Objectives: . Idiopathic sudden sensorineural hearing loss (ISSNHL) is a significant cause of hearing loss. Intratympanic steroid injection (ITSI) is commonly used as an initial or salvage treatment; however, the lack of a standardized treatment protocol has resulted in variability in clinical practice. In addition, no efficient prediction model currently exists to support personalized management. Therefore, this study aimed to develop tailored management strategies for ISSNHL using a machine-learning model. Methods: . This retrospective multicenter cohort study was conducted between January 2015 and December 2020, with data analysis performed between January 2021 and March 2024. Patients were selected based on the International Classification of Diseases, 10th Revision criteria for ISSNHL, along with relevant medication and procedure codes. Patients with pure-tone audiogram results not meeting ISSNHL criteria, better initial hearing in the affected ear, an identifiable etiology, no post-treatment audiogram, or delayed treatment (>6 weeks) were excluded. We included 770 patients diagnosed with ISSNHL who received ITSI. The primary outcome was the area under the receiver operating characteristic curve for prediction performance. Recovery status was determined using the last pure-tone audiogram. Modeling was conducted on the Quanta for Medical Care AI platform using five machine-learning algorithms and a nested cross-validation framework, in which feature selection and hyperparameter tuning were performed in the inner folds and model performance was evaluated in the outer folds. Results: . A random forest classifier outperformed the other models in predicting hearing outcomes, achieving an area under the receiver operating characteristic curve of 0.788. Time to ITSI was the most influential treatment-related factor, with ITSI administered within 10 days of hearing loss being associated with better outcomes. This model can be used to provide personalized prognostic estimates under different treatment protocols. Conclusion . The machine-learning-based prediction model facilitates personalized treatment strategies and timely treatment adjustments for ISSNHL, thereby optimizing the likelihood of complete recovery.

Processed electroencephalogram (EEG) indices, such as the Bispectral Index, have markedly influenced anesthesia practice as they translate brain activity into simple numerical indices. Nevertheless, as the manufacturing algorithms are not disclosed, the underlying neurophysiology remains obscured. Additionally, these indices are often affected by electromyographic contamination, pharmacological variability, and patient-specific EEG heterogeneity. In contrast, an EEG spectrogram, or density spectral array, preserves the frequency- and time-resolved structures of cortical oscillations. This information is presented in a form that is both physiologically meaningful and clinically interpretable. In this review, we trace the evolution of anesthesia from an index-based to a spectrogram-guided approach, and summarize the clinical rationale for adopting the latter. Key applications of this approach include the use of frontal alpha power as a biomarker of cortical stability and postoperative brain health, the identification of nociceptive arousal through alpha dropout and beta or delta arousal patterns, and individualized titration of multimodal or age-specific anesthetic management. Although current devices lack standardized quantitative alpha metrics and have limited sensitivity for low-frequency brain wave components, structured EEG education programs have proven to be effective in terms of fostering spectrogram literacy among anesthesiologists. By combining neurophysiological precision with bedside practicality, the EEG spectrogram represents a pivotal advance toward individualized, mechanism-based, and brain-protective anesthesia, transforming anesthetic monitoring from mere algorithmic abstraction to cortical insight.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background/Aims: Treatment indications for patients with chronic hepatitis B (CHB) remain contentious, particularly for patients with mild alanine aminotransferase (ALT) elevation. We aimed to evaluate treatment effects in this patient population. Methods: This rollover study extended a placebo-controlled trial that enrolled non-cirrhotic patients with CHB and ALT levels below two times the upper limit of normal. Following 3 years of randomized intervention with either tenofovir disoproxil fumarate (TDF) or placebo, participants were rolled over to open-label TDF for 3 years. Liver biopsies were performed before and after the treatment to evaluate histopathological changes. Virological, biochemical, and serological outcomes were also assessed (NCT02463019). Results: Of 146 enrolled patients (median age 47 years, 80.8% male), 123 completed the study with paired biopsies. Overall, the Ishak fibrosis score decreased in 74 (60.2%), remained unchanged in 32 (26.0%), and increased in 17 (13.8%) patients (p<0.0001). The Knodell necroinflammation score decreased in 58 (47.2%), remained unchanged in 29 (23.6%), and increased in 36 (29.3%) patients (p=0.0038). The proportion of patients with an Ishak score ≥ 3 significantly decreased from 26.8% (n=33) to 9.8% (n=12) (p=0.0002). Histological improvements were more pronounced in patients switching from placebo. Virological and biochemical outcomes also improved in placebo switchers and remained stable in patients who continued TDF. However, serum HBsAg levels did not change and no patient cleared HBsAg. Conclusions In CHB patients with minimally raised ALT, favorable histopathological, biochemical, and virological outcomes were observed following 3-year TDF treatment, for both treatment-naïve patients and those already on therapy.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

With the rapid development of sequencing technologies, the detection of alternative polyadenylation (APA) in mammals has become more precise. APA precisely regulates gene expression by altering the length and position of the poly(A) tail, and is involved in various biological processes such as disease occurrence and embryonic development. The research on APA in mammals mainly focuses on the following aspects:(1) identifying APA based on transcriptome data and elucidating their characteristics; (2) investigating the relationship between APA and gene expression regulation to reveal its important role in life regulation;(3) exploring the intrinsic connections between APA and disease occurrence, embryonic development, differentiation, and other life processes to provide new perspectives and methods for disease diagnosis and treatment, as well as uncovering embryonic development regulatory mechanisms. In this review, the classification, mechanisms and functions of APA were elaborated in detail and the methods for APA identifying and APA data resources based on various transcriptome data were systematically summarized. Moreover, we epitomized and provided an outlook on research on APA, emphasizing the role of sequencing technologies in driving studies on APA in mammals. In the future, with the further development of sequencing technology, the regulatory mechanisms of APA in mammals will become clearer.

Objective: To investigate the characteristics of hospitalized injury cases in Huangpu District, Guangzhou City in 2022, so as to provide evidence for optimizing injury prevention interventions. Methods: Data on hospitalized injury cases admitted between January to December 2022 were collected through the hospitalization registry system from 17 healthcare institutions in Huangpu District. The population distribution characteristics, causes of injury, injury sites, duration of hospital stay, and hospitalization costs were descriptively analyzed. Results: A total of 6 729 hospitalized injury cases were reported in Huangpu District in 2022, including 4 277 males and 2 452 females, with a male-to-female ratio of 1.74∶1. The average age was (49.57±19.82) years, with 2 064 cases (30.67%) aged 45 to <60 years and 1 921 cases (28.55%) aged ≥60 years. The median length of hospitalization was 9.00 (interquartile range, 11.00) days, with median hospitalization costs of 15 968.93 (interquartile range, 25 786.69) yuan. In the months of June to August, there were more cases of injury hospitalization,with 1 904 cases accounting for 28.30%. The top three causes of injury were falls (2 895 cases, 43.02%), transportation accidents (1 247 cases, 18.53%) and exposure to inanimate mechanical forces (1 104 cases, 16.41%). The top three injured sites were lower limb injuries (1 850 cases, 27.49%), upper limb injuries (1 596 cases, 23.72%) and other sites (1 178 cases, 17.51%). The three leading causes of injury with longest hospitalization duration were burns and scalds, transport accidents and falls, with the median duration being 12.00 (interquartile range, 8.00) days, 10.00 (interquartile range, 13.00) days and 10.00 (interquartile range, 11.00) days, respectively. The top three injury sites associated with the longest hospitalization duration were others, lower limb injuries, and head and neck injuries, with the median duration being 11.00 (interquartile range, 13.00) days, 11.00 (interquartile range, 11.00) days, and 10.00 (interquartile range, 12.00) days, respectively. The causes of injury associated with higher hospitalization costs were falls and transportation accidents, with the median hospitalization cost being 23 550.13 (interquartile range, 30 087.76) yuan for falls and 20 301.94 (interquartile range, 30 589.86) yuan for transportation accidents. The injury sites associated with higher hospitalization costs were lower limb injuries and upper limb injuries, with the median hospitalization cost being 24 257.32 (interquartile range, 34 145.54) yuan for lower limb injuries and 16 506.33 (interquartile range, 20 052.27) yuan for upper limb injuries. Conclusions In Huangpu District, hospitalized injury mainly occurred among males and individuals aged ≥45 years, with the higher incidence observed between June and August. Fall was the primary cause of injury, while lower limb injuries was the main injury sites. The injury resulted in substantially higher hospitalization costs.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Background/Aims: Treatment indications for patients with chronic hepatitis B (CHB) remain contentious, particularly for patients with mild alanine aminotransferase (ALT) elevation. We aimed to evaluate treatment effects in this patient population. Methods: This rollover study extended a placebo-controlled trial that enrolled non-cirrhotic patients with CHB and ALT levels below two times the upper limit of normal. Following 3 years of randomized intervention with either tenofovir disoproxil fumarate (TDF) or placebo, participants were rolled over to open-label TDF for 3 years. Liver biopsies were performed before and after the treatment to evaluate histopathological changes. Virological, biochemical, and serological outcomes were also assessed (NCT02463019). Results: Of 146 enrolled patients (median age 47 years, 80.8% male), 123 completed the study with paired biopsies. Overall, the Ishak fibrosis score decreased in 74 (60.2%), remained unchanged in 32 (26.0%), and increased in 17 (13.8%) patients (p<0.0001). The Knodell necroinflammation score decreased in 58 (47.2%), remained unchanged in 29 (23.6%), and increased in 36 (29.3%) patients (p=0.0038). The proportion of patients with an Ishak score ≥ 3 significantly decreased from 26.8% (n=33) to 9.8% (n=12) (p=0.0002). Histological improvements were more pronounced in patients switching from placebo. Virological and biochemical outcomes also improved in placebo switchers and remained stable in patients who continued TDF. However, serum HBsAg levels did not change and no patient cleared HBsAg. Conclusions In CHB patients with minimally raised ALT, favorable histopathological, biochemical, and virological outcomes were observed following 3-year TDF treatment, for both treatment-naïve patients and those already on therapy.