Association between patent foramen ovale and anxiety: a prospective study with deep learning-assisted analysis of contrast echocardiography
8 affiliations
- 1Department of Cardiology, Dongguan People’s Hospital (The Tenth Affiliated Hospital of Southern Medical University) , ,
- 2School of Electronic Information and Artificial Intelligence, Shaanxi University of Science & Technology , ,
- 3Department of Neurology, Dongguan People’s Hospital (The Tenth Affiliated Hospital of Southern Medical University) , ,
- 4Department of Cardiovascular and Neurology, Dongguan Xiegang Hospital , ,
- 5Department of Cardiology, Puji Campus of Dongguan People’s Hospital , ,
- 6Division of Cardiology, Department of Medicine and Therapeutics, Faculty of Medicine, The Chinese University of Hong Kong , ,
- 7Department of Thoracic Surgery, Dongguan People’s Hospital (The Tenth Affiliated Hospital of Southern Medical University) , ,
- 8Faculty of Electrical Engineering and Computer Science, Ningbo University , ,
Abstract
Purpose: To prospectively investigate the association between patent foramen ovale (PFO), detected via agitated saline contrast echocardiography (ASCE), and anxiety using a deep learning approach.
Materials and methods: This prospective study consecutively enrolled 161 participants between July 15, 2025 and October 31, 2025. Participants were stratified into ASCE-negative (n=58) and ASCE-positive (n=103) groups based on the examination results. All participants underwent ASCE and anxiety assessment using the Self-Rating Anxiety Scale (SAS). An artificial intelligence model was developed using a 10-fold cross-validation approach on the 103 ASCE-positive videos to predict anxiety scores. The primary endpoint was the association between PFO and anxiety, while the deep learning model was evaluated as a secondary/exploratory endpoint. Statistical analyses, including logistic regression, were performed with statistical significance set at p<0.05.
Results: Compared to the ASCE-negative group, the ASCE-positive group exhibited significantly higher anxiety levels (SAS score: 45.0 vs. 38.0, p<0.001) and a higher prevalence of anxiety (32.0% vs. 5.2%, p<0.001). Logistic regression identified a strong association between ASCE-positive status and anxiety (adjusted odds ratio=8.64, p<0.001), with no clear dose-dependent relationship across shunt grades. The imaging-only deep learning model achieved a mean absolute error (MAE) of 5.76 ± 0.12 and an R² of 0.46 ± 0.03 across cross-validation folds. After incorporating clinical and sociodemographic confounders, the model’s performance improved to an MAE of 5.15 ± 0.10 and an R² of 0.59 ± 0.02.
Conclusion: This prospective study confirms a significant association between PFO and anxiety and demonstrates the feasibility of using ASCE-based deep learning models to predict anxiety risk, although clinical application requires external validation.
Related
- A fully automated machine learning assisted pipeline to predict disease progression for early-stage hypertrophic cardiomyopathy from echocardiography
- Association between quality of life and pregnancy outcomes among infertility patients undergoing assisted reproduction technologies: a prospective cohort study
- AI-accelerated compressed sensing and deep learning reconstruction for colon MRI: prospective validation of image quality and preliminary assessment of staging accuracy versus contrast-enhanced CT
- Transthoracic Echocardiography-Assisted, Low-Fluoroscopy Left Bundle Branch Area Pacing: A Comparison of Implantation Approaches and Lead Types.
- Establishing reference ranges for right ventricular functional parameters on neonatal echocardiography: a multicenter, prospective observational study
BibTeX
@article{liao2026association,
title = {{Association between patent foramen ovale and anxiety: a prospective study with deep learning-assisted analysis of contrast echocardiography}},
author = {Minqi Liao and Changji Yang and Chengyu Hong and Xiaoyu Liu and Zheng Li and Shumin Ouyang and Xuande Zhang and Hanyu Weng and Ziying Cao and Zhihao Wu and Jiahua Ye and Zhichao Huang and Yanhua Yang and Kangmin Wang and Patience Ratidzo Ngombengombe and Jiongbin Lu and Zekui Wu and Zhanyang Wei and Mark T. K. Tam and Jianping Zhou and Xin Huang and Suxia Guo},
journal = {Frontiers in psychiatry},
year = {2026},
month = sep,
doi = {10.3389/fpsyt.2026.1877855},
url = {https://europepmc.org/article/PMC/PMC13661545},
note = {CC BY},
}
RIS
TY - JOUR
TI - Association between patent foramen ovale and anxiety: a prospective study with deep learning-assisted analysis of contrast echocardiography
AU - Minqi Liao
AU - Changji Yang
AU - Chengyu Hong
AU - Xiaoyu Liu
AU - Zheng Li
AU - Shumin Ouyang
AU - Xuande Zhang
AU - Hanyu Weng
AU - Ziying Cao
AU - Zhihao Wu
AU - Jiahua Ye
AU - Zhichao Huang
AU - Yanhua Yang
AU - Kangmin Wang
AU - Patience Ratidzo Ngombengombe
AU - Jiongbin Lu
AU - Zekui Wu
AU - Zhanyang Wei
AU - Mark T. K. Tam
AU - Jianping Zhou
AU - Xin Huang
AU - Suxia Guo
PY - 2026
DA - 2026/09/30
JO - Frontiers in psychiatry
DO - 10.3389/fpsyt.2026.1877855
UR - https://europepmc.org/article/PMC/PMC13661545
AB - Purpose: To prospectively investigate the association between patent foramen ovale (PFO), detected via agitated saline contrast echocardiography (ASCE), and anxiety using a deep learning approach. Materials and methods: This prospective study consecutively enrolled 161 participants between July 15, 2025 and October 31, 2025. Participants were stratified into ASCE-negative (n=58) and ASCE-positive (n=103) groups based on the examination results. All participants underwent ASCE and anxiety assessment using the Self-Rating Anxiety Scale (SAS). An artificial intelligence model was developed using a 10-fold cross-validation approach on the 103 ASCE-positive videos to predict anxiety scores. The primary endpoint was the association between PFO and anxiety, while the deep learning model was evaluated as a secondary/exploratory endpoint. Statistical analyses, including logistic regression, were performed with statistical significance set at p<0.05. Results: Compared to the ASCE-negative group, the ASCE-positive group exhibited significantly higher anxiety levels (SAS score: 45.0 vs. 38.0, p<0.001) and a higher prevalence of anxiety (32.0% vs. 5.2%, p<0.001). Logistic regression identified a strong association between ASCE-positive status and anxiety (adjusted odds ratio=8.64, p<0.001), with no clear dose-dependent relationship across shunt grades. The imaging-only deep learning model achieved a mean absolute error (MAE) of 5.76 ± 0.12 and an R² of 0.46 ± 0.03 across cross-validation folds. After incorporating clinical and sociodemographic confounders, the model’s performance improved to an MAE of 5.15 ± 0.10 and an R² of 0.59 ± 0.02. Conclusion: This prospective study confirms a significant association between PFO and anxiety and demonstrates the feasibility of using ASCE-based deep learning models to predict anxiety risk, although clinical application requires external validation.
SN - 1664-0640
ER -