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

Abstract

IntroductionThis 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 methodsAn 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.ResultsUsing 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.ConclusionsThe 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.

Revolutionizing Cardiology through Artificial Intelligence—Big Data from Proactive Prevention to Precise Diagnostics and Cutting-Edge Treatment—A Comprehensive Review of the Past 5 Years

“…A recent article has discussed screening for cardiovascular disease in women using AI [ 259 ], this being a subcategory analyzed by the authors within the wide range of areas in which AI has proven effective in screening (e.g., congenital disease screening from both ECG analysis [ 90 ] to heart sound analysis [ 91 ] and fetal ultrasound [ 93 ], screening for reduced fraction heart failure [ 109 ], screening for hypertension [ 138 ], screening for valvular disease [ 218 , 219 , 220 , 222 , 227 , 228 ], and screening for rare diseases such as Fabry disease [ 60 ]).…”

“…Thus, the use of AI could improve the quality of patient care, help optimize the treatment of these patients, extend life expectancy, save time for the attending physician, and reduce healthcare costs [ 243 ]. Artificial intelligence has found usefulness in current studies in the prediction of cardiovascular events in adults operated on for Fallot tetralogy [ 89 ] and the screening of congenital diseases based on ECG [ 90 ] based on cardiac auscultation [ 91 ] or echocardiography [ 93 , 94 ]. De Vries R.I. et al conducted a study that developed an ECG-based fetal screening method for CHD.…”

“…De Vries R.I. et al conducted a study that developed an ECG-based fetal screening method for CHD. They demonstrated a 63% detection rate for all CHD types and 75% for critical CHD [ 90 ]. A study of 386 patients identified predictors of impaired executive function in adolescents after surgical repair of critical congenital heart disease (CHD), which were as follow: social class as the primary predictor and birth weight, neurological events, and number of procedures as other predictors [ 92 ].…”

Role of artificial intelligence in early detection of congenital heart diseases in neonates

“…Research has consistently demonstrated improvements in sensitivity and specificity when detecting various Congenital Heart Diseases-(CHD) early in pregnancy. These findings hold the potential to enable earlier diagnosis of fetal cardiac conditions, offering a broader timeframe for implementing interventions that can ultimately reduce mortality rates and lower associated risks (11)(12)(13).…”

Diagnosis and Management of Fetal Arrhythmias in the Current Era

“…More recently, the group from Children’s National described a new frequency-based technique for attenuating the maternal ECG to enhance and extract the fECG [ 118 ]. Ongoing efforts utilize artificial intelligence, including artificial neural networks and deep learning models, to detect fetal arrhythmias [ 119 , 120 , 121 , 122 ].…”