Protected Health Information Recognition of Unstructured Code-Mixed Electronic Health Records in Taiwan.

Electronic health records (EHRs) at medical institutions provide valuable sources for research in both clinical and biomedical domains. However, before such records can be used for research purposes, protected health information (PHI) mentioned in the unstructured text must be removed. In Taiwan's EHR systems the unstructured EHR texts are usually represented in the mixing of English and Chinese languages, which brings challenges for de-identification. This paper presented the first study, to the best of our knowledge, of the construction of a code-mixed EHR de-identification corpus and the evaluation of different mature entity recognition methods applied for the code-mixed PHI recognition task.

Comparison of Vibration-Assisted Scratch Characteristics of SiC Polytypes (3C-, 4H- and 6H-SiC).

Single-crystal silicon carbide (SiC) is widely used because of its excellent properties. However, SiC is a typical hard and brittle material, and there are many challenges in realizing its high efficiency and high-precision machining. Grinding is the main method used to achieve the high-efficiency processing of SiC, but the contradiction between processing quality and processing efficiency is prominent. Vibration-assisted grinding is an effective method to realize high-efficiency and precision machining of SiC. To reveal the vibration-assisted grinding mechanism of SiC, the vibration-assisted nano-scratch process is studied using the molecular dynamics method, and the material removal process and damage formation mechanism in the vibration-assisted scratch are analyzed. Aiming at the three main structural crystal types, 3C-, 4H- and 6H-SiC, scratch simulations were carried out. The vibration-assisted scratch characteristics of SiC polytypes were evaluated from the perspectives of scratch force and the amorphous layer. It was found that the effects of vibration-assisted scratch on different crystal structures of SiC differ, and 3C-SiC is quite different from 4H- and 6H-SiC. Through vibration-assisted scratch simulations under different scratch conditions and vibration characteristics, the influence laws for machining parameters and vibration characteristic parameters were explored. It was found that increasing the frequency and amplitude was beneficial for improving the machining effect. This provides a basis for vibration-assisted grinding technology to be used in the high-efficiency precision machining of SiC.