Objective: To develop an automated, high-throughput, and reproducible method for reclassifying and validating ontological concepts for natural language processing applications.
Design: We developed a distributional similarity approach to classify the Unified Medical Language System (UMLS) concepts. Classification models were built for seven broad biomedically relevant semantic classes created by grouping subsets of the UMLS semantic types. We used contextual features based on syntactic properties obtained from two different large corpora and used alpha-skew divergence as the similarity measure.
Measurements: The testing sets were automatically generated based on the changes by the National Library of Medicine to the semantic classification of concepts from the UMLS 2005AA to the 2006AA release. Error rates were calculated and a misclassification analysis was performed.
Results: The estimated lowest error rates were 0.198 and 0.116 when considering the correct classification to be covered by our top prediction and top 2 predictions, respectively.
Conclusion: The results demonstrated that the distributional similarity approach can recommend high level semantic classification suitable for use in natural language processing.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2244895 | PMC |
| http://dx.doi.org/10.1197/jamia.M2314 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
BCT-Net: semantic-guided breast cancer segmentation on BUS.
Med Biol Eng Comput
January 2025
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, China.
Accurately and swiftly segmenting breast tumors is significant for cancer diagnosis and treatment. Ultrasound imaging stands as one of the widely employed methods in clinical practice. However, due to challenges such as low contrast, blurred boundaries, and prevalent shadows in ultrasound images, tumor segmentation remains a daunting task.
View Article and Find Full Text PDFHyperspectral images (HSI) have been extensively applied in a multitude of domains, due to their combined spatial and spectral characteristics along with a wealth of spectral bands. The ingenious combination of spatial and spectral information in HSI classification has remained a central research area for an extended period. In the classification process, it is essential to choose an expanded neighborhood window for learning.
View Article and Find Full Text PDFChemotherapy-induced nausea and vomiting: can we do better?
Curr Opin Oncol
January 2025
Gustave Roussy, Villejuif, France.
Purpose Of Review: Although the management of nausea and vomiting induced by cancer treatments has evolved, several questions remain unanswered.
Recent Findings: New antiemetics have been developed these last decades with therapeutic indications to be defined according to the anticancer regimen and partly as a consequence of the assessment of individual patient risk factors. Guidelines still seem to have a low level of knowledge and compliance, with a role for scientific societies in term of dissemination and education.
Cross-Modal Collaboration and Robust Feature Classifier for Open-Vocabulary 3D Object Detection.
Sensors (Basel)
January 2025
The 54th Research Institute, China Electronics Technology Group Corporation, College of Signal and Information Processing, Shijiazhuang 050081, China.
The multi-sensor fusion, such as LiDAR and camera-based 3D object detection, is a key technology in autonomous driving and robotics. However, traditional 3D detection models are limited to recognizing predefined categories and struggle with unknown or novel objects. Given the complexity of real-world environments, research into open-vocabulary 3D object detection is essential.
View Article and Find Full Text PDFSupporting vision-language model few-shot inference with confounder-pruned knowledge prompt.
Neural Netw
January 2025
National Key Laboratory of Space Integrated Information System, Institute of Software Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Beijing, China.
Vision-language models are pre-trained by aligning image-text pairs in a common space to deal with open-set visual concepts. Recent works adopt fixed or learnable prompts, i.e.
View Article and Find Full Text PDFWant 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!