De-identification is the first step to use these records for data processing or further medical investigations in electronic medical records. Consequently, a reliable automated de-identification system would be of high value. In this paper, a method of combining text skeleton and recurrent neural network is proposed to solve the problem of de-identification. Text skeleton is the general structure of a medical record, which can help neural networks to learn better. We evaluated our method on three datasets involving two English datasets from i2b2 de-identification challenge and a Chinese dataset we annotated. Empirical results show that the text skeleton based method we proposed can help the network to recognize protected health information. The comparison between our method and state-of-the-art frameworks indicates that our method achieves high performance on the problem of medical record de-identification.

Background The clinical manifestations of 22q11.2 deletion syndrome (22q11.2 DS) are highly heterogeneous, and the underlying causes of phenotypic variation remain unclear. This study conducted a systematic meta-analysis to evaluate the impact of the deletion position within the 22q11.2 region on phenotypic variability. Methods PubMed, Web of Science, Scopus, Embase, and Cochrane Library databases were searched through 25 September 2024. Literature was screened, and data were extracted based on predefined inclusion and exclusion criteria. Results A total of 17 articles comprising 4107 subjects were included in this study. Among these, 1296 patients presented with congenital heart malformations, while 220 exhibited psychiatric and behavioral abnormalities. 1. Congenital heart malformations: in the central deletion region, congenital heart malformations were significantly associated with the LCR22B-D deletion [OR (BD/CD): 2.74, 95% CI 1.27–5.92, P = 0.01]. 2. Psychiatric and behavioral abnormalities: psychiatric and behavioral abnormalities were significantly associated with smaller typical deletions. Comparisons between the central deletion region and the classic deletion region confirmed a significant association between mental and behavioral abnormalities and LCR22A-B [OR (AB/BD): 6.26, 95% CI 1.16–33.93, P = 0.03]. Conclusions Congenital heart malformations are strongly associated with the central deletion region, specifically LCR22B-D. In contrast, psychiatric and behavioral abnormalities are more strongly linked to the LCR22A-B region, suggesting that smaller deletions significantly elevate the risk of mental and behavioral abnormalities.