Measures of semantic similarity between concepts are widely used in Natural Language Processing. In this article, we show how six existing domain-independent measures can be adapted to the biomedical domain. These measures were originally based on WordNet, an English lexical database of concepts and relations. In this research, we adapt these measures to the SNOMED-CT ontology of medical concepts. The measures include two path-based measures, and three measures that augment path-based measures with information content statistics from corpora. We also derive a context vector measure based on medical corpora that can be used as a measure of semantic relatedness. These six measures are evaluated against a newly created test bed of 30 medical concept pairs scored by three physicians and nine medical coders. We find that the medical coders and physicians differ in their ratings, and that the context vector measure correlates most closely with the physicians, while the path-based measures and one of the information content measures correlates most closely with the medical coders. We conclude that there is a role both for more flexible measures of relatedness based on information derived from corpora, as well as for measures that rely on existing ontological structures.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.jbi.2006.06.004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Drug Development.
Alzheimers Dement
December 2024
Alzheimer Center Amsterdam, Neurology, Vrije Universiteit Amsterdam, Amsterdam UMC location VUmc, Amsterdam, North Holland, Netherlands.
The lack of an in-vivo pathology marker for synuclein pathology has been a long standing challenge for dementia for Lewy bodies (DLB) research. This issue is critically important for phase II trials, which are often small, requiring the precise measurement of the biological effects, whether disease modifying or symptomatic. Recent advances have enabled the determination of alpha-synuclein pathology status with CSF measurements, using aggregation assays [RT-QUIC].
View Article and Find Full Text PDFBackground: Lecanemab is a humanized IgG1 monoclonal antibody that binds with high affinity to Aβ soluble protofibrils. In two clinical studies (phase 2, NCT01767311 and phase 3 ClarityAD, NCT03887455) in early Alzheimer's disease, lecanemab substantially reduced amyloid PET and significantly slowed clinical decline on multiple measures of cognition and function, including CDR-SB at 18 months. Models describing the change in amyloid PET and CDR-SB in response to lecanemab treatment were used to explore the impact of changing from the initial dosage regimen (10 mg/kg every 2 weeks [Q2W]) to a less intensive maintenance dosing regimen (10 mg/kg every 4 weeks [Q4W]) on clinical efficacy, and to explore the optimal duration of the initial dosing regimen.
View Article and Find Full Text PDFDrug Development.
Alzheimers Dement
December 2024
Department of Anesthesiology and Critical Care, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, U.S.A., Philadelphia, PA, USA.
Background: The vicious cycle between depression and dementia increases the risk of Alzheimer's Disease (AD) pathogenesis and pathology. This study investigates therapeutic effectiveness versus side effects and the underlying mechanisms of intranasal dantrolene nanoparticles (IDNs) to treat depression behavior and memory loss in 5XFAD mice.
Method: 5XFAD and wild-type B6SJLF1/J mice were treated with IDNs (IDN, 5 mg/kg) in Ryanodex formulation for a duration of 12 weeks.
Background: In Alzheimer's Disease trials, the Mini-Mental State Examination (MMSE) and Clinical Dementia Rating (CDR) are commonly utilized as inclusionary criteria at screening. These measures, however, do not always reaffirm inclusionary status at baseline. Score changes between screening and baseline visits may imply potential score inflation at screening leading to inappropriate participant enrollment.
View Article and Find Full Text PDFBackground: Clinical outcome assessments (COAs) are an important part of clinical trials to measure what is meaningful to patients and caregivers. This study aimed to examine trends in Alzheimer's Disease (AD) COAs used in clinical trials, given the FDA's recent emphasis on patient-focused drug development and early AD.
Method: ClinicalTrials.
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!