November 1, 2018EP EuropaceOpen Access

An extended support vector machine model including T-wave morphology features improved the diagnosis of long QT syndrome compared to a baseline model (AUC 0.901 vs 0.821).

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Long QT syndrome (LQTS) (n=688). Intervention: Extended support vector machine model including T-wave morphology features vs. Baseline model (age, gender, RR, QT, and QTc intervals). Primary outcome: Area under the receiver-operating characteristic curve (AUC) for diagnosing LQTS.

View Full Paper

Ask AI

Bookmark

Why the study?

Does a support vector machine-based model incorporating T-wave morphology improve diagnostic accuracy for long QT syndrome compared to standard ECG intervals in patients and relatives?

Population

688 digital 12-lead ECGs from genotype-positive long QT syndrome patients and genotype-negative relatives at…

Comparison

Support vector machine-based extended model… vs Baseline model using only age, gender…

Design

Cohort

Key result

An extended support vector machine model including T-wave morphology features improved the diagnosis of long QT syndrome compared to a baseline model (AUC 0.901 vs 0.821).

Authors

BHB J M Hermans JSJob Stoks FBFrank C. Bennis

Discussion

Member takes

Overview

May aid LQTS diagnosis via T-wave ML models; leaves open prospective validation before clinical adoption.

Study Design

Type

Observational (n=688)

Structured PICO

Does a support vector machine-based model incorporating T-wave morphology improve diagnostic accuracy for long QT syndrome compared to standard ECG intervals in patients and relatives?

Population

688 digital 12-lead ECGs from genotype-positive LQTS patients and genotype-negative relatives at their first visit.

Exposure

Support vector machine-based extended model incorporating T-wave morphology features along with age, gender, RR-interval, QT-interval, and QTc-intervals

Comparator

Baseline model using only age, gender, RR-interval, QT-interval, and QTc-intervals, as well as clinically used QTc-interval cut-off values (>480 ms)

Outcome

Diagnostic accuracy for LQTS measured by Area Under the Receiver-Operating Characteristic Curve (AUC)surrogate

Main Result

Absolute Event Rate: 0.901% vs 0.821%

Incorporating T-wave morphology markers into a support vector machine model significantly improves the diagnostic accuracy for long QT syndrome compared to standard ECG intervals.

Cite This Study

Hermans et al. (2018) conducted an observational in Long QT syndrome (LQTS) (n=688). Extended support vector machine model including T-wave morphology features vs. Baseline model (age, gender, RR, QT, and QTc intervals) was evaluated on Area under the receiver-operating characteristic curve (AUC) for diagnosing LQTS. An extended support vector machine model including T-wave morphology features improved the diagnosis of long QT syndrome compared to a baseline model (AUC 0.901 vs 0.821).

synapsesocial.com/papers/6a22554725ab022a514501c3 https://doi.org/10.1093/europace/euy243

View Full Paper

Ask AI

Bookmark

November 1, 2018EP EuropaceOpen Access

An extended support vector machine model including T-wave morphology features improved the diagnosis of long QT syndrome compared to a baseline model (AUC 0.901 vs 0.821).

View Full Paper

Ask AI

Bookmark

Why the study?

Does a support vector machine-based model incorporating T-wave morphology improve diagnostic accuracy for long QT syndrome compared to standard ECG intervals in patients and relatives?

Population

688 digital 12-lead ECGs from genotype-positive long QT syndrome patients and genotype-negative relatives at…

Comparison

Support vector machine-based extended model… vs Baseline model using only age, gender…

Design

Cohort

Key result

An extended support vector machine model including T-wave morphology features improved the diagnosis of long QT syndrome compared to a baseline model (AUC 0.901 vs 0.821).

Authors

BHB J M Hermans JSJob Stoks FBFrank C. Bennis

Discussion

Member takes

Overview

May aid LQTS diagnosis via T-wave ML models; leaves open prospective validation before clinical adoption.

Study Design

Type

Observational (n=688)

Structured PICO

Does a support vector machine-based model incorporating T-wave morphology improve diagnostic accuracy for long QT syndrome compared to standard ECG intervals in patients and relatives?

Population

688 digital 12-lead ECGs from genotype-positive LQTS patients and genotype-negative relatives at their first visit.

Exposure

Support vector machine-based extended model incorporating T-wave morphology features along with age, gender, RR-interval, QT-interval, and QTc-intervals

Comparator

Baseline model using only age, gender, RR-interval, QT-interval, and QTc-intervals, as well as clinically used QTc-interval cut-off values (>480 ms)

Outcome

Diagnostic accuracy for LQTS measured by Area Under the Receiver-Operating Characteristic Curve (AUC)surrogate

Main Result

Absolute Event Rate: 0.901% vs 0.821%

Incorporating T-wave morphology markers into a support vector machine model significantly improves the diagnostic accuracy for long QT syndrome compared to standard ECG intervals.

Cite This Study

synapsesocial.com/papers/6a22554725ab022a514501c3 https://doi.org/10.1093/europace/euy243

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark