Fetal Heart Monitoring and Pregnancy Surveillance:
Fetal heart rate (FHR) monitoring helps the healthcare provider to monitor the fetus and diagnose associated high-risk complications. It also gives a qualitative and quantitative overview of baseline fetal heart rate, variability, acceleration, deceleration, uterine contraction intensity, and FHR pattern changes [6]. Currently, AI is used to monitor the fetal heart rate during labor via analyzing cardiotocographs and estimating possible outcomes. As Desai states in his study, the benefits of its incorporation in obstetrics, specifically antepartum monitoring, would be advantageous [2]. This technology would help decrease the discrepancies between different obstetricians interpreting intrapartum monitoring, thus providing a more reliable and replicable output for each analysis, and ultimately reducing perinatal and maternal complications and morbidity. Artificial intelligence systems can also provide supporting evidence in cases of unpredictable poor outcomes that can potentially result in litigation. Some examples of where AI has been tested in cardiotocography (CTG) analysis include: CAFE (Computer-Aided Fetal Evaluator) studied the possibility of an AI system being able to interpret CTG data [2,6]. The results concluded that the AI system read the information at a similar level as the experts in the field and was also able to detect errors. Some limitations in this study were disagreements between specialists when interpreting some data, mostly in interpreting variations, which led to an inability to conclude if the error in interpretation arose from a problem in the system, or in obtaining agreement between experts in the field [7]. This was an obstacle in proving that the system is optimum and confirming its precision. More robust research is required to enhance flexibility in data interpretation.
The INFANT study protocol is a large trial currently evaluating the ability of AI interpretation of CTG during labor to assist practitioners in deciding the best management on an individual basis [8]. The goal is to make FHR reading more reliable, to aid the physician in interpreting and decision-making, and decrease the burden of work by making it more efficient. Perinatal asphyxia is a significant problem worldwide, and by creating an efficient way to monitor FHR, it would improve care and decrease poor outcomes. Thus, an alarm monitor that warns of potential fetal distress can guide the practitioner to act in a timely matter and perform intrapartum interventions when necessary. It can also provide reassurance and avoid unnecessary treatment in those women where fetal distress is not observed.
System 8000 is a computer system that analyzes the antenatal fetal heart rate (FHR) [8,9]. It monitors changes in FHR and detects amplitudes associated with hypoxemia by detecting decelerations and changes in variability. Currently, a decrease in variation is the most dependable index of fetal deterioration, but unfortunately, there is significant observer variation in interpreting this data. The introduction of AI can decrease this difference between readers, which can lead to a more reliable interpretation of variation, decrease unnecessary interventions, and expedite the delivery if necessary.
CTG technology arose 50 years ago, and frequent differences between specialists urge for a system that decreases error and unifies interpretation while analyzing CTG. A study was done by Kazantsev et al. urges the development of new technologies that can address the issue of maternal and infant mortality [9,10] The researchers in this study believe that AI technology can be used for out-patient care in the form of home monitors that can adequately provide surveillance of high-risk patients. This technology in conjunction with telemedicine can potentially aid in earlier detection of potential complications and reassure the clinician and the patient that a safe system of monitoring is being used even if an outside clinic or hospital care. It also provides a warning system that informs the patient of dangerous FHR readings and signals them to notify the physician to decide on further care according to the in-home AI analysis. In this study, they used neural network recognition algorithms that can provide a solution to interpretation discrepancies between specialists. It also mentioned that outpatient monitoring is readily accessible because most homes have access to the Internet and smartphones. The insertion of AI into Doppler ultrasound has proven to be cost-effective. The system is also able to exclude readings of uncertain meaning, such as pseudo accelerations and pseudo decelerations that occur due to intense fetal movement, thus not falsely alarming the patient of possible fetal endangerment. The downside of the study was that the proposed method was only tested in one subject, and even though it proved successful, a larger study is needed to replicate its results and validate this intervention. The possibility of guiding decision-making and management using telecommunications combined with in-home pregnancy monitoring can prove beneficial in early detection of pregnancy complications and decrease maternal and infant mortality [8,9,10].