Publications by authors named "D Radev"
Purpose: Assessment of scaphoid union after operative treatment might be associated with uncertainty, disagreement, and misinterpretation. Union is defined as consolidation on three of four X-ray views. Computed tomography (CT) scans are increasingly used to evaluate union of scaphoid fractures and nonunion.
View Article and Find Full Text PDFArticle Synopsis
- Medical texts are difficult to manage and time-consuming to curate manually, prompting the development of NLP algorithms to automate this process for improved efficiency in the biomedical field.
- The study introduces Ascle, a user-friendly tool designed for biomedical researchers that offers generative functions like question-answering and text summarization, along with 12 essential NLP functions and search capabilities.
- After fine-tuning 32 language models and validating through physician assessments, results showed significant improvements in text generation tasks, with notable increases in machine translation and question-answering accuracy.
Background Due to conflicting findings in the literature, there are concerns about a lack of objectivity in grading knee osteoarthritis (KOA) on radiographs. Purpose To examine how artificial intelligence (AI) assistance affects the performance and interobserver agreement of radiologists and orthopedists of various experience levels when evaluating KOA on radiographs according to the established Kellgren-Lawrence (KL) grading system. Materials and Methods In this retrospective observer performance study, consecutive standing knee radiographs from patients with suspected KOA were collected from three participating European centers between April 2019 and May 2022.
View Article and Find Full Text PDFObjective: To investigate potential differences in structural knee joint damage assessed by MRI and patient-reported outcomes (PROMs) at 2-year follow-up between young adults randomised to early surgery or exercise and education with optional delayed surgery for a meniscal tear.
Methods: A secondary analysis of a multicentre randomised controlled trial including 121 patients (18-40 years) with an MRI-verified meniscal tear. For this study, only patients with 2-year follow-up were included.
Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the limited quantity of structural data. Meanwhile, protein language models trained on substantial 1D sequences have shown burgeoning capabilities with scale in a broad range of applications.
View Article and Find Full Text PDF