Background: With the increasing variety of drugs, the incidence of adverse drug events (ADEs) is increasing year by year. Massive numbers of ADEs are recorded in electronic medical records and adverse drug reaction (ADR) reports, which are important sources of potential ADR information. Meanwhile, it is essential to make latent ADR information automatically available for better postmarketing drug safety reevaluation and pharmacovigilance. Objective: This study describes how to identify ADR-related information from Chinese ADE reports. Methods: Our study established an efficient automated tool, named BBC-Radical. BBC-Radical is a model that consists of 3 components: Bidirectional Encoder Representations from Transformers (BERT), bidirectional long short-term memory (bi-LSTM), and conditional random field (CRF). The model identifies ADR-related information from Chinese ADR reports. Token features and radical features of Chinese characters were used to represent the common meaning of a group of words. BERT and Bi-LSTM-CRF were novel models that combined these features to conduct named entity recognition (NER) tasks in the free-text section of 24,890 ADR reports from the Jiangsu Province Adverse Drug Reaction Monitoring Center from 2010 to 2016. Moreover, the man-machine comparison experiment on the ADE records from Drum Tower Hospital was designed to compare the NER performance between the BBC-Radical model and a manual method. Results: The NER model achieved relatively high performance, with a precision of 96.4%, recall of 96.0%, and F1 score of 96.2%. This indicates that the performance of the BBC-Radical model (precision 87.2%, recall 85.7%, and F1 score 86.4%) is much better than that of the manual method (precision 86.1%, recall 73.8%, and F1 score 79.5%) in the recognition task of each kind of entity. Conclusions: The proposed model was competitive in extracting ADR-related information from ADE reports, and the results suggest that the application of our method to extract ADR-related information is of great significance in improving the quality of ADR reports and postmarketing drug safety evaluation.

Introduction: Recently, the rise of antibiotic resistance has prompted a reconsideration of tetracyclines. However, existing studies are inadequate in assessing the pediatric safety of this class of antibiotics. To address the gap, our study aims to comprehensively assess the safety of tetracyclines in children.Methods: Adverse event (AE) reports from January 2005 to September 2023 were obtained from the U.S. Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) database, and reporting odds ratio (ROR) was performed to identify potential risk signals in children under 18 years old who were administered any of the three tetracyclines: doxycycline, minocycline, and tigecycline.Results: A total of 1903 AE cases were included in our study: 782 for doxycycline, 981 for minocycline, and 140 for tigecycline. Doxycycline and tigecycline were predominantly associated with “general disorders and administration site conditions” and “gastrointestinal disorders,” while minocycline was more frequently linked to “skin and subcutaneous tissue disorders” and “gastrointestinal disorders.” Psychiatric risks predominantly included depression, suicidal ideation, and suicide attempt. In the category of skin and subcutaneous tissues, 30.88% of the minocycline-induced drug reaction with eosinophilia and systemic symptoms (DRESS) cases resulted in death, alongside a high occurrence of co-occurring AEs such as multiple organ dysfunction syndrome, Type 1 Diabetes Mellitus (T1DM), and autoimmune thyroiditis. As for the endocrine system, both doxycycline and minocycline were found to potentially increase the risk of thyroid dysfunction. For children under the age of 8, doxycycline was associated with tooth discoloration (N = 7, ROR = 20.11%, 95% CI: 9.48–42.67), although it remained unclear whether the discoloration was permanent.Conclusion: Our findings indicated that for pediatric patients, the majority of results were in line with the prescribing information and previous studies, and minocycline tended to cause more frequent and severe AEs than doxycycline. However, it is noteworthy that exceptions were found for psychiatric disorders and thyroid dysfunction associated with doxycycline, which are not mentioned in its FDA prescribing information. Additionally, further safety studies on tigecycline are still needed for children. When prescribing tetracyclines to pediatric patients, a careful risk-benefit assessment is crucial.

Introduction: The epidural-related maternal fever (ERMF) induced by patient-controlled epidural analgesia (PCEA) remains unpredictable. Our objective is to develop ERMF prediction models using real-world data, aiming to identify pertinent contributing factors and support obstetricians in making personalized clinical decisions.Methods: Women who used patient-controlled epidural analgesia between October 2021 and March 2023 at a tertiary hospital in Jiangsu Province were retrospectively documented. The primary outcome was the occurrence of maternal fever associated with epidural use. We developed six machine learning (ML) models and assessed the area under curve (AUC) for characteristics of subjects' performance, calibration curves, and decision curve analyses.Results: A total of 1,492 women were enrolled, with 24.3% experiencing ERMF (362 cases). The AUC ratios between the logistic regression (LR) model and the stochastic gradient descent (SGD) models showed statistical significance (p < 0.05), while the differences between the other models were not statistically significant. In comparison to the SVM model, the LR model exhibited better calibration (Brier score: 0.193; calibration slope: 0.715; calibration intercept: 0.062). Consequently, the LR model was selected as the prediction model. Furthermore, the LR-based nomogram identified eight significant predictors of ERMF, including neutrophil percentage, first stage of labor, amniotic fluid contamination during membrane rupture, artificial rupture of membranes, chorioamnionitis, post-analgesic antimicrobials, pre-analgesic oxytocin, post-analgesic oxytocin, and dinoprostone suppositories.Conclusion: Optimally applying logistic regression models can enable rapid and straightforward identification of ERMF risk and the implementation of rational therapeutic measures, in contrast to machine learning models.

In this study, we determined the complete mitochondrial genome of Neolissochilus heterostomus. The genome is 16,585 bp in length, including 2 ribosomal RNA genes, 13 proteins-coding genes, 22 transfer RNA genes, and two non-coding control regions. Sequence analysis showed that the overall base composition of N. heterostomus is T 24.8%, C 27.7%, A 31.7%, and G 15.8%. The sequence is a slight A + T bias of 56.5%, which is similar to other fishes. We describe a phylogenetic analysis of 16 species of Cypriniformes based on the complete mitochondrial genome, and the result showed that N. stracheyi is most closely related to N. heterostomus. This mitogenome sequence data would play an important role in the investigation of phylogenetic relationship of the Cyprinidae.

Objective. To explore the incidence and influencing factors of postoperative hypoglycemia in diabetic patients during the perioperative period and to construct a risk prediction model for postoperative hypoglycemia. Methods. Patients with T2DM admitted to the nonendocrinology department of Nanjing Drum Tower Hospital from December 2019 to January 2022 were included as research subjects. Basic information, hospital blood glucose management methods, laboratory indicators, and surgery-related indicators were collected. A risk prediction model and scoring table for postoperative hypoglycemia in patients with perioperative diabetes mellitus were established. Results. A total of 440 patients were included, of which 109 had hypoglycemia, resulting in an incidence of postoperative hypoglycemia of 24.78. The results show that preoperative C-peptide and operation duration were risk factors for postoperative hypoglycemia, while BMI and preoperative fasting blood glucose were protective factors. Conclusion. The model constructed in this study is a good method for evaluating the risk of postoperative hypoglycemia. The scoring table intuitively quantifies the risk of risk factors for outcome variables and has strong clinical practicability.