Prediction of post-delivery hemoglobin levels with machine learning algorithms.

Predicting postpartum hemorrhage (PPH) before delivery is crucial for enhancing patient outcomes, enabling timely transfer and implementation of prophylactic therapies. We attempted to utilize machine learning (ML) using basic pre-labor clinical data and laboratory measurements to predict postpartum Hemoglobin (Hb) in non-complicated singleton pregnancies. The local databases of two academic care centers on patient delivery were incorporated into the current study. Patients with preexisting coagulopathy, traumatic cases, and allogenic blood transfusion were excluded from all analyses. The association of pre-delivery variables with 24-h post-delivery hemoglobin level was evaluated using feature selection with Elastic Net regression and Random Forest algorithms. A suite of ML algorithms was employed to predict post-delivery Hb levels. Out of 2051 pregnant women, 1974 were included in the final analysis. After data pre-processing and redundant variable removal, the top predictors selected via feature selection for predicting post-delivery Hb were parity (B: 0.09 [0.05-0.12]), gestational age, pre-delivery hemoglobin (B:0.83 [0.80-0.85]) and fibrinogen levels (B:0.01 [0.01-0.01]), and pre-labor platelet count (B*1000: 0.77 [0.30-1.23]). Among the trained algorithms, artificial neural network provided the most accurate model (Root mean squared error: 0.62), which was subsequently deployed as a web-based calculator: https://predictivecalculators.shinyapps.io/ANN-HB . The current study shows that ML models could be utilized as accurate predictors of indirect measures of PPH and can be readily incorporated into healthcare systems. Further studies with heterogenous population-based samples may further improve the generalizability of these models.

Comparison of laparoscopic and hysteroscopic surgical treatments for isthmocele: A prospective cohort.

Objective: To evaluate the clinical outcomes of laparoscopic and hysteroscopic surgical approaches for treating symptomatic isthmocele and identify their associated factors. Materials and Methods: Forty-six patients with symptomatic isthmocele diagnosed using transvaginal saline infusion sonohysterography were enrolled in this prospective cohort study. Patients underwent either laparoscopic or hysteroscopic isthmoplasty based on their residual myometrial thicknesses and fertility desires and were subsequently followed by clinical and ultrasonographic examinations. Results: Twenty-two patients underwent laparoscopy and 24 underwent hysteroscopic surgery. At baseline, there was no significant difference in the mean age and years since the last cesarean section between the two groups. However, the hysteroscopy group had a higher mean parity and previous cesarean sections (p=0.00, 0.03). The most common symptoms were abnormal uterine bleeding, infertility, and dysmenorrhea. The mean baseline residual myometrial thickness was significantly higher in the laparoscopy group (p=0.00), and only laparoscopic surgery led to a significant increase in residual myometrial thickness in patients (p=0.00). Both procedures significantly reduced abnormal uterine bleeding (p=0.00), but only laparoscopy reduced infertility (p=0.00) and hysteroscopy reduced dysmenorrhea (p=0.03). Hysteroscopy showed better symptom resolution in younger patients (p=0.01), whereas age did not affect laparoscopy outcomes. Conclusion: Both approaches showed similar effectiveness in resolving abnormal uterine bleeding, with laparoscopy excelling in infertility resolution and hysteroscopy excelling in dysmenorrhea resolution.

Maternal and neonatal outcomes and determinants of iodine deficiency in third trimester of pregnancy in an iodine sufficient area.

BACKGROUND: Mild to moderate iodine deficiency in pregnant women may expose them to the increased risk of the development of goiter and thyroid disorder. There is a relationship between low maternal UIC (Urinary iodine concentration) in pregnancy and diminished placental weight and neonatal head circumference. The current study was an attempt to assess iodine nutritional status, its determinants and relationship with maternal and neonatal outcomes. METHODS: In this population based cross-sectional study, which was conducted from April 2017 to September 2018, information was collected from 884 women of 20-45 years old who referred for periodic pregnancy visits. UIC was measured in random urine samples by applying a manual method which was based on the Sandell-Kolthoff technique. Information related to neonatal and maternal complications was collected from the individuals enrolled in the study through systematic follow-ups of the research team in each hospitals and the referral of trained midwives to the place of delivery and the retrieval of the case files. RESULTS: The results showed that out of 884 participants 838 (94.8%) had a urinary iodine concentration of more than 150 micrograms/litre and 46 (5.2%) showed urinary iodine concentrations less than 150 micrograms/litre. The median (IQR) urinary iodine concentration in the third trimester was 176 (165-196) µg/l. According to the WHO criteria 46 of the participants (5.2%) had insufficient urinary iodine concentrations, 805 (91.06%) had adequate urinary iodine concentrations while 33 (3.73%) showed more than adequate levels. There were no participants with urinary iodine concentrations higher than 500 micrograms/litre. The main influencing factors on maternal iodine deficiency in this study were weight gain during pregnancy (Odds Ratio (OR) =0.88, 95% CI: 0.82-0.95), number of previous pregnancy (OR = 0.59, 95% CI: 0.39-0.89) the interval between the most recent pregnancies (OR = 0.78, 95% CI: 0.64-0.95), whether or not the pregnancy has been Planned (OR = 2.92, 95% CI: 1.29-6.58) and nutritional complement consumption (OR = 3.64, 95% CI: 1.44-9.1). The need for a neonatal intensive care unit (NICU) admission (OR = 4.64, 95% CI: 1.81-11.9) and preterm birth (OR = 3.29, 95% CI: 1.51-7.1) were significantly related with maternal iodine deficiency before delivery. Also there is no significant differences regarding the mean maternal urinary iodine concentration between the normal and different maternal complications groups (p = 0.47). CONCLUSION: Iodine deficiency in pregnant women can be improved by appreciate planning for pregnancy, proper inter-pregnancy time interval (> 12 months to < 5 years), appropriate nutrition during pregnancy. Besides, controlling maternal urinary iodine concentrations is important to prevent neonatal complications such as preterm delivery and NICU admission.