Machine Learning in Predicting Printable Biomaterial Formulations for Direct Ink Writing

作     者：Hongyi Chen Yuanchang Liu Stavroula Balabani Ryuji Hirayama Jie Huang Hongyi Chen;Yuanchang Liu;Stavroula Balabani;Ryuji Hirayama;Jie Huang

作者机构：Department of Mechanical EngineeringUniversity College LondonLondonUK Department of Computer ScienceUniversity College LondonLondonUK Wellcome-EPSRC Centre for Interventional Surgical Sciences(WEISS)University College LondonLondonUK. 

出 版 物：《Research》 (研究（英文）)

年 卷 期：2023年第2023卷第4期

页      面：105-115页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The study was supported by University College London internal funds 

主　　题：printing formulation biomaterials 

摘      要：Three-dimensional(3D)printing is emerging as a transformative technology for biomedical *** 3D printed product can be patient-specific by allowing customizability and direct control of the *** trial-and-error approach currently used for developing the composition of printable inks is time-and resource-consuming due to the increasing number of variables requiring expert *** intelligence has the potential to reshape the ink development process by forming a predictive model for printability from experimental *** this paper,we constructed machine learning(ML)algorithms including decision tree,random forest(RF),and deep learning(DL)to predict the printability of biomaterials.A total of 210 formulations including 16 different bioactive and smart materials and 4 solvents were 3D printed,and their printability was *** ML methods were able to learn and predict the printability of a variety of inks based on their biomaterial *** particular,the RF algorithm has achieved the highest accuracy(88.1%),precision(90.6%),and F1 score(87.0%),indicating the best overall performance out of the 3 algorithms,while DL has the highest recall(87.3%).Furthermore,the ML algorithms have predicted the printability window of biomaterials to guide the ink *** printability map generated with DL has finer granularity than other *** has proven to be an effective and novel strategy for developing biomaterial formulations with desired 3D printability for biomedical engineering applications.