Prediction of Pregnancy-Related Cardiovascular Outcomes Using Electrocardiogram-Based Deep Learning Estimation of Cardiorespiratory Fitness
- multi-institutional electronic health record pregnancy cohort
- multivariable-adjusted mixed-effects logistic regression
+1 more
- multivariable-adjusted mixed-effects logistic regression
Authors' conclusion
Lower ECG-estimated cardiorespiratory fitness was associated with a higher risk of pregnancy-related CV complications, supporting artificial intelligence-enabled ECG analysis as a scalable tool for antepartum risk stratification of pregnancy-related CV complications.
Study context
- Population
- Individuals with a clinical 12-lead electrocardiogram (ECG) from 1 year before pregnancy to 13 weeks of gestationpregnancies from 3,437 women
- Participants
- 3,650 individuals
- Exposure
- associations between ECG-estimated peak VO2 with pregnancy-related cardiovascular (CV) complications up to 1 year postpartum
Main finding
As reported in the abstract
Pregnancy-related CV complication · median follow-up time of 1.7 years (IQR: 1.6-1.8 years)
experienced a pregnancy-related CV complication
723 (20%; 95% CI: 19%-21%)
Observational data: associations, not effects.
Further findings
| Outcome | Estimate | P value | |
|---|---|---|---|
| Pregnancy-related CV complication risk per 1-metabolic equivalent lower fitness | adjusted OR 1.09 (95% CI 1.03–1.17) | P < 0.01 | |
| CV complications by quartile of ECG-estimated peak VO2 · 61% greater odds | OR 1.61 (95% CI 1.13–2.30) | P = 0.008 | |
| 0.512Ratio (log scale) |
- Pregnancy-related CV complication risk per 1-metabolic equivalent lower fitness: lower ECG-estimated peak VO2 associated with higher complication risk
ECG-estimated VO2
- median ECG-estimated VO2
- 27.0 mL/kg/min (IQR: 21.9-31.2)
- Mean age at delivery was 33 ± 6 years among 3,650 pregnancies from 3,437 women
Original publication
Prediction of Pregnancy-Related Cardiovascular Outcomes Using Electrocardiogram-Based Deep Learning Estimation of Cardiorespiratory Fitness. JACC Adv. Published 24 April 2026. doi:10.1016/j.jacadv.2026.102764
Summarised from the published abstract; every number is checked against it