample containing the highest amount of gelatin and genipin had the highest degree of crosslinking and increasing the percentage of genipin from 0.125% to 0.5% enhances ultimate tensile strength (UTS) up to 113% and 92%, for samples with 2.5% and 10% gelatin, respectively. For these samples, increasing the percentage of genipin, reduce their degradation rate significantly with an average value of 124%. Furthermore, experimental data are used to develop a machine learning model, which compares artificial neural networks (ANN) and kernel ridge regression (KRR) to predict degradation rate of genipin-cross-linked gelatin scaffolds as a property of interest. The predicted degradation rate demonstrates that the ANN, with mean squared error (MSE) of 2.68%, outperforms the KRR with MSE = 4.78% in terms of accuracy. These results suggest that machine learning models offer an excellent prediction accuracy to estimate the degradation rate which will significantly help reducing experimental costs needed to carry out scaffold design. •There is no single theory to describe degradation rate of polymers.•Converting data to knowledge make it feasible to expose the underlying principles.•For designing new experiments, it is inevitable to invest on data-drive approach through Machine Learning models.•Our results suggest that there is a great potential for applying ML techniques in biomedical engineering.