This operative report documents the details of a surgery. Standardization of the medical terminology for the operative report written in free text is significant for performing medical research and establishing insurance systems by accurately sharing information on treatment. However, standardization of operative reports is a labor-intensive task that has a risk of induced errors. We have proposed a concatenation of bidirectional encoder representations from transformers (ConBERT) model for predicting the International Classification of Disease -9 code using the operative report and diagnosis recorded in free text to standardize the operative report automatically. We compared the pre-trained models of BERT and character BERT and created a new model by concatenating the combinations of each model. The proposed ConBERT model showed a micro AP score of 0.7672, F1 score of 0.7415, and AUC of 0.9842. In addition, we developed a web-based application to demonstrate the performance of our model and make it publicly accessible.

No abstract

Tumor-associated (TA) autoantibodies are considered to be promising biomarkers for the early detection of cancer, prior to the development of clinical symptoms. In the present study, a novel TA autoantibody was detected, which may prove to be useful as a diagnostic marker of human HCC using an HBx-transgenic (HBx-tg) hepatocellular carcinoma (HCC) mouse model. Its target antigen was identified as the bromodomain-containing protein 2 (BRD2), a transcriptional regulator that plays a pivotal role in the transcriptional control of diverse genes. BRD2 was upregulated in HCC tissues of the H-ras12V-tg mouse and human subjects, as demonstrated using western blotting or immunohistochemical analysis, with the BRD2 autoantibody. In addition, the truncated BRD2 reactive to the BRD2 autoantibody was detected in tumor cell-derived exosomes, which possibly activated TA immune responses and the generation of autoantibodies. For the detection of the serum BRD2 autoantibody, epitope mimicries of autoantigenic BRD2 were screened from a random cyclic peptide CX 7 C library with the BRD2 autoantibody. A mimotope with the sequence of CTSVFLPHC, which was cyclized by one pair of cysteine residues, exhibited high affinity to the BRD2 autoantibody and competitively inhibited the binding of the autoantibody to the cellular BRD2 antigen. The use of this cyclic peptide as a capture antigen in human serum enzyme-linked immunosorbent assay allowed the distinction of patients with HCC from healthy subjects with 64.41% sensitivity and 82.42% specificity (area under the ROC curve, 0.7761), which is superior to serum alpha-fetoprotein (AFP; 35.83% sensitivity; 100% specificity; area under the ROC curve, 0.5337) for the diagnosis of HCC. In addition, the detection of the BRD2 autoantibody combined with other autoantibody biomarkers or AFP has increased the accuracy of HCC diagnosis, suggesting that the combinational detection of cancer biomarkers, including the BRD2 autoantibody, is a promising assay for HCC diagnosis.

No abstract

No abstract