An evaluation of cervical maturity for Chinese women with labor induction by machine learning and ultrasound images.

BACKGROUND: To evaluate the improvement of evaluation accuracy of cervical maturity for Chinese women with labor induction by adding objective ultrasound data and machine learning models to the existing traditional Bishop method. METHODS: The machine learning model was trained and tested using 101 sets of data from pregnant women who were examined and had their delivery in Peking University Third Hospital in between December 2019 and January 2021. The inputs of the model included cervical length, Bishop score, angle, age, induced labor time, measurement time (MT), measurement time to induced labor time (MTILT), method of induced labor, and primiparity/multiparity. The output of the model is the predicted time from induced labor to labor. Our experiments analyzed the effectiveness of three machine learning models: XGBoost, CatBoost and RF(Random forest). we consider the root-mean-squared error (RMSE) and the mean absolute error (MAE) as the criterion to evaluate the accuracy of the model. Difference was compared using t-test on RMSE between the machine learning model and the traditional Bishop score. RESULTS: The mean absolute error of the prediction result of Bishop scoring method was 19.45 h, and the RMSE was 24.56 h. The prediction error of machine learning model was lower than the Bishop score method. Among the three machine learning models, the MAE of the model with the best prediction effect was 13.49 h and the RMSE was 16.98 h. After selection of feature the prediction accuracy of the XGBoost and RF was slightly improved. After feature selection and artificially removing the Bishop score, the prediction accuracy of the three models decreased slightly. The best model was XGBoost (p = 0.0017). The p-value of the other two models was < 0.01. CONCLUSION: In the evaluation of cervical maturity, the results of machine learning method are more objective and significantly accurate compared with the traditional Bishop scoring method. The machine learning method is a better predictor of cervical maturity than the traditional Bishop method.

Management strategy for urologic morbidity in surgery of placenta accreta spectrum: stents or catheters?

OBJECTIVE: Surgery for placenta accreta spectrum disorders is known to be associated with urologic morbidity. Although previous studies have shown preoperative ureteral stent placement might be useful for preventing the urologic morbidity, the patient's discomfort caused by it should not be ignored. Whether there is an alternative management strategy remains unknown. This study was to evaluate the effectiveness of ureteral stents and catheters in preventing urologic injury in patients with placenta accreta spectrum undergoing surgery. METHODS: We conducted a retrospective cohort study. All cases with diagnosed placenta accreta spectrum who underwent surgery at Peking University Third Hospital between January 2018 and December 2020 were collected and reviewed. They were divided into two groups according to the different management strategies for preoperative placement of ureteral catheters or stents. The primary outcome was urologic injury, which was defined as the presence of ureteral or bladder injury during and after surgery. Secondary outcomes included urologic complications within the first three months after surgery. The median (interquartile range) or proportions were reported for variables. The Man Whitney U test, chi-square test and multivariate logistic regression were used for analysis. RESULTS: Ultimately, 99 patients were included in this study. Ureteral catheters were placed in 52 patients and ureteral stents were placed in 47 patients. Placenta accreta, placenta increta, and placenta percreta were diagnosed in three, 19, and 77 women, respectively. The hysterectomy rate was 52.53%. Overall, urologic injuries occurred in three patients (3.03%), including one case of combined bladder and ureteral injury (1.01%) and two cases of bladder injuries (2.02%). Only one ureteral injury occurred in a patient with a ureteral stent, which was recognized postoperatively (p = .475). All bladder injuries were vesical rupture which were recognized and repaired intraoperatively; one patient in the catheter group and two patients in the stent group (p = .929). After adjusting for confounding variables, multinomial regression analysis revealed no significant differences between the two groups in the incidence of bladder injuries(aOR: 0.695, 95% CI: 0.035-13.794, p = .811). A lower risk of urinary irritation (aOR: 0.186, 95% CI: 0.057-0.605, p = .005), hematuria (aOR: 0.011, 95% CI: 0.001-0.136, p < .001), and lower back pain (aOR: 0.075, 95% CI: 0.022-0.261, p < .001) was found in patients with ureteral catheters than in those with ureteral stents. CONCLUSION: The ureteral stents didn't confer a protective benefit in the surgical management for placenta accreta spectrum compare with catheters; however, they did result in a higher incidence of postoperative urologic complications. Ureteral temporal catheters may be an alternative strategy for placenta accreta spectrum cases suspected with urinary tract involved prenatally. Moreover, clearly and explicitly reporting "double J stent" or "temporal catheter" is necessary for future researches.

Value of inferior vena cava diameter and inferior vena cava collapse index in the evaluation of peripartum volume: A prospective cohort study.

OBJECTIVE: The maternal intravascular volume status assessed during and after gestation is valuable but challenging due to the influence of the substantial adaptive cardiovascular changes during pregnancy. The present study aimed to investigate the changes in the size of inferior vena cava (IVC) diameter and collapse index (IVC-CI) during perinatal delivery and whether it is affected by the change in intravascular volume during delivery. STUDY DESIGN: A total of 31 full-term, singleton, and cephalic delivery women delivered by vagina with an estimated blood loss of >500 mL measured longitudinally between September 2019 and September 2020 in the Department of Obstetrics and Gynecology of The Third Hospital in China. The end-expiratory (IVCe) and end-inspiratory (IVCi) diameters of the inferior vena cava were measured at the first, second, and third stages of labor (T1, T2, and T3, respectively) and postpartum haemorrhage ≥500 mL (T4 and after rapid rehydration 500 mL (T5). The collapse index of IVC was calculated, and blood pressure and heart rate were measured. RESULTS: IVCe and IVC-CI changed significantly in a volume-dependent manner during the perinatal period (T1-T5; P < 0.05). IVCe narrowed significantly with volume reduction (after postpartum hemorrhage) and widened significantly with volume increase (after volume resuscitation). IVC-CI increases significantly with decreased capacity and decreases significantly with increased capacity. CONCLUSION: The width and collapse index of IVC reflect the circulatory volume changes during the parturient's perinatal period with postpartum hemorrhage.

Ultrasound for monitoring twin cesarean scar pregnancy following feticide.

OBJECTIVE: Implantation of the conceptus in a twin cesarean scar pregnancy (CSP) is considered the rarest type of ectopic pregnancy. Preserving the fetus in utero and effectively dealing with CSP can be challenging. This study aimed to determine the clinical value of ultrasonography by monitoring imaging changes in twin CSP following selective feticide. METHODS: Ultrasonographic and clinical data were collected from four patients with twin CSP who were treated between December 2017 and December 2018 at our hospital. RESULTS: All patients had a history of cesarean section, followed by a heterotopic CSP, with one embryo implanted into the uterine cavity and the other located in the anterior isthmus. All of the patients were pregnant with twins with double chorionic and amniotic sacs, and all gave birth in our hospital. The patients underwent feticide at 8 to 9 weeks of gestation, after which we focused on monitoring the implantation. Delivery was performed by cesarean section according to scores of an ultrasonic scoring system and clinical manifestations. The patients' uterus was preserved and they recovered. CONCLUSIONS: This study shows that ultrasound is useful for determining the timing of clinical termination of CSP by selective feticide.

An observation study of the emergency intervention in placenta accreta spectrum.

OBJECTIVE: This study explored the probability and outcome of delivery in women with placenta accreta spectrum (PAS) according to gestational age at delivery. METHODS: A retrospective cohort study among women with PAS who had cesarean section was conducted. The gestational week (gw) of delivery and estimated blood loss (EBL) were recorded. The proportion of urgent delivery beyond 32 gw and EBL in women with or without antepartum suspected diagnosis of placenta accreta was compared. RESULTS: Totally, 180 women with PAS were enrolled. Of these, 54 (30.0%, 95% CI 23.8-37.1%) were delivered by urgent cesarean delivery and 126 (70.0%, 95% CI 62.9-76.2%) by elective cesarean section. The probability of emergent delivery was increased from 3.1 to 5.7% at 33-36 weeks, and increased by > 10% beyond 37 weeks. Among 121 antenatal suspected PAS patients, 25 (20.7%, 95% CI 14.4-28.7%) had emergency cesarean section, and 96 (79.3%, 95% CI 71.3-85.6%) experienced elective cesarean. The EBL of PAS in both emergent group (r = - 0.276, p = 0.044) and elective group (r = - 0.370, p < 0.001) was significantly decreased with gestational age progression. The antepartum hemorrhage increased the risk of urgent delivery [OR 2.54 (1.19, 5.44)] (p = 0.016), while PAS with antepartum diagnosis decreased the risk [OR 0.21 (0.10, 0.43)] (p < 0.001). CONCLUSION: Although the incidence of emergency operation in PAS patients was increased at 32-36 gw, there was no significant difference among the groups. The decision of timing for pregnancy termination should be made cautiously. We recommend scheduled operation at around 36-37 gw. In serious cases, the termination time could be arranged as early as appropriate.

An ultrasonic scoring system to predict the prognosis of placenta accreta: A prospective cohort study.

To discuss the value of "self-made ultrasonic scoring system" in predicting the different types of placenta accreta, and for predicting its associated risk of bleeding and hysterectomy.A prospective study was performed in 137 patients who were suspiciously diagnosed with placenta accreta before delivery. All the patients were examined by the scoring system, and were classified into 3 groups according to their scores: score of ≤5 as N1, ≥6 and ≤9 as N2, and ≥10 as N3 groups. The accuracy and the Kappa values were calculated. Hemorrhage during the operation and the uterine resection rate were also compared.There were 73 patients in N1, 36 in N2, and 28 in N3 groups. The prediction accuracy rates were 87.6% (64/73) and 92.0% (25/28), respectively in groups 1 and 3. The Kappa value was 0.75\0.77 for the prediction accuracy rate. The median quantities of hemorrhage during the operation were 400[100, 2000] mL, 1200[300, 9000] mL, and 4000[800, 13,000] mL, respectively. The uterine resection rates were 0.0%(0/73), 11.1%(4/36), and 39.3%(11/28), respectively. Comparison of hemorrhage and uterine resection rate among the 3 groups was significant (P < .001). Among them, statistically significant differences in hemorrhage and uterine resection rate were observed in every 2 groups (P < .05).These results suggested that self-made ultrasonic scoring system remained an effective diagnostic tool for assessing the types of placenta accreta, and predicted the associated bleeding risk, indicating the possibility of hysterectomy.

Ultrasonographic diagnosis of severe placental invasion.

AIM: Placental invasion is a life-threatening obstetric complication. The aim of this study was to identify the optimal ultrasonographic (US) criteria for placenta increta/percreta in order to improve diagnostic accuracy. METHODS: In a retrospective diagnostic study, all 116 patients at Peking University Third Hospital who had been diagnosed with placental invasion from October 2006 to October 2013 were included. Depending on their clinical and/or histopathological diagnosis, the study was divided into two groups: the Placenta Accreta Group (63 cases) and the Placenta Increta/Percreta Group (53 cases). The US images were analyzed for differences between placenta accreta and placenta increta/percreta. RESULTS: The sonographic criteria found to have predictive value for placenta increta/percreta using a regression model were: deficiency of retroplacental sonolucent zone and/or segmental retroplacental myometrial thinning less than 1 mm, multiple vascular lacunae presenting a 'moth hole' appearance, and placenta previa. Using a cut-off point of 0.589, the sensitivity and specificity were 81.1% and 77.8%, respectively. The area under the receiver-operator curve was 0.848 (P < 0.001). CONCLUSION: US diagnosis not only allows the detection of placental invasion, but also facilitates preliminary classification. The three aforementioned criteria facilitate the identification of placenta increta/percreta for precise and comprehensive clinical decision-making.

[Clinical value of MRI in cesarean scar pregnancy].

OBJECTIVE: To explore the clinical value of MRI in diagnosing and treating cesarean scar pregnancy (CSP). METHODS: A retrospective analysis was conducted on the clinical manifestations of 54 patients diagnosed with CSP between January 2009 to January 2013 in Peking University Third Hospital. Based on the patients' MRI image and other clinical datas, we did transvaginal operation on patients with CSP1, and transvaginal combined with abdominal operations on patients with CSP2. The intraoperative blood loss, operation time, postoperative hospital stay, and the length of time required for of serum hCG dropping to normal of the patients were analyzed. RESULTS: The average age of the 54 patients was (34±5) years and the average duration of gestation was (56±16) days, all patients' vital sign were stable, the hCG level was 23-142 962 U/L before treatment. Twelve patients were diagnosed with CSP1 by MRI, and 5 of them had focus of 1-2 cm in diameter, the 5 patients' serum hCG level was 436-1 159 U/L and 23-32 days after drug administration, their hCG level returned to normal; the other 7 patients had focus of 2.0-4.4 cm in diameter, and their hCG level was 2 218-63 446 U/L, lesion resection was done on the 7 patients by hysteroscope or under B-ultrasound monitor. Forty-two patients were diagnosed with CSP2, and their focus were 1.0-7.1 cm in diameter, and serum hCG level were 23-142 962 U/L. We did bilateral uterine artery occlusion by laparoscope or laparotomy during operation for 22 patients or bilateral uterine artery embolization (UAE) before operation for 20 patients, then we did lesion resections. The blood loss during operation of CSP1 or CSP 2 was 50.1, 267.2 ml; operation time was 30, 128 minutes; postoperative hospital stay was 4.6, 6.7 days; their serum hCG returned to normal 13-30 days after the surgery. All the 54 patients' uterus were and the patients undergoing operations were all cured without the second operation. CONCLUSION: MRI is an effective method to conduct clinical treatment in CSP.