Identification and ranking biomaterials for bone scaffolds using machine learning and PROMETHEE

Bones have a complex hierarchical structure that supports their diverse chemical, biological, and mechanical functions. High rates of bone susceptibility to fractures injury attracted extensive research interest find alternate biomaterials for scaffolds. Natural healing is only successful if the defect very small when exceeds 1 cm3 then grafting required. Large defects or injuries are serious problems in orthopedics as they bring great harm health normal function daily life routine. A scaffold should good strength maintain its own after implantation load bearing environment without being stiff shields surrounding from load. Therefore, properties scaffolds match those host tissue be part natural body any further damage. In this paper, we present two main contributions. First, investigate use machine learning models identifying suitable Second, rank best materials biomedical applications using multi-criteria decision analysis methods, Preference Ranking Organization METhod Enrichment Evaluations (PROMETHEE). Machine investigated AdaBoost, artificial neural network (ANN), Naïve Bayes (NB), Decision tree (DT), Support Vector (SVM), K-Nearest Neighbor (KNN). Mechanical such comprehensive strength, tensile Young’s modulus with cortical used standard reference classification. The results show ANN outperforms other engineering, while ranking PROMETHEE Brushite Titanium alloy appropriate cancellous bones, respectively.