FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3215454871> ?p ?o ?g. }

• W3215454871 abstract "Introduction: Increasing prevalence of multimorbidity (>2 conditions) put individuals, especially older adults, at increased risk for acute coronary syndrome (ACS). Machine learning techniques provide an opportunity to identify clinical factors associated with multimorbidity that may aid in identifying subgroups of multimorbid patients that are at higher risk for ACS. Our primary objective was to use machine learning techniques to identify factors associated multimorbidity in individuals presenting to the emergency department (ED) for potential ACS. Hypothesis: Markers of chronologic and physiologic aging are associated with multimorbidity and vary by functional status and inflammatory profiles. Methods: This was a secondary analysis of data collected from a large multi-site study aimed at characterizing sex differences in symptoms suggestive of ACS in the ED. Variables of interests were measured with the Charlson Comorbidity Index, the Duke Activity Status Index, and serum cytokines (TNF-α, IL-6, and IL-18). A logistic regression model was applied to a sample of 414 patients utilizing a 70/30 test/train split to determine if biomarkers, functional status, sex, and age were associated with multimorbidity. Results: Patients were predominantly male (62.5%), white (73.0%), and had a mean age of 58.9 years. The accuracy of the model in predicting multimorbidity was 86.8% in the training set (n=290). In validation testing, accuracy was 73.0% (n=124). Functional status (OR .960, 95% CI .94-.206, p<0.000), age (OR 1.10, 95% CI 1.04-1.10, p<0.000), and TNF- α (OR 2.21, 95% CI 1.17-4.45, p<0.000), were associated with multimorbidity. The overall model was significant with a χ 2 (286, N=71.1) = 6, p>0.05. A responder operator curve was run on the individual variables and age, functional status, and TNF- α and showed significant discrimination levels (c-statistic 0.74, 0.73, and 0.65, respectively). Conclusions: Multimorbidity increases the risk for ACS. TNF-α, functional status, and age improved models of ACS risk stratification in a heterogeneous sample of multimorbid patients. Machine learning methodologies exhibit utility in identifying potential clinical markers of multimorbidity." @default.
• W3215454871 created "2021-12-06" @default.
• W3215454871 creator A5034122594 @default.
• W3215454871 creator A5075737093 @default.
• W3215454871 creator A5081242284 @default.
• W3215454871 date "2021-11-16" @default.
• W3215454871 modified "2023-09-25" @default.
• W3215454871 title "Abstract 12915: Machine Learning Models Show That Age, Functional Status, and TNF-α Accurately Predicts Multimorbidity in Acute Coronary Syndrome" @default.
• W3215454871 doi "https://doi.org/10.1161/circ.144.suppl_1.12915" @default.
• W3215454871 hasPublicationYear "2021" @default.
• W3215454871 type Work @default.
• W3215454871 sameAs 3215454871 @default.
• W3215454871 citedByCount "0" @default.
• W3215454871 crossrefType "journal-article" @default.
• W3215454871 hasAuthorship W3215454871A5034122594 @default.
• W3215454871 hasAuthorship W3215454871A5075737093 @default.
• W3215454871 hasAuthorship W3215454871A5081242284 @default.
• W3215454871 hasConcept C118552586 @default.
• W3215454871 hasConcept C126322002 @default.
• W3215454871 hasConcept C151956035 @default.
• W3215454871 hasConcept C2777698277 @default.
• W3215454871 hasConcept C2779159551 @default.
• W3215454871 hasConcept C2780724011 @default.
• W3215454871 hasConcept C2909273474 @default.
• W3215454871 hasConcept C3019063607 @default.
• W3215454871 hasConcept C500558357 @default.
• W3215454871 hasConcept C71924100 @default.
• W3215454871 hasConcept C74909509 @default.
• W3215454871 hasConceptScore W3215454871C118552586 @default.
• W3215454871 hasConceptScore W3215454871C126322002 @default.
• W3215454871 hasConceptScore W3215454871C151956035 @default.
• W3215454871 hasConceptScore W3215454871C2777698277 @default.
• W3215454871 hasConceptScore W3215454871C2779159551 @default.
• W3215454871 hasConceptScore W3215454871C2780724011 @default.
• W3215454871 hasConceptScore W3215454871C2909273474 @default.
• W3215454871 hasConceptScore W3215454871C3019063607 @default.
• W3215454871 hasConceptScore W3215454871C500558357 @default.
• W3215454871 hasConceptScore W3215454871C71924100 @default.
• W3215454871 hasConceptScore W3215454871C74909509 @default.
• W3215454871 hasIssue "Suppl_1" @default.
• W3215454871 hasLocation W32154548711 @default.
• W3215454871 hasOpenAccess W3215454871 @default.
• W3215454871 hasPrimaryLocation W32154548711 @default.
• W3215454871 hasRelatedWork W2038070146 @default.
• W3215454871 hasRelatedWork W2081454999 @default.
• W3215454871 hasRelatedWork W2088157814 @default.
• W3215454871 hasRelatedWork W2415222164 @default.
• W3215454871 hasRelatedWork W2588773192 @default.
• W3215454871 hasRelatedWork W2804805127 @default.
• W3215454871 hasRelatedWork W2991357112 @default.
• W3215454871 hasRelatedWork W3012959175 @default.
• W3215454871 hasRelatedWork W3215454871 @default.
• W3215454871 hasRelatedWork W4321341361 @default.
• W3215454871 hasVolume "144" @default.
• W3215454871 isParatext "false" @default.
• W3215454871 isRetracted "false" @default.
• W3215454871 magId "3215454871" @default.
• W3215454871 workType "article" @default.