MétaCan
Menu
Back to cohort
Record W4387615420 · doi:10.1161/res.133.suppl_1.p3144

Abstract P3144: A Deep Neural Network Algorithm For Accurate Detection Of Brugada Syndrome Features In Electrocardiograms

2023· article· en· W4387615420 on OpenAlexaff
Luke Melo, Giuseppe Ciconte, Ashton Christy, Gabriele Vicedomini, Luigi Anastasia, Edward R. Grant, Carlo Pappone

Bibliographic record

VenueCirculation Research · 2023
Typearticle
Languageen
FieldMedicine
TopicECG Monitoring and Analysis
Canadian institutionsUniversity of British Columbia
Fundersnot available
KeywordsBrugada syndromeMedicineAjmalineCohortAlgorithmInternal medicineCardiologyElectrocardiographyArtificial neural networkGold standard (test)Artificial intelligenceMachine learningComputer science

Abstract

fetched live from OpenAlex

Brugada Syndrome (BrS) is a rare but potentially fatal cardiac condition that is difficult to diagnose due to the elusive nature of its characteristic ECG pattern. The diagnosis of BrS requires identification of a specific electrocardiographic (ECG) pattern, which often appears only upon administration of sodium-channel blockers. Here, we present a deep neural network (DNN) algorithm that accurately detects BrS features in ECGs without the need for a drug challenge. We trained and validated the DNN on two independent cohorts of patients who were enrolled in electrophysiological studies for BrS diagnosis. The internal prospective validation cohort included 370 subjects, and the multicenter external validation cohort included 110 subjects from three other medical institutions in Italy. All subjects who did not present a spontaneous type 1 ECG underwent an ajmaline drug challenge to aid in confirming a BrS diagnosis. We found that the DNN approach classified ECGs for BrS with a sensitivity of 79.6%, specificity of 93.6%, accuracy of 88.4%, and area under the curve (AUC) of 0.934±0.027 in the validation cohorts. The DNN model also detected BrS with 100% accuracy in all cases in which a patient presented the spontaneous type 1 pattern. Our results demonstrate that a multivariate machine-learning algorithm can accurately detect the features of BrS in a conventional ECG without the challenge of a sodium-channel blocker. The computer-assisted analysis of digital ECG traces from current electrocardiographs might help physicians recognize patients affected by this disease. In conclusion, we have developed an advanced deep learning algorithm that can accurately detect BrS features in ECGs. Our results demonstrate that the DNN approach could be an effective tool to improve the diagnosis of BrS and potentially prevent sudden cardiac death in affected individuals.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.771
Threshold uncertainty score0.336

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.059
GPT teacher head0.384
Teacher spread0.325 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueCirculation ResearchSame topicECG Monitoring and AnalysisFrench-language works237,207