Background: Word sense disambiguation (WSD) methods automatically assign an unambiguous concept to an ambiguous term based on context, and are important to many text-processing tasks. In this study we developed and evaluated a knowledge-based WSD method that uses semantic similarity measures derived from the Unified Medical Language System (UMLS) and evaluated the contribution of WSD to clinical text classification.
Methods: We evaluated our system on biomedical WSD datasets and determined the contribution of our WSD system to clinical document classification on the 2007 Computational Medicine Challenge corpus.
Results: Our system compared favorably with other knowledge-based methods. Machine learning classifiers trained on disambiguated concepts significantly outperformed those trained using all concepts.
Conclusions: We developed a WSD system that achieves high disambiguation accuracy on standard biomedical WSD datasets and showed that our WSD system improves clinical document classification.
Data Sharing: We integrated our WSD system with MetaMap and the clinical Text Analysis and Knowledge Extraction System, two popular biomedical natural language processing systems. All codes required to reproduce our results and all tools developed as part of this study are released as open source, available under http://code.google.com/p/ytex.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3756260 | PMC |
| http://dx.doi.org/10.1136/amiajnl-2012-001350 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Fusion of Visible and Infrared Aerial Images from Uncalibrated Sensors Using Wavelet Decomposition and Deep Learning.
Sensors (Basel)
December 2024
Department of Electrical and Computer Engineering, University of Missouri, Columbia, MO 65211, USA.
Multi-modal systems extract information about the environment using specialized sensors that are optimized based on the wavelength of the phenomenology and material interactions. To maximize the entropy, complementary systems operating in regions of non-overlapping wavelengths are optimal. VIS-IR (Visible-Infrared) systems have been at the forefront of multi-modal fusion research and are used extensively to represent information in all-day all-weather applications.
View Article and Find Full Text PDFGene-diet interactions in carbonated sugar-sweetened beverage consumption and metabolic syndrome risk: A machine learning analysis in a large hospital-based cohort.
Clin Nutr ESPEN
December 2024
Dept. of Food and Nutrition, Obesity/Diabetes Research Center, Hoseo University, Asan, South Korea.
Article Synopsis
- The study investigates the relationship between carbonated sugar-sweetened beverage (CSSB) intake and the risk of metabolic syndrome (MetS), considering both genetic factors and dietary habits.
- Analyzing data from 57,940 participants, it categorizes them into low-CSSB and high-CSSB groups, revealing that high consumers also have poorer dietary patterns and higher consumption of unhealthy foods.
- The research highlights that genetic predisposition, assessed through specific genetic markers, interacts with diet type, indicating that tailored dietary recommendations may help reduce MetS risk, especially for those with higher CSSB intake and Western-style diets.
Investigation of kinetics, reaction mechanisms, thermodynamics, and synergetic effects in co-pyrolysis of wood sawdust and linear low-density polyethylene using the thermogravimetric approach.
Environ Sci Pollut Res Int
September 2024
Department of Environmental Science and Engineering, Indian Institute of Technology (Indian School of Mines, Dhanbad, Jharkhand, 826004, India.
Article Synopsis
- - This study explored how mixing wood sawdust (WSD) with linear low-density polyethylene (LLDPE) affects their thermal degradation during co-pyrolysis, revealing that the LW1:3 blend (25 wt.% LLDPE) loses mass at lower temperatures compared to the individual materials.
- - Various reaction mechanisms and kinetic parameters were analyzed, showing that the LW1:3 blend had the highest drop in activation energy, indicating it reacts more easily under pyrolysis conditions.
- - The thermodynamic analysis confirms that adding a small amount of plastic to WSD enhances reactivity and reduces the energy required for the process, making the co-pyrolysis more efficient and beneficial for reactor design.
Integrating point-of-care diabetes detection with lifestyle counselling in community settings: outcomes from Western Sydney, Australia.
BMC Health Serv Res
August 2024
Western Sydney Diabetes (WSD), Western Sydney Local Health District (WSLHD), Sydney, Australia.
Article Synopsis
- Early detection of type 2 diabetes is crucial, and this study assesses a community-based program in western Sydney aimed at identifying and managing diabetes risks among high-risk populations.
- The program involved partnerships with local community organizations, offering HbA1C testing, personalized feedback, education, and referrals to lifestyle modification programs, with follow-up surveys conducted to measure effectiveness.
- Results showed a high prevalence of pre-diabetes and diabetes among participants, with positive feedback indicating that the program successfully encouraged healthier lifestyles and greater engagement with healthcare providers.*
Three-dimensional simultaneous T1 and T2* relaxation times and quantitative susceptibility mapping at 3 T: A multicenter validation study.
Magn Reson Imaging
October 2024
Department of Radiology, Juntendo University, 1-2-1 Hongo, Bunkyo-ku, Tokyo 113-8421, Japan; Department of Health Data Science, Faculty of Health Data Science, Juntendo University, 6-8-1 Hinode, Urayasu, Chiba 279-0013, Japan.
Article Synopsis
- The study assessed the repeatability of T1 and T2* relaxation times and quantitative susceptibility (χ) values using quantitative parameter mapping (QPM) across three different 3T MRI scanners at three sites.
- Twelve healthy volunteers underwent three separate scans at each site, and various statistical analyses were used to measure consistency and variation.
- Results showed high intra-site repeatability for all measured values (T1, T2*, and χ) and acceptable cross-site reproducibility, suggesting QPM can reliably support multisite studies in MRI research.
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!