Expectant Management of a Triploid Partial Molar Pregnancy at 26 Weeks' Gestation: A Case Report.

Introduction Triploid partial molar pregnancies are not viable, and confer maternal risks including preeclampsia, hemorrhage, gestational trophoblastic neoplasia, and trophoblastic embolization. We report a case managed expectantly until 26 weeks' gestation in a patient requesting continuation of pregnancy. Case Presentation This G2P1 presented with fetal anomalies indicative of triploid partial molar pregnancy. The pregnancy was complicated by anemia, hyperthyroidism, supraventricular tachycardia, and threatened preterm labor. Her care involved maternal fetal medicine collaborating with internal medicine, palliative care, anesthesia and critical care. Labor was augmented at 26 weeks' gestation, resulting in vaginal delivery. Postpartum course was notably complicated by acute respiratory distress in the immediate postpartum period, which self-resolved. Postpartum hemorrhage and retained products of conception were additional complications. Conclusion This unique case highlights the role of multidisciplinary collaboration and shared decision making in challenging circumstances.

Deep learning prediction of renal anomalies for prenatal ultrasound diagnosis.

Deep learning algorithms have demonstrated remarkable potential in clinical diagnostics, particularly in the field of medical imaging. In this study, we investigated the application of deep learning models in early detection of fetal kidney anomalies. To provide an enhanced interpretation of those models' predictions, we proposed an adapted two-class representation and developed a multi-class model interpretation approach for problems with more than two labels and variable hierarchical grouping of labels. Additionally, we employed the explainable AI (XAI) visualization tools Grad-CAM and HiResCAM, to gain insights into model predictions and identify reasons for misclassifications. The study dataset consisted of 969 ultrasound images from unique patients; 646 control images and 323 cases of kidney anomalies, including 259 cases of unilateral urinary tract dilation and 64 cases of unilateral multicystic dysplastic kidney. The best performing model achieved a cross-validated area under the ROC curve of 91.28% ± 0.52%, with an overall accuracy of 84.03% ± 0.76%, sensitivity of 77.39% ± 1.99%, and specificity of 87.35% ± 1.28%. Our findings emphasize the potential of deep learning models in predicting kidney anomalies from limited prenatal ultrasound imagery. The proposed adaptations in model representation and interpretation represent a novel solution to multi-class prediction problems.

Expanding the clinical spectrum of autosomal-recessive renal tubular dysgenesis: Two siblings with neonatal survival and review of the literature.

BACKGROUND: Autosomal-recessive renal tubular dysgenesis (AR-RTD) is a rare genetic disorder caused by defects in the renin-angiotensin system that manifests as fetal anuria leading to oligohydramnios and Potter sequence. Although the most common outcome is neonatal death from renal failure, pulmonary hypoplasia, and/or refractory arterial hypotension; several cases have been reported that describe survival past the neonatal period. METHODS: Herein, we report the first family with biallelic ACE variants and more than one affected child surviving past the neonatal period, as well as provide a review of the previously reported 18 cases with better outcomes. RESULTS: While both siblings with identical compound heterozygous ACE variants have received different treatments, neither required renal replacement therapy. We show that both vasopressin and fludrocortisone in the neonatal period may provide survival advantages, though outcomes may also be dependent on the type of gene variant, as well as other factors. CONCLUSION: While AR-RTD is most often a lethal disease in the neonatal period, it is not universally so. A better understanding of the factors affecting survival will help to guide prognostication and medical decision-making.

Evaluation of residents' documentation skills after a simulated operative vaginal delivery.

OBJECTIVE: We sought to evaluate the role of the physician as communicator by assessing obstetrics trainees' documentation of a simulated operative vaginal delivery. METHODS: Nineteen residents in obstetrics and gynaecology (PGY-2 to PGY-5) participated in a simulation exercise involving an operative vaginal delivery on a high-fidelity mannequin. After the session, the residents were asked to document the events of the delivery as they would in a standard progress note. The residents' notes were then evaluated for the presence of 14 elements that the Society of Obstetricians and Gynaecologists of Canada has determined are essential in the appropriate documentation of an operative vaginal delivery. RESULTS: Sixty-three percent (12/19) of trainees documented at least 10 of the 14 elements required, with a range of 7 to 13 elements included. The elements that were most likely to be documented were the instrument used (100%, 19/19) and the number of contractions during which traction was applied (94.7%, 18/19). The elements that were least likely to be included were the location of application of the instrument (15.8%, 3/19) and the amount of traction applied with the instrument (0%, 0/19). CONCLUSION: Simulation can be used as a form of standardized formative evaluation to assess trainees' written communication skills and to identify deficiencies.