The INFANT trial

Artificial Intelligence in Obstetrics and Gynecology: Transforming Care and Outcomes

The integration of artificial intelligence (AI) in obstetrics and gynecology (OB/GYN) is revolutionizing the landscape of women's healthcare. This review article explores the transformative impact of AI technologies on the diagnosis, treatment, and management of obstetric and gynecological conditions. We examine key advancements in AI-driven imaging techniques, predictive analytics, and personalized medicine, highlighting their roles in enhancing prenatal care, improving maternal and fetal outcomes, and optimizing gynecological interventions. The article also addresses the challenges and ethical considerations associated with the implementation of AI in clinical practice. This paper highlights the potential of AI to greatly improve the standard of care in OB/GYN, ultimately leading to better health outcomes for women, by offering a thorough overview of present AI uses and future prospects.

Pathophysiological interpretation of fetal heart rate tracings in clinical practice

The onset of regular, strong, and progressive uterine contractions may result in both mechanical (compression of the fetal head and/or umbilical cord) and hypoxic (repetitive and sustained compression of the umbilical cord or reduction in uteroplacental oxygenation) stresses to a human fetus. Most fetuses are able to mount effective compensatory responses to avoid hypoxic-ischemic encephalopathy and perinatal death secondary to the onset of anaerobic metabolism within the myocardium, culminating in myocardial lactic acidosis. In addition, the presence of fetal hemoglobin, which has a higher affinity for oxygen even at low partial pressures of oxygen than the adult hemoglobin, especially increased amounts of fetal hemoglobin (ie, 180-220 g/L in fetuses vs 110-140 g/L in adults), helps the fetus to withstand hypoxic stresses during labor. Different national and international guidelines are currently being used for intrapartum fetal heart rate interpretation. These traditional classification systems for fetal heart rate interpretation during labor are based on grouping certain features of fetal heart rate (ie, baseline fetal heart rate, baseline variability, accelerations, and decelerations) into different categories (eg, category I, II, and III tracings, "normal, suspicious, and pathologic" or "normal, intermediary, and abnormal"). These guidelines differ from each other because of the features included within different categories and because of their arbitrary time limits stipulated for each feature to warrant an obstetrical intervention. This approach fails to individualize care because the "ranges of normality" for stipulated parameters apply to the population of human fetuses and not to the individual fetus in question. Moreover, different fetuses have different reserves and compensatory responses and different intrauterine environments (presence of meconium staining of amniotic fluid, intrauterine inflammation, and the nature of uterine activity). Pathophysiological interpretation of fetal heart rate tracing is based on the application of the knowledge of fetal responses to intrapartum mechanical and/or hypoxic stress in clinical practice. Both experimental animal studies and observational human studies suggest that, just like adults undertaking a treadmill exercise, human fetuses show predictable compensatory responses to a progressively evolving intrapartum hypoxic stress. These responses include the onset of decelerations to reduce myocardial workload and preserve aerobic metabolism, loss of accelerations to abolish nonessential somatic body movements, and catecholamine-mediated increases in the baseline fetal heart rate and effective redistribution and centralization to protect the fetal central organs (ie, the heart, brain, and adrenal glands), which are essential for intrauterine survival. Moreover, it is essential to incorporate the clinical context (progress of labor, fetal size and reserves, presence of meconium staining of amniotic fluid and intrauterine inflammation, and fetal anemia) and understand the features suggestive of fetal compromise in nonhypoxic pathways (eg, chorioamnionitis and fetomaternal hemorrhage). It is important to appreciate that the timely recognition of the speed of onset of intrapartum hypoxia (ie, acute, subacute, and gradually evolving) and preexisting uteroplacental insufficiency (ie, chronic hypoxia) on fetal heart rate tracing is crucial to improve perinatal outcomes.

Applications of artificial intelligence in obstetrics

Artificial intelligence, which has been applied as an innovative technology in multiple fields of healthcare, analyzes large amounts of data to assist in disease prediction, prevention, and diagnosis, as well as in patient monitoring. In obstetrics, artificial intelligence has been actively applied and integrated into our daily medical practice. This review provides an overview of artificial intelligence systems currently used for obstetric diagnostic purposes, such as fetal cardiotocography, ultrasonography, and magnetic resonance imaging, and demonstrates how these methods have been developed and clinically applied.

The present and future of intrapartum computerized cardiotocography: role of pattern recognition incorporating single vs. multiple parameters

Computer assisted cardiotocography holds a great promise in minimizing human errors thereby improving perinatal outcome. Despite exponential growth (Moore's law) in computing power for decades, this promise remains unrealized. The systematic analyses of studies on computerized cardiotocography offer little guide to future. This analytical review presents a more qualitative discussion of available evidence as well as concepts regarding the development and acceptance of computerized cardiotocography. To begin with, a workable approach would be for computer algorithms to follow the most scientific visual cardiotocography interpretation frameworks incorporating multiple fetal heart rate parameters and uterine contractions. This ability could be studied and form the basis for regulation of computer algorithms. Addition of background risk factors would be another step. This may take form of familiar multi-tier systems or new alternative strategies like the fetal reserve index. "Machine learning" will remain challenging because of complex variability in fetal-maternal conditions, labor characteristics and clinical intervention changing the outcomes. Randomized controlled trials of adequate size may remain very rare. However, prospective and retrospective testing of computer algorithms with careful qualitative and comparative approach would help clinicians and hospital managers in their decisions. Singular parameters like the popular "deceleration area" and "deceleration capacity" have poor predictive value for fetal acidemia or hypoxic injury. Scientific pattern-recognition of important fetal heart rate parameters like decelerations seems crucial for visual as well as computerized cardiotocography. Success of computerizedcardiotocography depends on team effort by the obstetricians with in-depth practical knowledge/experience and skilled artificial intelligence (AI) specialists.

Second-Generation Digital Health Platforms: Placing the Patient at the Center and Focusing on Clinical Outcomes

Artificial intelligence (AI) digital health systems have drawn much attention over the last decade. However, their implementation into medical practice occurs at a much slower pace than expected. This paper reviews some of the achievements of first-generation AI systems, and the barriers facing their implementation into medical practice. The development of second-generation AI systems is discussed with a focus on overcoming some of these obstacles. Second-generation systems are aimed at focusing on a single subject and on improving patients' clinical outcomes. A personalized closed-loop system designed to improve end-organ function and the patient's response to chronic therapies is presented. The system introduces a platform which implements a personalized therapeutic regimen and introduces quantifiable individualized-variability patterns into its algorithm. The platform is designed to achieve a clinically meaningful endpoint by ensuring that chronic therapies will have sustainable effect while overcoming compensatory mechanisms associated with disease progression and drug resistance. Second-generation systems are expected to assist patients and providers in adopting and implementing of these systems into everyday care.

Earlier and improved screening for impending fetal compromise

OBJECTIVE

The use of pH and base excess (FSSPHBE) from fetal scalp sampling (FSS) was abandoned when cardiotocography (CTG) was believed to be sufficiently accurate to direct patient management. We sought to understand the fetus' tolerance to stress in the 1st stage of labor and to develop a better and earlier screening test for its risk for developing acidosis. To do so, we investigated sequential changes in fetal pH and BE obtained from FSS in the 1st stage of labor as part of a research protocol from the 1970s. We then examined the utility of multiple of the median (MoM's) conversion of BE and pH values, and the capacity of Fetal Reserve Index (FRI) scores to be a proxy for such changes. We then sought to examine the predictive capacity of 1st stage FRI and its change over the course of the first stage of labor for the subsequent development of acidosis risk in the 2nd stage of labor.

METHODS

Using a retrospective research database evaluation, we evaluated FSSPHBE data from 475 high-risk parturients monitored in labor and their neonates for 1 h postpartum. We categorized specimens according to cervical dilatation (CxD) at the time of FSSPHBE and developed non-parametric, multiples of the median (MOMs) assessments. FRI scores and their change over time were used as predictors of FSSPHBE. Our main outcome measures were the changes in BE and pH at different cervical dilatations (CxD) and acidosis risk in the early 2nd stage of labor.

RESULTS

FSSPHBE worsens over the course of the 1st stage. The implications of any given BE are very different depending upon CxD. At 9 cm, -8 Mmol/L is 1.1 MOM; at 3 cm, it would be 2.0 MOM. The FRI level and its trajectory provide a 1st stage screening tool for acidosis risk in the second stage.

CONCLUSIONS

Fetal acid-base balance ("reserve") deteriorates beginning early in the 1st stage of labor, irrespective of whether the fetus reaches a critical threshold of concern for actual acidosis. The use of MoM's logic improves appreciation of such information. The FRI and its trajectory reasonably approximate the trajectory of the FSSPHBE and appears to be a suitable screening test for early deterioration and for earlier interventions to keep the fetus out of trouble rather than wait until high risk status develops.

Planned delivery or expectant management for late preterm pre-eclampsia: study protocol for a randomised controlled trial (PHOENIX trial)

Background

Pre-eclampsia is a pregnancy disorder, characterised by hypertension and multisystem complications in the mother. The adverse outcomes of pre-eclampsia include severe hypertension, stroke, renal and hepatic injury, haemorrhage, fetal growth restriction and even death. The optimal time to instigate delivery to prevent morbidity when pre-eclampsia occurs between 34 and 37 weeks’ gestation, without increasing problems related to infant immaturity or complications, remains unclear.

Methods/design

The PHOENIX trial is a non-masked, randomised controlled trial, comparing planned early delivery (with initiation of delivery within 48 h of randomisation) with usual care (expectant management) in women with pre-eclampsia between 34^+ 0 and 36^+ 6 weeks’ gestation. The primary objectives of the trial are to determine if planned delivery reduces adverse maternal outcomes, without increasing the short-term harm to infants (composite of perinatal deaths or neonatal unit admissions up to infant hospital discharge) or impacting long-term infant neurodevelopmental status at 2 years corrected age (Parent Report of Cognitive Abilities-Revised).

Discussion

Current practice in the UK at the time of trial commencement for management of pre-eclampsia varies by gestation. Previous trials have shown that in women with pre-eclampsia after 37 weeks of gestion, delivery is initiated, as maternal complications are reduced without increasing fetal risks. Prior to 34 weeks of gestation, usual management aims to prolong pregnancy for fetal benefit, unless severe complications occur, necessitating preterm delivery. This trial aims to address the uncertainty for women where the balance of benefits and risks of delivery compared to expectant management are uncertain. Previous trials in this area have been undertaken, but have not provided a definitive answer, and the research question remains active. The results of this trial are expected to influence clinical practice internationally, through direct adoption and by incorporation into guidelines in countries with similar settings.

Trial registration

ISRCTN01879376. Registered on 25 November 2013.

Electronic supplementary material

The online version of this article (10.1186/s13063-018-3150-1) contains supplementary material, which is available to authorized users.

Safely lowering the emergency Cesarean and operative vaginal delivery rates using the Fetal Reserve Index

Objective: The cardiotocograph (CTG) or electronic fetal monitoring (EFM) was developed to prevent fetal asphyxia and subsequent neurological injury. From a public health perspective, it has failed these objectives while increasing emergency operative deliveries (emergency operative deliveries (EODs) - emergency cesarean delivery or operative vaginal delivery) for newborns, who in retrospect, actually did not require the assistance. EODs increase the risks of complications and stress for patients, families, and medical personnel. A safe reduction in the need for EOD will likely reduce both the overall Cesarean section rate as well as the risk of fetal neurological injury during labor to which it is related. We have developed the fetal reserve index (FRI), which is more comprehensive than CTG as a new screening method for early identification of the fetus at-risk of both neurological harm and the need to "rescue" by means of an EOD. Here, we compare prospectively the need for EOD in two groups of parturients undergoing a trial of labor at term. One group was managed conventionally, the other by the principles of the FRI.Study design: We compared the need for EOD of 800 parturients with singleton cases undergoing a trial of labor at term entering with normal CTG patterns (ACOG category 1). Patients were either treated routinely (400 - "early cases") or in a second group seen later actively managed using the principles of the FRI (400 - "late cases"). The FRI includes measurements of five components of the CTG: rate, variability, decelerations, accelerations, and abnormal uterine activity combined with the presence of medical, obstetrical, and fetal risk factors. The 8-point metric categorizes cases as "green", "yellow", and "red" with the latter being at risk.Results: All 800 patients delivered babies, who were discharged in the usual time course with no untoward outcomes noted. The incidence of red zone scores was comparable in the two groups (≈25%), but the use of intrauterine resuscitation (IR) when reaching the red zone in the late group (47%) was more than double the incidence in the early group (20%) (p < .001). Despite (or because of) this, EODs were significantly reduced in the late group, from 17.3 to 4.0% (p < .001). Further, the late group spent less time in the red zone without increasing overall time in labor. Overall, EOD cases averaged >1 h in the red zone versus 0.5 h for non-EODs.Conclusions: The FRI may provide a metric to reduce EODs and by extension also reduce the risks of both cesarean delivery and adverse fetal/neonatal outcomes. The safe avoidance of EOD would seem to be an important metric to assess the quality of intrapartum management. This study represents the first attempt to apply the principles of the FRI "live" for the concurrent management of patients during labor. These promising results, if confirmed, in larger sample sizes, set the stage for our computerization of the FRI for widespread study. Benefits appear to come from identification and early, conservative management of fetal deterioration before the need to "rescue" the fetus by EOD.