APSR2026-648

Yes
Late-Breaking
Submitted
Oral Presentation
AO20-003
 
 
https://storage.unitedwebnetwork.com/files/1285/1221020-46903-APSR2026-648_440297.pptx
Format: PPTX Only
 
Format: PDF Only
15. Pulmonary Circulation
6

No more than 15 authors can be listed.
Please ensure the authors are listed in the right order.
If there are multiple affiliations, please use the "+" button next to "Select Country/Region" to add additional affiliation fields.

Feiya Xu * Chinese Academy of Medical Sciences & Peking Union Medical College China-Japan Friendship Hospital (Institute of Clinical Medical Sciences) Beijing China
Yanshuang Lyu - Chinese Academy of Medical Sciences & Peking Union Medical College State Key Laboratory of Respiratory Health and Multimorbidity Beijing China
Jing Ma - The Second Affiliated Hospital of Harbin Medical University Department of Respiratory and Critical Care Medicine Harbin China
Guohui Fan - China-Japan Friendship Hospital Department of Clinical research and Data management Beijing China
Zhenguo Zhai - China-Japan Friendship Hospital Department of Pulmonary and Critical Care Medicine Beijing China
Dingyi Wang - China-Japan Friendship Hospital Department of Clinical research and Data management Beijing China
 
 
 
 
 
 
 
 
 
Presenting Author Details
Feiya
Xu
feiyaxu521@126.com
+8618001266954
Under 30
China
Original Research
Dynamic monitoring of right ventricular function in acute pulmonary embolism using artificial intelligence-enhanced electrocardiogram analysis
Maximum 25 words
Abstract Content
Right ventricular dysfunction (RVD) is the major risk of short-term mortality and long-term sequelae in acute pulmonary embolism (PE). About 30% of patients retain RVD at 1 year, yet its recovery trajectory remains unclear. We aimed to characterize dynamic changes in right ventricular function in intermediate-/high-risk PE using continuous electrocardiogram (ECG) monitoring with artificial intelligence (AI)-based analysis.
In this prospective multicenter cohort, 60 patients with confirmed intermediate-/high-risk PE were enrolled across four tertiary hospitals. Exclusion criteria included symptom onset >14 days before diagnosis, chronic PE without recurrence, and contraindications to ECG patch. Patients received either reperfusion (systemic thrombolysis or catheter-directed therapy) and anticoagulation only. Continuous ECG signals were recorded using patch-type monitors for 72 h within the first 3 days after admission. ECG frequency-domain features were decomposed via convolutional neural networks (CNNs), and temporal modeling was applied to analyze dynamic changes.
Within 72 h, heart rate, P-wave amplitude, QRS amplitude, QT interval, and T-wave amplitude increased, while P-wave width, QRS duration, ST-segment amplitude, and T-wave width decreased. RR interval declined after 48 h; PR interval remained stable. Heart rate variability (HRV) indices (SDNN, vitality index, RMSSD, NN_50%) progressively improved, with decreasing LF/HF ratio, indicating enhanced parasympathetic activity. Compared with intermediate-low risk patients, intermediate-high risk group showed wider P waves, higher QRS amplitude, longer RR/PR/ST intervals, more pronounced ST depression, higher HRV indices, and lower LF/HF. Reperfusion group (n=10) showed lower HRV indices (total power, SDNN, SDANN, RMSSD) than anticoagulation group, suggesting faster autonomic stabilization.
Dynamic ECG and HRV demonstrate progressive recovery within 72 h after acute PE, with parasympathetic activation as a marker of improvement. Intermediate-high risk patients display more severe disturbances, while reperfusion accelerates stabilization. AI-assisted ECG offers a practical, non-invasive approach to monitor RVD, complementing echocardiography and guiding clinical management.
 
 
 
 
 
No
No
 
JPG or JPEG or PNG format ONLY
pulmonary embolism, right ventricular dysfunction, electrocardiogram
maximum 3 keywords and no abbreviations, separated by commas
All authors declared no conflicts of interest. The authors thank the patients and China pUlmonary thromboembolism REgistry (CURES) Study study investigators for their contribution to the study.
300