Machine learning for predicting elective fertility preservation outcomes.

This retrospective study applied machine-learning models to predict treatment outcomes of women undergoing elective fertility preservation. Two-hundred-fifty women who underwent elective fertility preservation at a tertiary center, 2019-2022 were included. Primary outcome was the number of metaphase II oocytes retrieved. Outcome class was based on oocyte count (OC): Low (≤ 8), Medium (9-15) or High (≥ 16). Machine-learning models and statistical regression were used to predict outcome class, first based on pre-treatment parameters, and then using post-treatment data from ovulation-triggering day. OC was 136 Low, 80 Medium, and 34 High. Random Forest Classifier (RFC) was the most accurate model (pre-treatment receiver operating characteristic (ROC) area under the curve (AUC) was 77%, and post-treatment ROC AUC was 87%), followed by XGBoost Classifier (pre-treatment ROC AUC 74%, post-treatment ROC AUC 86%). The most important pre-treatment parameters for RFC were basal FSH (22.6%), basal LH (19.1%), AFC (18.2%), and basal estradiol (15.6%). Post-treatment parameters were estradiol levels on trigger-day (17.7%), basal FSH (11%), basal LH (9%), and AFC (8%). Machine-learning models trained with clinical data appear to predict fertility preservation treatment outcomes with relatively high accuracy.

A novel method for office aspiration curettage in cases of retained products of conception: A randomized controlled trial.

INTRODUCTION: Missed abortion can be treated with medication or aspiration curettage. A Karman aspiration cannula is another option. We evaluated its success in evacuating retained products of conception (RPOC) based on symptoms, endometrial thickness, endometrial irregularity, and blood flow seen on Doppler ultrasound (indicative of placenta). MATERIAL AND METHODS: This prospective, randomized, nonblinded trial was conducted in a university-affiliated medical center. It included 40 women diagnosed with missed abortion and two failed courses of 600 µg buccal misoprostol, one  week apart, randomly assigned to treatment or controls. One week after the second misoprostol course, immediately after evaluating endometrial thickness, endometrial irregularity using Doppler ultrasound, and with blood flow indicative of RPOC, women in the aspiration group underwent endometrial suction with a Karman aspiration cannula. The 5-6 mm cannula attached to a 60 mL syringe was inserted into the uterus under ultrasound guidance. The contents were aspirated until the uterus was empty. Control group patients did not receive additional treatment. All were scheduled for ambulatory, operative hysteroscopy under anesthesia 1 month later (departmental protocol). On that day, all women with RPOC on Doppler ultrasound underwent hysteroscopy. Bleeding days, days with pain, pain according to visual analog scale, length of hospitalization, and infection rate were recorded. NIH clinical trial registration number NCT02917785. RESULTS: In the study group, 90% did not need hysteroscopy, compared with 50% of controls (p = 0.014). No complications were noted. At all visits, we used Doppler ultrasound to exclude or confirm RPOC. Pathology revealed RPOC in all women who underwent aspiration. Average visual analog scale score for office aspiration (n = 20) was 4.9 ± 3.6. vs. 6.3 ± 3.4 for the first (p = 0.157) and 4.7 ± 3.3 for the second (p = 0.836) misoprostol treatment cycle. The treatment group experienced 6.1 days of bleeding and the control group experienced 1.4 days (p = .006). CONCLUSIONS: Based on our criteria of diagnosing RPOC according to symptoms, endometrial thickness, endometrial irregularity, and blood flow indicative of placental tissue seen on Doppler ultrasound and histo-pathological confirmation, aspiration using Karman cannula can be an effective therapeutic approach. It may be a safe alternative for women with RPOC after misoprostol failure.