Optimizing the mechanical properties of a bi-layered knitted/nanofibrous esophageal prosthesis using artificial intelligence

Abstract

The esophagus is a tubular multi-layer organ that carries the food bolus and liquids from the mouth to the stomach. Esophageal prostheses and scaffolds should have the appropriate mechanical and strain properties in the longitudinal and circumferential directions. A novel bi-layered esophageal prosthesis was produced using knitted tubular silk fabric and a coating of polyurethane (PU) nanofibers. The optimization process was performed in two steps. First, 12 different tubular structures of knitted silk fabrics were produced and mechanical properties were measured in both directions. The mechanical properties were optimized using an artificial neural network (ANN) and a genetic algorithm (GA) and the optimum knitted structure was produced as a substrate for coating with PU nanofibers. In second step, 20 different samples were produced by electrospinning the PU nanofibers at different process conditions (collector speed, feeding rate) on the optimized structure of the knitted fabric. Finally, the elastic properties of the bi-layered tubular structures were measured and optimized by the ANN and GA methods. Results presented show that the optimized structure of the esophageal prosthesis had proper mechanical properties similar to the esophagus. Such a structure can be used as a substitute in esophageal disorders. © 2016 Walter de Gruyter GmbH, Berlin/Boston.