Predicting the toxicity of molecules is essential in fields like drug discovery, environmental protection, and industrial chemical management. While traditional experimental methods are time-consuming and costly, computational models offer an efficient alternative. In this study, we introduce ToxinPredictor, a machine learning-based model to predict the toxicity of small molecules using their structural properties.
View Article and Find Full Text PDFBackground: Longitudinal tracking of multiple sclerosis (MS) symptoms in an individual's own environment may improve self-monitoring and clinical management for people with MS (pwMS).
Objective: We present a machine learning approach that enables longitudinal monitoring of clinically relevant patient-reported symptoms for pwMS by harnessing passively collected data from sensors in smartphones and fitness trackers.
Methods: We divide the collected data into discrete periods for each patient.
Background: Vaccination has been shown to attenuate the risk of post-acute sequelae following SARS-CoV-2 infection. However, no prior population-based studies have evaluated if updated bivalent boosters reduce risk of post-acute sequelae following Omicron-variant infection, versus ancestral vaccines.
Methods: National databases were utilised to construct a population-based cohort of adult individuals infected during Omicron-predominant transmission.
Introduction: Transarterial chemoembolization (TACE) has an established role in advanced HCC. The present study evaluates the role of TACE as a neoadjuvant modality in the management of intermediate HCC [Hong Kong Liver Cancer (HKLC) stage IIB].
Materials And Methods: A retrospective analysis of HCC patients treated between January 2010 and August 2022 was performed.