Sonographic confirmation of fetal position before operative vaginal delivery should be recommended in clinical guidelines

Use of artificial intelligence in obstetrics: not quite ready for prime time

Artificial intelligence is finding several applications in healthcare settings. This study aimed to report evidence on the effectiveness of artificial intelligence application in obstetrics. Through a narrative review of literature, we described artificial intelligence use in different obstetrical areas as follows: prenatal diagnosis, fetal heart monitoring, prediction and management of pregnancy-related complications (preeclampsia, preterm birth, gestational diabetes mellitus, and placenta accreta spectrum), and labor. Artificial intelligence seems to be a promising tool to help clinicians in daily clinical activity. The main advantages that emerged from this review are related to the reduction of inter- and intraoperator variability, time reduction of procedures, and improvement of overall diagnostic performance. However, nowadays, the diffusion of these systems in routine clinical practice raises several issues. Reported evidence is still very limited, and further studies are needed to confirm the clinical applicability of artificial intelligence. Moreover, better training of clinicians designed to use these systems should be ensured, and evidence-based guidelines regarding this topic should be produced to enhance the strengths of artificial systems and minimize their limits.

Angle of progression measured using transperineal ultrasound for prediction of uncomplicated operative vaginal delivery: systematic review and meta-analysis

OBJECTIVE

To determine whether intrapartum transperineal ultrasound measurement of the angle of progression (AoP) during the second stage of labor can predict uncomplicated operative vaginal delivery (OVD) using vacuum or forceps extraction.

METHODS

A systematic search in PubMed, EMBASE, Scopus, Web of Science and Google Scholar was performed from inception to February 2021. Studies assessing the predictive accuracy of AoP, measured using intrapartum transperineal ultrasound, for uncomplicated OVD, defined as successful vaginal delivery within three pulls using forceps or no more than two detachments of the vacuum extractor cup, were included. Study quality was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) tool. Summary receiver-operating-characteristics (ROC) curves, pooled sensitivity and specificity, area under the ROC curve (AUC) and summary likelihood ratios (LRs) were calculated.

RESULTS

Seven studies reporting on a total of 782 patients undergoing OVD were included in this systematic review and meta-analysis. Second-stage AoP measured during maternal rest had a pooled sensitivity of 80% (95% CI, 59-92%) and specificity of 89% (95% CI, 76-95%), with a LR+ of 7.3 (95% CI, 3.1-15.8) for uncomplicated OVD. AoP measured during active pushing had a sensitivity of 91% (95% CI, 85-94%) and specificity of 83% (95% CI, 69-92%), with a LR+ of 5.4 (95% CI, 2.7-10.6) for uncomplicated OVD. The performance of AoP measured at rest was particularly high in nulliparous women, with a sensitivity of 87% (95% CI, 75-94%) and specificity of 90% (95% CI, 82-94%) for uncomplicated OVD.

CONCLUSION

AoP may be a reliable predictor for uncomplicated OVD when measured during the second stage of labor, especially in nulliparous women. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Sonographic evaluation of the fetal head position and attitude during labor

Fetal malpresentation, malposition, and asynclitism are among the most common determinants of a protracted active phase of labor, arrest of dilatation during the first stage, and arrest of descent in the second stage. The diagnosis of these conditions is traditionally based on vaginal examination, which is subjective and poorly reproducible. Intrapartum sonography has been demonstrated to yield higher accuracy than vaginal examination in characterizing fetal malposition, and some guidelines endorse its use for the verification of the occiput position before performing an instrumental delivery. It is also useful for the objective diagnosis of the malpresentation or asynclitism of the fetal head. According to our experience, the sonographic assessment of the head position in labor is simple to perform also for clinicians with basic ultrasound skills, whereas the assessment of malpresentation and asynclitism warrants a higher level of expertise. When clinically appropriate, the fetal occiput position can be easily ascertained using transabdominal sonography combining the axial and the sagittal planes. With the transducer positioned on the maternal suprapubic region, the fetal head can be visualized, and landmarks including the fetal orbits, the midline, and the occiput itself with the cerebellum and the cervical spine (depending on the type of fetal position) can be demonstrated below the probe. Sinciput, brow, and face represent the 3 "classical" variants of cephalic malpresentation and are characterized by a progressively increasing degree of deflexion from vertex presentation. Transabdominal sonography has been recently suggested for the objective assessment of the fetal head attitude when a cephalic malpresentation is clinically suspected. Fetal attitude can be evaluated on the sagittal plane with either a subjective or an objective approach. Two different sonographic parameters such as the occiput-spine angle and the chin-chest angle have been recently described to quantify the degree of flexion in fetuses in non-occiput-posterior or occiput-posterior position, respectively. Finally, although clinical examination still represents the mainstay of diagnosis of asynclitism, the use of intrapartum sonography has been shown to confirm the digital findings. The sonographic diagnosis of asynclitism can be achieved in expert hands using a combination of transabdominal and transperineal sonography. At suprapubic sonography on the axial plane only, 1 orbit can be visualized (squint sign) while the sagittal suture appears anteriorly (posterior asynclitism) or posteriorly (anterior asynclitism) displaced. Eventually the transperineal approach does not allow the visualization of the cerebral midline on the axial plane if the probe is perpendicular to the fourchette. In this expert review we summarize the indications, technique, and clinical role of intrapartum sonographic evaluation of fetal head position and attitude.

Novel artificial intelligence approach for automatic differentiation of fetal occiput anterior and non-occiput anterior positions during labor

OBJECTIVES

To describe a newly developed machine-learning (ML) algorithm for the automatic recognition of fetal head position using transperineal ultrasound (TPU) during the second stage of labor and to describe its performance in differentiating between occiput anterior (OA) and non-OA positions.

METHODS

This was a prospective cohort study including singleton term (> 37 weeks of gestation) pregnancies in the second stage of labor, with a non-anomalous fetus in cephalic presentation. Transabdominal ultrasound was performed to determine whether the fetal head position was OA or non-OA. For each case, one sonographic image of the fetal head was then acquired in an axial plane using TPU and saved for later offline analysis. Using the transabdominal sonographic diagnosis as the gold standard, a ML algorithm based on a pattern-recognition feed-forward neural network was trained on the TPU images to discriminate between OA and non-OA positions. In the training phase, the model tuned its parameters to approximate the training data (i.e. the training dataset) such that it would identify correctly the fetal head position, by exploiting geometric, morphological and intensity-based features of the images. In the testing phase, the algorithm was blinded to the occiput position as determined by transabdominal ultrasound. Using the test dataset, the ability of the ML algorithm to differentiate OA from non-OA fetal positions was assessed in terms of diagnostic accuracy. The F₁ -score and precision-recall area under the curve (PR-AUC) were calculated to assess the algorithm's performance. Cohen's kappa (κ) was calculated to evaluate the agreement between the algorithm and the gold standard.

RESULTS

Over a period of 24 months (February 2018 to January 2020), at 15 maternity hospitals affiliated to the International Study group on Labor ANd Delivery Sonography (ISLANDS), we enrolled into the study 1219 women in the second stage of labor. On the basis of transabdominal ultrasound, they were classified as OA (n = 801 (65.7%)) or non-OA (n = 418 (34.3%)). From the entire cohort (OA and non-OA), approximately 70% (n = 824) of the patients were assigned randomly to the training dataset and the rest (n = 395) were used as the test dataset. The ML-based algorithm correctly classified the fetal occiput position in 90.4% (357/395) of the test dataset, including 224/246 with OA (91.1%) and 133/149 with non-OA (89.3%) fetal head position. Evaluation of the algorithm's performance gave an F₁ -score of 88.7% and a PR-AUC of 85.4%. The algorithm showed a balanced performance in the recognition of both OA and non-OA positions. The robustness of the algorithm was confirmed by high agreement with the gold standard (κ = 0.81; P < 0.0001).

CONCLUSIONS

This newly developed ML-based algorithm for the automatic assessment of fetal head position using TPU can differentiate accurately, in most cases, between OA and non-OA positions in the second stage of labor. This algorithm has the potential to support not only obstetricians but also midwives and accoucheurs in the clinical use of TPU to determine fetal occiput position in the labor ward. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.