Innovations in ultrasound training in obstetrics

The performance of sonographic antenatal birth weight assessment assisted with artificial intelligence compared to that of manual examiners at term

PURPOSE

The aim of this study is to investigate the differences in the accuracy of sonographic antenatal fetal weight estimation at term with artificial intelligence (AI) compared to that of clinical sonographers at different levels of experience.

METHODS

This is a prospective cohort study where pregnant women at term scheduled for an imminent elective cesarean section were recruited. Three independent antenatal fetal weight estimations for each fetus were blindly measured by an experienced resident physician with level I qualification from the German Society for Ultrasound in Medicine (group 1), a senior physician with level II qualification (group 2), and an AI-supported algorithm (group 3) using Hadlock formula 3. The differences between the three groups and the actual birth weight were examined with a paired t-test. A variation within 10% of birth weight was deemed accurate, and the diagnostic accuracies of both groups 1 and 3 compared to group 2 were assessed using receiver operating characteristic (ROC) curves. The association between accuracy and potential influencing factors including gestational age, fetal position, maternal age, maternal body mass index (BMI), twins, neonatal gender, placental position, gestational diabetes, and amniotic fluid index was tested with univariate logistic regression. A sensitivity analysis by inflating the estimated weights by daily 25 grams (g) gain for days between examination and birth was conducted.

RESULTS

300 fetuses at a mean gestational week of 38.7 ± 1.1 were included in this study and examined on median 2 (2-4) days prior to delivery. Average birth weight was 3264.6 ± 530.7 g and the mean difference of the sonographic estimated fetal weight compared to birthweight was -203.6 ± 325.4 g, -132.2 ± 294.1 g, and -338.4 ± 606.2 g for groups 1, 2, and 3 respectively. The estimated weight was accurate in 62% (56.2%, 67.5%), 70% (64.5%, 75,1%), and 48.3% (42.6%, 54.1%) for groups 1, 2, and 3 respectively. The diagnostic accuracy measures for groups 1 and 3 compared to group 2 resulted in 55.7% (48.7%, 62.5%) and 68.6% (61.8%, 74.8%) sensitivity, 68.9% (58.3%, 78.2%) and 53.3% (42.5%, 63.9%) specificity and 0.62 (0.56, 0.68) and 0.61 (0.55, 0.67) area under the ROC curves respectively. There was no association between accuracy and the investigated variables. Adjusting for sensitivity analysis increased the accuracy to 68% (62.4%, 73.2%), 75% (69.7%, 79.8%), and 51.3% (45.5%, 57.1%), and changed the mean difference compared to birth weight to -136.1 ± 321.8 g, -64.7 ± 291.2 g, and -270.7 ± 605.2 g for groups 1, 2, and 3 respectively.

CONCLUSION

The antenatal weight estimation by experienced specialists with high-level qualifications remains the gold standard and provides the highest precision. Nevertheless, the accuracy of this standard is less than 80% even after adjusting for daily weight gain. The tested AI-supported method exhibits high variability and requires optimization and validation before being reliably used in clinical practice.

Clinical examination for identifying low-risk pregnancies suitable for expectant management beyond 40-41 gestational weeks: maternal and fetal outcomes

PURPOSE

There is an ongoing discussion on whether the benefits of term elective labor induction outweigh its potential risks. This study evaluated the utility of a comprehensive clinical examination in identifying low-risk pregnancies suitable for expectant management beyond gestational age 40‒41 weeks and compared their outcomes with earlier labor induction by indication.

METHODS

Pregnant women (n = 722) with ≥ 40 + 0 gestational weeks referred to a tertiary hospital were included in this prospective cohort. The study population was divided into the primary induction group (induction before 42 + 0 gestational weeks) and the expectant management group (spontaneous labor onset or induction at 42 + 0 gestational weeks), by decision based on a primary consultation. The Chi-square test and logistic regression were applied. The outcome measures were composite adverse fetal outcome (admission to a neonatal intensive care unit, metabolic acidosis, or Apgar score < 7 at 5 min), treatment with intrapartum antibiotics, intrapartum maternal fever ≥ 38 °C, intrapartum cesarean section, and postpartum hemorrhage ≥ 1500 ml.

RESULTS

The main outcome measures did not differ significantly between the primary induction group (n = 258) and the expectant management group (n = 464): composite adverse fetal outcome (OR = 2.29, 95% CI = 0.92-5.68; p = 0.07), intrapartum cesarean section (OR = 1.00, 95% CI = 0.64-1.56; p = 1.00), postpartum hemorrhage ≥ 1500 ml (OR = 1.89, 95% CI = 0.92-3.90; p = 0.09), intrapartum maternal fever ≥ 38 °C (OR = 1.26, 95% CI = 0.83-1.93; p = 0.28), or treatment with intrapartum antibiotics (OR = 1.25, 95% CI = 0.77-2.02; p = 0.37).

CONCLUSION

A comprehensive clinical examination at 40‒41 gestational weeks can identify pregnancies that might be managed expectantly until 42 gestational weeks obtaining similar outcomes to those induced earlier.

Effectiveness of Technology-Supported Ultrasound Training in Prenatal Diagnosis through an Adaptive Image Recognition Training System (AdaptUS)

Background

Prenatal diagnostics, particularly ultrasound examinations, are vital for monitoring fetal development and detecting potential complications. Traditional ultrasound training often lacks adequate focus on image recognition and interpretation, which are crucial for accurate diagnostics. This study evaluates the effectiveness of the AdaptUS module, a technology-supported, adaptive learning platform designed to enhance ultrasound diagnostic skills in prenatal medicine.

Methods

A prospective cross-sectional study was conducted with 76 medical students from the German University Hospital, divided into an intervention group (n = 37) and a control group (n = 39). The intervention group engaged with the AdaptUS module, which adjusts its content based on individual performance. More precisely, it is a learning program for ultrasound images that, while not directly adaptive to the user's skill level, can be considered adaptive in the sense that incorrectly answered images are presented again for re-interpretation. However, the images are currently shown at random and are not yet adjusted to the user's abilities, ensuring that the challenge is consistent but not tailored to skill level. It is important to note that this is not an ultrasound image software, but rather an image interpretation software designed to help users improve their diagnostic skills through repeated exposure to medical images. In contrast, the control group did not receive this training. Both groups were assessed on their ultrasound diagnostic skills at the beginning and end of the semester using a series of 16 questions, which involved interpreting images correctly rather than a standard multiple-choice format. Statistical analysis was performed to compare the pre- and post-test results within and between the groups.

Results

The intervention group showed a significant improvement in their mean test scores, increasing from 70.9% to 86.0% (p < 0.001), while the control group's scores decreased slightly from 62.0% to 59.0%, though this change was not statistically significant. The difference in score improvements between the intervention and control groups was statistically significant (p < 0.001). The feedback from students in the intervention group was overwhelmingly positive, highlighting the system's flexibility in addressing individual learning needs and suggesting its potential for broader integration into medical curricula.

Discussion

The AdaptUS training module significantly enhances ultrasound diagnostic skills, particularly in prenatal medicine, by providing a personalized learning experience that addresses the gaps in traditional training methods. The success of AdaptUS underscores the importance of integrating adaptive learning technologies into medical education to bridge the gap between theoretical knowledge and practical application. Future research should explore the long-term impact of such training on clinical practice and consider incorporating advanced technologies like virtual reality to further enhance educational outcomes.