FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377197214> ?p ?o ?g. }

• W4377197214 endingPage "S256" @default.
• W4377197214 startingPage "S256" @default.
• W4377197214 abstract "Brugada Syndrome (BrS) is a lethal cardiac rhythm disorder that can result in life threatening arrhythmias and carries high risk of sudden cardiac death. The gold standard treatment is implantation of an ICD. Statistical models have been developed to ascertain if a patient should receive an ICD. Previously, we compared a machine learning approach to existing statistical models (Siddiqui and Gonzalez Corcia, 2021). The statistical model was designed to stratify the risk of lethal cardiac events in a young population (<20 years old). Our research found that using additional variables improved the accuracy of our model as compared to the statistical approaches. We now explore further variables to determine whether the accuracy of the predictions can be improved. The initial project undertook a study that compared a statistical model developed by Gonzalez Corcia et al. (2017) with machine learning models using a 2-Step methodology. The statistical model used four clinical variables (Symptoms, Spontaneous Type I ECG, Sinus Node Dysfunction/Atrial (Tachycardia and Conduction Abnormality). We found that adding four more variables (Genotype for Brugada, Cardiac Electrophysiology Study, Ajmaline Challenge and patient’s gender) improved the accuracy of the predictions (from 0.93 to 0.988). Here we add two further steps to explore further combinations of variables. In Step 3, in addition to the original variables we add Baseline PR interval, , Baseline QRS in V1, Baseline QTc, Genotype and Gender. In Step 4, we add Ajmaline Challenge, EP Study, PR interval, QTc and QRS after the Ajmaline challenge along with the original four variables. In Step 3, we trained a Random Forest classifier resulting in a prediction accuracy of 0.966. In Step 4, a Random Forest classifier resulted in a prediction accuracy of 0.931. This confirms that Step 2 from the original research is the optimal combination of variables that can help clinicians decide if a paediatric patient should receive an ICD. This research further confirms that Machine learning can play an integral role in improving clinical practice and patient outcomes, particularly given the psychological implications of having an ICD at a young age. This is true even though it is a life saving device in case of sudden cardiac arrest/lethal ventricular arrhythmias. The importance of this research is further proven by the fact that implanting an ICD in a young person remains controversial." @default.
• W4377197214 created "2023-05-22" @default.
• W4377197214 creator A5015116406 @default.
• W4377197214 creator A5056252875 @default.
• W4377197214 date "2023-05-01" @default.
• W4377197214 modified "2023-09-27" @default.
• W4377197214 title "PO-01-055 USING MACHINE LEARNING TECHNIQUES TO PREDICT WHETHER A PAEDIATRIC PATIENT WITH BRUGADA SYNDROME SHOULD RECEIVE AN ICD" @default.
• W4377197214 doi "https://doi.org/10.1016/j.hrthm.2023.03.704" @default.
• W4377197214 hasPublicationYear "2023" @default.
• W4377197214 type Work @default.
• W4377197214 citedByCount "0" @default.
• W4377197214 crossrefType "journal-article" @default.
• W4377197214 hasAuthorship W4377197214A5015116406 @default.
• W4377197214 hasAuthorship W4377197214A5056252875 @default.
• W4377197214 hasBestOaLocation W43771972141 @default.
• W4377197214 hasConcept C111773187 @default.
• W4377197214 hasConcept C118441451 @default.
• W4377197214 hasConcept C126322002 @default.
• W4377197214 hasConcept C164705383 @default.
• W4377197214 hasConcept C2775935837 @default.
• W4377197214 hasConcept C2776331378 @default.
• W4377197214 hasConcept C2777382798 @default.
• W4377197214 hasConcept C2779578097 @default.
• W4377197214 hasConcept C2779703243 @default.
• W4377197214 hasConcept C2779801569 @default.
• W4377197214 hasConcept C2908647359 @default.
• W4377197214 hasConcept C65409693 @default.
• W4377197214 hasConcept C71924100 @default.
• W4377197214 hasConcept C99454951 @default.
• W4377197214 hasConceptScore W4377197214C111773187 @default.
• W4377197214 hasConceptScore W4377197214C118441451 @default.
• W4377197214 hasConceptScore W4377197214C126322002 @default.
• W4377197214 hasConceptScore W4377197214C164705383 @default.
• W4377197214 hasConceptScore W4377197214C2775935837 @default.
• W4377197214 hasConceptScore W4377197214C2776331378 @default.
• W4377197214 hasConceptScore W4377197214C2777382798 @default.
• W4377197214 hasConceptScore W4377197214C2779578097 @default.
• W4377197214 hasConceptScore W4377197214C2779703243 @default.
• W4377197214 hasConceptScore W4377197214C2779801569 @default.
• W4377197214 hasConceptScore W4377197214C2908647359 @default.
• W4377197214 hasConceptScore W4377197214C65409693 @default.
• W4377197214 hasConceptScore W4377197214C71924100 @default.
• W4377197214 hasConceptScore W4377197214C99454951 @default.
• W4377197214 hasIssue "5" @default.
• W4377197214 hasLocation W43771972141 @default.
• W4377197214 hasOpenAccess W4377197214 @default.
• W4377197214 hasPrimaryLocation W43771972141 @default.
• W4377197214 hasRelatedWork W1734509126 @default.
• W4377197214 hasRelatedWork W1966401982 @default.
• W4377197214 hasRelatedWork W1968088618 @default.
• W4377197214 hasRelatedWork W1973160752 @default.
• W4377197214 hasRelatedWork W2027655243 @default.
• W4377197214 hasRelatedWork W2034455015 @default.
• W4377197214 hasRelatedWork W2163937281 @default.
• W4377197214 hasRelatedWork W2280346775 @default.
• W4377197214 hasRelatedWork W4367044915 @default.
• W4377197214 hasRelatedWork W2518854066 @default.
• W4377197214 hasVolume "20" @default.
• W4377197214 isParatext "false" @default.
• W4377197214 isRetracted "false" @default.
• W4377197214 workType "article" @default.