Dynamic data balancing strategy-based Xception-dual-channel LSTM model for laparoscopic cholecystectomy phase recognition.

Purpose: To enhance the temporal feature learning capability of the laparoscopic cholecystectomy phase recognition model and address the class imbalance issue in the training data, this paper proposes an Xception-dual-channel LSTM fusion model based on a dynamic data balancing strategy.

Methods: The model dynamically adjusts the undersampling rate for each surgical phase, extracting short video clips from the original data as training samples to balance the data distribution and mitigate biased learning. The Xception model, utilizing depthwise separable convolutions, extracts fundamental visual features frame by frame, which are then passed to a dual-channel LSTM network.

[Multi-system involvement characteristics and influencing factors of disease progression in Kennedy's disease].

To investigate multi-system involvement in Kennedy's disease and its association with disease progression. We retrospectively reviewed the clinical, laboratory, and electrophysiological data from 48 genetically confirmed patients with Kennedy's disease at the Department of Neurology, First Medical Center of the Chinese PLA General Hospital, between February 2016 and February 2024. The disease progression rate was calculated based on the functional scores at baseline and follow-up.

[A case of occupational allergic contact dermatitis caused by sinomenine hydrochloride].

Sinomenine hydrochloride is an alkaloid preparation commonly used in clinical practice in traditional Chinese medicine, and allergic reactions induced by occupational exposure to it are relatively rare in clinical settings. This article analyzes a case of allergic contact dermatitis in a medical worker after occupational exposure to sinomenine hydrochloride. The patient developed generalized skin rashes with the fingertips as the initial site three months after exposure to sinomenine hydrochloride.

Bacillus thuringiensis G-5 efficiently suppresses Codonopsis pilosula postharvest diseases by generating antifungal volatile organic compounds.

Inappropriate storage conditions make Codonopsis pilosula more susceptible to infection by harmful fungi because of moisture, which reduces the plant's therapeutic effectiveness. The volatile organic compounds (VOCs) of plant endophytes have shown great promise in recent years for managing postharvest plant diseases. This study investigates the inhibitory effects of VOCs released by Bacillus thuringiensis G-5 on two postharvest pathogenic fungi of C.

Antibiotic therapy for severe bacterial infections.

Background: Early antibiotic therapy for patients with severe infections is essential to improve outcomes. Conversely, use of overly broad antibiotic therapy for susceptible pathogens or unnecessary antibiotics in patients without bacterial infections is associated with adverse life-threatening events and superinfections. Antibiotics-induced changes in the human microbiota alter both immune and metabolic systems.