There is a rapid growth in the volume of data in the cancer field and fine-grained classification is in high demand especially for interdisciplinary and collaborative research. There is thus a need to establish a multi-label classifier with higher resolution to reduce the burden of screening articles for clinical relevance. This research trains a multi-label classifier with scalability for classifying literature on cancer research directly at the publication level. Firstly, a corpus was divided into a training set and a testing set at a ratio of 7:3. Secondly, we compared the performance of classifiers developed by "PubMedBERT + TextRNN" and "BioBERT + TextRNN" with ICRP CT. Finally, the classifier was obtained based on the optimal combination "PubMedBERT + TextRNN", with P= 0.952014, R=0.936696, F1=0.931664. The quantitative comparisons demonstrate that the resulting classifier is fit for high-resolution classification of cancer literature at the publication level to support accurate retrieving and academic statistics.

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI240425DOI Listing

Publication Analysis

Top Keywords

publication level
12
"pubmedbert textrnn"
12
cancer literature
8
multi-label classifier
8
classifier
5
multi-label text
4
text classifier
4
classifier publication
4
level based
4
based "pubmedbert
4

Similar Publications

Background: This study aimed to provide a comprehensive review of adverse events (AEs) associated with factor Xa (FXa) inhibitors in pediatric patients.

Methods: We searched PubMed, Embase, Cochrane Library, ClinicalTrials.gov, and the European Union Clinical Trials Register for English-language records from the establishment of the database up to October 17, 2023.

View Article and Find Full Text PDF

Introduction: Colorectal cancer (CRC) is the second most common cause of cancer-related deaths globally. The gut microbiota, along with adenomatous polyps (AP), has emerged as a plausible contributor to CRC progression. This study aimed to scrutinize the impact of the FadA antigen derived from Fusobacterium nucleatum on the expression levels of the ANXA2 ceRNA network and assess its relevance to CRC advancement.

View Article and Find Full Text PDF

Introduction: Therapeutic drug monitoring (TDM) in inflammatory rheumatic diseases (RMDs) is gaining interest. However, there are unresolved questions about the best practices for implementing TDM effectively in clinical settings.

Objective: The primary objective of this study was to evaluate whether early TDM of adalimumab predicts drug survival at 52 weeks in patients with RMDs.

View Article and Find Full Text PDF

Objectives: To investigate the clinical and laboratory features of Sjögren's syndrome-associated autoimmune liver disease (SS-ALD) patients and identify potential risk and prognostic factors.

Methods: SS patients with or without ALD, who visited Tongji Hospital between the years 2011 and 2021 and met the 2012 American College of Rheumatology (ACR) classification criteria for Sjögren's syndrome, were retrospectively enrolled. The clinical and laboratory data of the enrolled patients, including autoimmune antibodies, were collected and analyzed with principal component analysis, correlation analysis, LASSO regression, and Cox regression.

View Article and Find Full Text PDF

Impact of hemoadsorption with CytoSorb® on meropenem and piperacillin exposure in critically ill patients in a post-CKRT setup: a single-center, retrospective data analysis.

Intensive Care Med Exp

January 2025

Freie Universität Berlin and Humboldt-Universität Zu Berlin, Department of Anesthesiology and Intensive Care Medicine, Charité-Universitätsmedizin Berlin, Campus Benjamin Franklin, Berlin, Germany.

Purpose: CytoSorb® (CS) adsorbent is a hemoadsorption filter for extracorporeal blood purification often integrated into continuous kidney replacement therapy (CKRT). It is primarily used in critically ill patients with sepsis and related conditions, including cytokine storms and systemic inflammatory responses. Up to now, there is no evidence nor recommendation for the use of CS filters in sepsis (22).

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!