a b s t r a c t Keywords: Pregnancy Fontan circulation Congenital heart disease AnticoagulationBackground: Despite serious long-term sequel, women with Fontan palliation have reached childbearing age. However there is paucity of data on the pregnancy outcomes and management of this condition. We aimed to determine the maternal and fetal outcomes of pregnancy in women with Fontan palliation. Methods: This multicentric, retrospective study included women with Fontan circulation followed in 13 French specialized centers from January 2000 to June 2014. All pregnancies were reviewed, including miscarriages, abor-tions, premature and term births. We reviewed maternal and fetal outcomes. Results: Thirty-seven patients had 59 pregnancies. Mean age was 27 ± 5 years at first pregnancy. There were 16 miscarriages (27%) and 36 live births with 1 twin pregnancy. Cardiac events occurred in 6 (10%) pregnancies, with no maternal death. The most common cardiac complication was atrial arrhythmia, which occurred in 3 pa-tients. Hematological complications including thromboembolic/hemorrhagic events (n = 3/7) occurred in 5 women antepartum (n = 2/3), and 4 women postpartum (n = 1/4). Two of the 3 thromboembolic events oc-curred in patients without anticoagulation. There was a high incidence of prematurity (n = 25/36, 69%). Anticoagulation was associated with adverse neonatal outcome (OR = 10.0, 95% CI [1.5-91.4], p b 0.01). After a median followup of 24 months, there was no significant worsening of clinical status and thromboembolic disease noted. Conclusions: Pre-selected women can successfully complete pregnancy with Fontan circulation. There is an increase in cardiac and neonatal morbidity during pregnancy. Because thromboembolism could have a severe consequence on Fontan circulation, anticoagulation should be indicated during pregnancy and postpartum period.

Outcome of pregnancy in women with PAH-CHD is better than previously reported, with only 5% maternal mortality in our cohort. However, because of the severity of heart failure and the high rate of neonatal complications, patients should still be advised against pregnancy.

No abstract

Aims To investigate the utility of novel deep learning (DL) algorithms in recognizing transposition of the great arteries (TGA) after atrial switch procedure or congenitally corrected TGA (ccTGA) based on routine transthoracic echocardiograms. In addition, the ability of DL algorithms for delineation and segmentation of the systemic ventricle was evaluated. Methods and results In total, 132 patients (92 TGA and atrial switch and 40 with ccTGA; 60% male, age 38.3 ± 12.1 years) and 67 normal controls (57% male, age 48.5 ± 17.9 years) with routine transthoracic examinations were included. Convolutional neural networks were trained to classify patients by underlying diagnosis and a U-Net design was used to automatically segment the systemic ventricle. Convolutional networks were build based on over 100 000 frames of an apical four-chamber or parasternal short-axis view to detect underlying diagnoses. The DL algorithm had an overall accuracy of 98.0% in detecting the correct diagnosis. The U-Net architecture model correctly identified the systemic ventricle in all individuals and achieved a high performance in segmenting the systemic right or left ventricle (Dice metric between 0.79 and 0.88 depending on diagnosis) when compared with human experts. Conclusion Our study demonstrates the potential of machine learning algorithms, trained on routine echocardiographic datasets to detect underlying diagnosis in complex congenital heart disease. Automated delineation of the ventricular area was also feasible. These methods may in future allow for the longitudinal, objective, and automated assessment of ventricular function.