The emergence of new hybrid nanomaterial has enabled prosthetic devices to have more performance and significantly improved the quality of life of the disabled. Due to the biosensing properties of prosthetic limbs made of nanomaterials, a large number of nanocomposites have been designed, developed, and evaluated for various prosthetic limbs, such as e-skin, e-skin’s neurotactility sensing, human prosthetic interface tissue engineering, bones, and biosensors. Nano-based materials are also considered to be the new generation of scientific and technological materials for the preparation of various prosthetic devices for the disabled, which can effectively improve the sense of use of the disabled and achieve functional diversity. The study described various nanomaterials for prosthetic devices, and introduced some basic components of nanocomposites; their applications are in three areas, such as bone, skin, and nerve, and evaluated and summarized the advantages of these applications. The results show that (1) carbon-based nanomaterials as neural materials have been studied most deeply. Due to that strong stability of the carbon-based material and the simple transmission mechanism, the cost can be controlled in manufacturing the artificial limb. Materials with human-computer interaction function are the research focus in the future. (2) Skin nanomaterials are mainly composite materials, generally containing metal- and carbon-based materials. Ionic gels, ionic liquids, hydrogels, and elastomers have become the focus of attention due to the sensitivity, multimodal, and memory properties of their materials. (3) Outstanding nanomaterials for bone are fibrous materials, metallic synthetic materials, and composite materials, with extremely high hardness, weight, and toughness. Of the skeletal materials, the choice of prosthetic socket material is the most important and is typically based on fiber laminate composites. Some of these materials make sensors for durability and performance that can be used for large-scale clinical testing.

Brain Tumor originates from abnormal cells, which is developed uncontrollably. Magnetic resonance imaging (MRI) is developed to generate high-quality images and provide extensive medical research information. The machine learning algorithms can improve the diagnostic value of MRI to obtain automation and accurate classification of MRI. In this research, we propose a supervised machine learning applied training and testing model to classify and analyze the features of brain tumors MRI in the performance of accuracy, precision, sensitivity and F1 score. The result presents that more than 95% accuracy is obtained in this model. It can be used to classify features more accurate than other existing methods.