Artificial Intelligence, Intrapartum Ultrasound and Dystocic Delivery: AIDA (Artificial Intelligence Dystocia Algorithm), a Promising Helping Decision Support System

Abstract

The position of the fetal head during engagement and progression in the birth canal is the primary cause of dystocic labor and arrest of progression, often due to malposition and malrotation. The authors performed an investigation on pregnant women in labor, who all underwent vaginal digital examination by obstetricians and midwives as well as intrapartum ultrasonography to collect four "geometric parameters", measured in all the women. All parameters were measured using artificial intelligence and machine learning algorithms, called AIDA (artificial intelligence dystocia algorithm), which incorporates a human-in-the-loop approach, that is, to use AI (artificial intelligence) algorithms that prioritize the physician's decision and explainable artificial intelligence (XAI). The AIDA was structured into five classes. After a number of "geometric parameters" were collected, the data obtained from the AIDA analysis were entered into a red, yellow, or green zone, linked to the analysis of the progress of labor. Using the AIDA analysis, we were able to identify five reference classes for patients in labor, each of which had a certain sort of birth outcome. A 100% cesarean birth prediction was made in two of these five classes. The use of artificial intelligence, through the evaluation of certain obstetric parameters in specific decision-making algorithms, allows physicians to systematically understand how the results of the algorithms can be explained. This approach can be useful in evaluating the progress of labor and predicting the labor outcome, including spontaneous, whether operative VD (vaginal delivery) should be attempted, or if ICD (intrapartum cesarean delivery) is preferable or necessary.

Keywords: artificial intelligence; asynclitism; cesarean section; dystocia; intrapartum ultrasound; labor; malposition; malrotation; vaginal operative delivery.

Figure 1

Midline angle (MLA) and fetal head–symphysis distance (HSD) for all patients involved in the study.

Figure 2

The ROC curve of six machine learning algorithms in the delivery outcome classification of our dataset.

Figure 3

(A) Angle of progression (AoP): the drawing on the right and the US photo on the left show the AoP (red line) with the fetal head in the occiput anterior position; (B) fetal head–symphysis distance (HSD): the drawing on the right and the US photo on the left show the HSD (red line) with the fetal head in the occiput anterior position; (C) midline angle (MLA): the drawing on the right and the US photo on the left shows the MLA with the fetal head in the left occiput posterior position (white/black line: midline, the echogenic line between the two cerebral hemispheres; red line: anteroposterior diameter of the pubis). Longitudinal translabial sonography detected the MLA; (D) asynclitism degree (AD): the drawing on the right and the US photo on the left show the AD with the fetal head in the right occiput posterior position with anterior asynclitism (white/black line: midline, the echogenic line between the two cerebral hemispheres; red line: anterior asynclitism degree, perpendicular to the white/black line).

Figure 4

The values of the four geometric parameters, AoP, HSD, MLA, and AD, measured at the same time for the 135 cases of the patients involved in this study and grouped by delivery outcome. (A) Angle of progression (AoP), values between min 72° and max 192°. (B) Fetal head–symphysis distance (HSD), values between min 10 mm and max 51 mm. (C) Asynclitism degree (AD), values between min 4 mm and max 95 mm. (D) Midline angle (MLA): values between min 26° and max 90°.