Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
January 16, 2025PLoS ONEOpen Access

Machine learning model outperforms CHA2DS2-VASc in predicting LAT/SEC in NVAF with an AUC of ~0.83.

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Left atrial thrombus or spontaneous echo contrast are major contributors to cardiogenic embolism in NVAF, prompting the development and validation of an interpretable machine learning risk prediction model.

Does a machine learning-based logistic regression model improve the prediction of left atrial thrombus or spontaneous echo contrast compared to the CHA2DS2-VASc score in patients with non-valvular atrial fibrillation?

Population

1,222 NVAF patients scheduled for catheter ablation

Comparison

Optimal machine learning model vs CHA2DS2-VASc scoring system

Design

Retrospective single-center cohort study

Key result

A machine learning-based logistic regression model significantly outperformed the CHA2DS2-VASc scoring system in predicting left atrial thrombus or spontaneous echo contrast in NVAF patients (AUC 0.831 vs 0.650, P < 0.001).

Authors

CHChaoqun HuangSSShangzhi ShuMZMiaomiao Zhou

Discussion

Loading...

Member takes

Overview

May enhance LAT/SEC prediction in NVAF; hypothesis-generating and should not yet change practice.

Study Design

Type

Observational (n=1,078)

Multicenter

No

Structured PICO

Does a machine learning-based logistic regression model improve the prediction of left atrial thrombus or spontaneous echo contrast compared to the CHA2DS2-VASc score in patients with non-valvular atrial fibrillation?

P
Population
1,078 consecutive patients with non-valvular atrial fibrillation (NVAF) scheduled for catheter ablation who underwent transesophageal echocardiography (TEE). Median age 62 years, 63.27% male. Single-center (First Hospital of Jilin University, China).
I
Intervention
Machine learning-based logistic regression predictive model utilizing 6 features (age, non-paroxysmal AF, diabetes, ischemic stroke or thromboembolism, hyperuricemia, and left atrial diameter) with SHAP interpretation.
C
Comparator
CHA2DS2-VASc scoring system.
O
Outcome
Presence of left atrial thrombus (LAT) or spontaneous echo contrast (SEC) detected by transesophageal echocardiography.surrogate

Main Result

Absolute Event Rate: 0.831% vs 0.65%

p-value: p=<0.001

A machine learning-based logistic regression model incorporating six clinical and echocardiographic features significantly outperforms the CHA2DS2-VASc score in predicting left atrial thrombus or spontaneous echo contrast in patients with non-valvular atrial fibrillation.

Limitations

  • Data regarding anticoagulation in NVAF patients were not available
  • Sample size was relatively small and data were collected from a single institution
  • Possibility of segmentation uncertainty introduces potential errors
  • Small sample size of HCM patients limiting statistical significance for this subgroup
  • Unavailability of data for patients with cardiac amyloidosis

Cite This Study

Huang et al. (2025) conducted an observational in Non-valvular atrial fibrillation (NVAF) (n=1,078). Machine learning (logistic regression) model vs. CHA2DS2-VASc scoring system was evaluated on Area under the receiver operating characteristic curve (AUC) for predicting LAT/SEC (95% CI 0.790-0.868, p=<0.001). A machine learning-based logistic regression model significantly outperformed the CHA2DS2-VASc scoring system in predicting left atrial thrombus or spontaneous echo contrast in NVAF patients (AUC 0.831 vs 0.650, P < 0.001).

synapsesocial.com/papers/6a0f83f29e54838161fcd017https://doi.org/10.1371/journal.pone.0313562
View Full Paper
Ask AI
Bookmark
Share