New method for determining fibrinogen and FDP threshold criteria by artificial intelligence in cases of massive hemorrhage during delivery

Predicting risk of postpartum hemorrhage associated with vaginal delivery of twins: A retrospective study

Many studies have only focused on the risk factors for postpartum hemorrhage (PPH) in singleton vaginal deliveries and twin cesarean deliveries. We analyzed the factors of influencing PPH occurrence in twin vaginal deliveries and developed a nomogram for clinical application. This retrospective study included 274 pregnant women with twin pregnancies who were hospitalized for delivery from January 2014 to December 2018. The patients opted for vaginal delivery and experienced spontaneous labor. Univariate analysis of PPH risk factors was performed. Multivariate analysis was performed using the least absolute shrinkage and selection operator (LASSO) to obtain relevant factors and build a prediction model, which was presented as a nomogram. The model was internally validated by bootstrap self-sampling method. Model accuracy was evaluated with the concordance index (C-index). There were 36 (13.14%) and 238 (86.9%) patients in the PPH and no PPH groups, respectively. Univariate analysis identified twin chorionicity, hypertensive disorders complicating pregnancy (HDCP), anemia in pregnancy, delivery mode of the second twin, oxytocin use during labor, postpartum curettage, cervical laceration, intrapartum fever, fibrinogen degradation products (FDP), and platelet count (PLT) as significant PPH factors. On multivariate analysis, HDCP, anemia in pregnancy, intrapartum fever, oxytocin use during labor, fetal distress, PLT, direct bilirubin, and FDP were noted as significant PPH factors and were included in the prediction model. A C-index of 0.816 was noted after internal validation, and the calibration curve showed good consistency. We developed a model to predict PPH risk in the vaginal delivery of twin pregnancies and visualized it with a nomogram that can be applied clinically to assess PPH risk and aid PPH prevention.

Artificial intelligence to understand fluctuation of fetal brain activity by recognizing facial expressions

OBJECTIVE

To examine whether artificial intelligence can achieve discoveries regarding fetal brain activity.

METHODS

In this observational study, the authors collected images of fetal faces using a four-dimensional ultrasound technique obtained from singleton pregnancies of outpatients in routine practice at 27 to 37 weeks of gestation between February 1 and December 31, 2021. The authors developed an artificial intelligence classifier to recognize seven facial expressions of fetuses, then applied it to video files of fetal facial images to generate the probabilities, as confidence scores, of each expression category. Discrete Fourier transform and chaotic analysis were used to investigate the scores. Mann-Whitney test, t test, variance test, and one-way analysis of variance were used for statistical analysis.

RESULTS

Facial expression changes were observed in cycles averaging 66 to 73 s. The power spectrum showed that mouthing and neutral expressions were the most prevalent. There was a difference between categories for the spectrum (p = 0.004). Two different states--dense and sparse--of confidence scores were discovered. The correlation dimension was 1.19 ± 0.22 and 1.33 ± 0.27 for dense and sparse, respectively (p = 0.047).

CONCLUSION

This method objectively and quantitatively demonstrated fetal brain activity and may provide insight into how the fetus spends its time in utero.

Contributions of artificial intelligence reported in Obstetrics and Gynecology journals: a systematic review

Background

The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been applied in medicine: symbolic AI (eg, knowledge base and ontologies) and nonsymbolic AI (eg, machine learning and artificial neural networks). Consequently, AI has also been applied across most obstetrics and gynecology (OB/GYN) domains, including general obstetrics, gynecology surgery, fetal ultrasound, and assisted reproductive medicine, among others.

Objective

The aim of this study was to provide a systematic review to establish the actual contributions of AI reported in OB/GYN discipline journals.

Methods

The PubMed database was searched for citations indexed with “artificial intelligence” and at least one of the following medical subject heading (MeSH) terms between January 1, 2000, and April 30, 2020: “obstetrics”; “gynecology”; “reproductive techniques, assisted”; or “pregnancy.” All publications in OB/GYN core disciplines journals were considered. The selection of journals was based on disciplines defined in Web of Science. The publications were excluded if no AI process was used in the study. Review, editorial, and commentary articles were also excluded. The study analysis comprised (1) classification of publications into OB/GYN domains, (2) description of AI methods, (3) description of AI algorithms, (4) description of data sets, (5) description of AI contributions, and (6) description of the validation of the AI process.

Results

The PubMed search retrieved 579 citations and 66 publications met the selection criteria. All OB/GYN subdomains were covered: obstetrics (41%, 27/66), gynecology (3%, 2/66), assisted reproductive medicine (33%, 22/66), early pregnancy (2%, 1/66), and fetal medicine (21%, 14/66). Both machine learning methods (39/66) and knowledge base methods (25/66) were represented. Machine learning used imaging, numerical, and clinical data sets. Knowledge base methods used mostly omics data sets. The actual contributions of AI were method/algorithm development (53%, 35/66), hypothesis generation (42%, 28/66), or software development (3%, 2/66). Validation was performed on one data set (86%, 57/66) and no external validation was reported. We observed a general rising trend in publications related to AI in OB/GYN over the last two decades. Most of these publications (82%, 54/66) remain out of the scope of the usual OB/GYN journals.

Conclusions

In OB/GYN discipline journals, mostly preliminary work (eg, proof-of-concept algorithm or method) in AI applied to this discipline is reported and clinical validation remains an unmet prerequisite. Improvement driven by new AI research guidelines is expected. However, these guidelines are covering only a part of AI approaches (nonsymbolic) reported in this review; hence, updates need to be considered.

Early Warning Model of Placenta Accreta Spectrum Disorders Complicated with Cervical Implantation: A Single-Center Retrospective Study

Background

Placenta accreta spectrum (PAS) disorders seriously threaten the safety of the mother and infant in the perinatal period. Moreover, PAS is associated with poor maternal and perinatal outcomes once complicated with cervical implantation. Dismally, there are few reports about PAS complicated with cervical involvement currently, and the early warning models are also rarely reported. To screen the risk factors of PAS complicated with cervical implantation and construct an early risk warning model, we performed the analysis of clinical indicators and images of PAS patients by artificial intelligence (AI) data processing methods.

Methods

The clinical data of 166 patients with PAS in our hospital from January 2016 to September 2020 were retrospectively analyzed. The patients were divided into cervical implantation group and lower uterine implantation group according to the position of placenta implantation. Then, we compared the pregnancy outcomes of the two groups, screened the possible related factors of PAS complicated with cervical implantation by univariate analysis, and established the early warning model by logistic regression analysis.

Results

The maternal outcome of PAS complicated with cervical implantation was worse than that of the lower uterine implantation group. Through univariate analysis and logistic regression analysis, we found that the cervical width, abundant cervical blood flow, and bladder line interruption were all risk factors of PAS complicated with cervical implantation, and their contribution to the establishment of the regression model was statistically significant.

Conclusion

PAS complicated with cervical implantation was extremely severe. Early identification of risk factors and establishment of a risk warning model have certain guiding significance for clinical formulation of a reasonable treatment plan.

Recognition of facial expression of fetuses by artificial intelligence (AI)

OBJECTIVES

The development of the artificial intelligence (AI) classifier to recognize fetal facial expressions that are considered as being related to the brain development of fetuses as a retrospective, non-interventional pilot study.

METHODS

Images of fetal faces with sonography obtained from outpatient pregnant women with a singleton fetus were enrolled in routine conventional practice from 19 to 38 weeks of gestation from January 1, 2020, to September 30, 2020, with completely de-identified data. The images were classified into seven categories, such as eye blinking, mouthing, face without any expression, scowling, smiling, tongue expulsion, and yawning. The category in which the number of fetuses was less than 10 was eliminated before preparation. Next, we created a deep learning AI classifier with the data. Statistical values such as accuracy for the test dataset and the AI confidence score profiles for each category per image for all data were obtained.

RESULTS

The number of fetuses/images in the rated categories were 14/147, 23/302, 33/320, 8/55, and 10/72 for eye blinking, mouthing, face without any expression, scowling, and yawning, respectively. The accuracy of the AI fetal facial expression for the entire test data set was 0.985. The accuracy/sensitivity/specificity values were 0.996/0.993/1.000, 0.992/0.986/1.000, 0.985/1.000/0.979, 0.996/0.888/1.000, and 1.000/1.000/1.000 for the eye blinking, mouthing, face without any expression, scowling categories, and yawning, respectively.

CONCLUSIONS

The AI classifier has the potential to objectively classify fetal facial expressions. AI can advance fetal brain development research using ultrasound.

Clinical Effects of Form-Based Management of Forceps Delivery under Intelligent Medical Model

Background

Forceps delivery is one of the most important measures to facilitate vaginal delivery. It can reduce the rate of first cesarean delivery. Frustratingly, adverse maternal and neonatal outcomes associated with forceps delivery have been frequently reported in recent years. There are two major reasons: one is that the abilities of doctors and midwives in forceps delivery vary from hospital to hospital and the other one is lack of regulations in the management of forceps delivery. In order to improve the success rate of forceps delivery and reduce the incidence of maternal and neonatal complications, we applied form-based management to forceps delivery under an intelligent medical model. The aim of this work is to explore the clinical effects of form-based management of forceps delivery.

Methods

Patients with forceps delivery in Maternal and Child Health Hospital Affiliated to Nanchang University were divided into two groups: form-based patients from January 1, 2019, to December 31, 2020, were selected as the study group, while traditional protocol patients from January 1, 2017, to December 31, 2018, were chosen as the control group. Then, we compared the maternal and neonatal outcomes of these two groups.

Results

There were significant differences in the maternal and neonatal adverse outcomes such as rate of postpartum hemorrhage, degree of perineal laceration, and incidence of neonatal facial skin abrasions between the two groups, whereas differences in the incidence of asphyxia and intracranial hemorrhage were not significant.

Conclusions

Form-based management could help us assess the security of forceps delivery comprehensively, as it could not only improve the success rate of the one-time forceps traction scheme but also reduce the incidence of maternal and neonatal adverse outcomes effectively.