A5035163413- Topic Modeling
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Natural Language Processing Techniques
- Machine Learning in Healthcare
- Advanced Text Analysis Techniques
- Advanced Image Processing Techniques
- Cervical Cancer and HPV Research
- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- MicroRNA in disease regulation
- Text and Document Classification Technologies
- Geophysical Methods and Applications
- Advanced Vision and Imaging
- Epigenetics and DNA Methylation
- Circular RNAs in diseases
- Diet and metabolism studies
- Image and Signal Denoising Methods
- Soil Moisture and Remote Sensing
- Histone Deacetylase Inhibitors Research
- Medical Coding and Health Information
- Advanced Graph Neural Networks
- Cancer Mechanisms and Therapy
- Artificial Intelligence in Healthcare and Education
- Bioinformatics and Genomic Networks
Kunming University of Science and Technology
2024-2025
China Light Industry Press (China)
2024-2025
Shandong Academy of Sciences
2024-2025
Qilu University of Technology
2024-2025
First Teaching Hospital of Tianjin University of Traditional Chinese Medicine
2024
Union Hospital
2019-2024
Jilin University
2011-2024
eBay (United States)
2024
Nanjing Medical University
2022-2024
Nanjing University
2023-2024
Abstract Objectives The aim of this study was to investigate GPT-3.5 in generating and coding medical documents with International Classification Diseases (ICD)-10 codes for data augmentation on low-resource labels. Materials Methods Employing we generated coded 9606 discharge summaries based lists ICD-10 code descriptions patients infrequent (or generation) within the MIMIC-IV dataset. Combined baseline training set, formed an augmented set. Neural models were trained evaluated test We...
This study is to evaluate the dose calculation accuracy using Varian's cone-beam CT (CBCT) for pelvic adaptive radiotherapy. We first calibrated Hounsfield Unit (HU) electron density (ED) CBCT a mini QC phantom embedded into an IMRT QA phantom. then used Catphan 500 with annulus around it check calibration. The combined and provided correct HU calibration, but not annulus. For latter, only was Teflon incorrect substitute bone, inserts were also too small provide HUs air bone. former, three...
Panax ginseng has long been used in Asia as a herbal medicine for the prevention and treatment of various diseases, including cancer. The current study evaluated cytotoxic potency against variety cancer cells by using ethanol extracts (RSE), protopanaxadiol (PPD)-type, protopanaxatriol (PPT)-type ginsenosides fractions, their hydrolysates, which were prepared stepwise hydrolysis sugar moieties ginsenosides. results showed that hydrolysates RSE total PPD-type or PPT-type ginsenoside fractions...
Abstract The coronavirus disease 2019 (COVID-19) pandemic has been severely impacting global society since December 2019. related findings such as vaccine and drug development have reported in biomedical literature—at a rate of about 10 000 articles on COVID-19 per month. Such rapid growth significantly challenges manual curation interpretation. For instance, LitCovid is literature database COVID-19-related PubMed, which accumulated more than 200 with millions accesses each month by users...
Computational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due few cases available for machine learning need data annotation domain experts. We propose a method using ontologies weak supervision, recent pre-trained contextual representations Bi-directional Transformers (e.g. BERT). The ontology-based framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by...
Abstract Single‐cell epigenetics is envisioned to decipher manifold epigenetic phenomena and contribute our accurate knowledge about basic mechanisms. Engineered nanopipette technology has gained momentum in single‐cell studies; however, solutions questions remain unachieved. This study addresses the challenge by exploring N6‐methyladenine (m 6 A)‐bearing deoxyribozyme (DNAzyme) confined within a for profiling representative m A‐modifying enzyme, fat mass obesity‐associated protein (FTO)....
Integrating deep learning techniques, particularly language models (LMs), with knowledge representation techniques like ontologies has raised widespread attention, urging the need of a platform that supports both paradigms. Although packages such as OWL API and Jena offer robust support for basic ontology processing features, they lack capability to transform various types information within into formats suitable downstream learning-based applications. Moreover, widely-used APIs are...
Purpose: Circular RNA (circRNA) is a key regulatory factor in the development and progression of human tumors. However, working mechanism clinical significance most circRNAs remain unknown cancers, including multiple myeloma (MM). Patients Methods: This study employs high-throughput circRNA microarray with bioinformatics to identify differentially expressed patients MM. The hsa_circ_0007841 expressions were observed MM tissues 86 patients. Drug-resistant cell lines pathological features also...
This study investigates motivations for self‐archiving research items on academic social networking sites (ASNSs). A model of these was developed based two existing motivation models: in academia and information sharing media. The proposed is composed 18 factors drawn from personal, social, professional, external contexts, including enjoyment, personal/professional gain, reputation, learning, self‐efficacy, altruism, reciprocity, trust, community interest, engagement, publicity,...
Aim: This study aimed to use machine learning algorithms identify critical preoperative variables and predict the red blood cell (RBC) transfusion during or after liver transplantation surgery. Study Design Methods: A total of 1,193 patients undergoing in three large tertiary hospitals China were examined. Twenty-four collected, including essential population characteristics, diagnosis, symptoms, laboratory parameters. The cohort was randomly split into a train set (70%) validation (30%)....
The success of the state-of-the-art video deblurring methods stems mainly from implicit or explicit estimation alignment among adjacent frames for latent restoration. However, due to influence blur effect, estimating information blurry is not a trivial task. Inaccurate estimations will interfere following frame Instead information, we propose simple and effective deep Recurrent Neural Network with Multi-scale Bi-directional Propagation (RNN-MBP) effectively propagate gather unaligned...
Herein, the first iontronic photoelectrochemical (PEC) biorecognition probing is devised by rational engineering of a dual-functional bioconjugate, i.e., light-sensitive intercalated structural DNA, as smart gating module confined within nanotip, which could respond to both incident light and biotargets interest. Light stimulation bioconjugate intensify negative charge at nano-orifice sustain enhanced ionic current. The presence proteins (e.g., acetylcholinesterase, AChE) or nucleic acids...
Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence heterogeneous clinical presentations. Unstructured notes contain valuable information for identifying rare diseases, but manual curation is time-consuming prone subjectivity. This study aims develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large models (LLMs) improve disease identification from unstructured reports.
This study employs 3-aminopropyltriethoxysilane (APTS) to eliminate the hydrophilic hydroxyl groups on surface of silica, followed by use defunctionalized silica as a filler and boric acid (BA) crosslinking agent prepare polyvinyl alcohol (PVA)/silica coating. The experimental results indicate that coating not only reduces inherent hydrophilicity PVA, but also enhances uniformity film forming properties coating, providing solid foundation for patterning leather surfaces. characterization...
Symmetry-protected topological phases cannot be described by any local order parameter and are beyond the conventional symmetry-breaking paradigm for understanding quantum matter. They characterized boundary states robust against perturbations that respect protecting symmetry. In a clean system without disorder, these edge modes typically only occur ground of systems with bulk energy gap would not survive at finite temperatures due to mobile thermal excitations. Here, we report observation...