Fetal electrocardiography and artificial intelligence for prenatal detection of congenital heart disease.

INTRODUCTION: This study aims to investigate non-invasive electrocardiography as a method for the detection of congenital heart disease (CHD) with the help of artificial intelligence. MATERIAL AND METHODS: An artificial neural network was trained for the identification of CHD using non-invasively obtained fetal electrocardiograms. With the help of a Bayesian updating rule, multiple electrocardiographs were used to increase the algorithm's performance. RESULTS: Using 122 measurements containing 65 healthy and 57 CHD cases, the accuracy, sensitivity, and specificity were found to be 71%, 63%, and 77%, respectively. The sensitivity was however 75% and 69% for CHD cases requiring an intervention in the neonatal period and first year of life, respectively. Furthermore, a positive effect of measurement length on the detection performance was observed, reaching optimal performance when using 14 electrocardiography segments (37.5 min) or more. A small negative trend between gestational age and accuracy was found. CONCLUSIONS: The proposed method combining recent advances in obtaining non-invasive fetal electrocardiography with artificial intelligence for the automatic detection of CHD achieved a detection rate of 63% for all CHD and 75% for critical CHD. This feasibility study shows that detection rates of CHD might improve by using electrocardiography-based screening complementary to the standard ultrasound-based screening. More research is required to improve performance and determine the benefits to clinical practice.

A simulation model to study maternal hyperoxygenation during labor.

OBJECTIVE: To investigate the effect of maternal hyperoxygenation on fetal oxygenation and fetal heart rate decelerations during labor, using a simulation model. DESIGN: Use of a mathematical model that simulates feto-maternal hemodynamics and oxygenation, designed in Matlab R2012a. SETTING: Clinical and engineering departments in the Netherlands. METHODS: We simulated variable and late fetal heart rate decelerations, caused by uterine contractions with a different contraction interval. We continuously recorded oxygen pressure in different feto-placental compartments and fetal heart rate, during maternal normoxia and during hyperoxygenation with 100% oxygen. MAIN OUTCOME MEASURES: Changes in oxygen pressure in the intervillous space, umbilical vein and arteries, fetal cerebral and microcirculation as well as fetal heart rate deceleration depth and duration. RESULTS: Maternal hyperoxygenation leads to an increase in fetal oxygenation: in the presence of variable decelerations, oxygen pressure in the intervillous space increased 9-10 mmHg and in the cerebral circulation 1-2 mmHg, depending on the contraction interval. In addition, fetal heart rate deceleration depth decreased from 45 to 20 beats per minute. In the presence of late decelerations, oxygen pressure in the intervillous space increased 7-10 mmHg and in the cerebral circulation 1-2 mmHg, depending on the contraction interval. The fetus benefited more from maternal hyperoxygenation when contraction intervals were longer. CONCLUSIONS: According to the simulation model, maternal hyperoxygenation leads to an increase in fetal oxygenation, especially in the presence of variable decelerations. In addition, in the presence of variable decelerations, maternal hyperoxygenation leads to amelioration of the fetal heart rate pattern.