Monopronucleated (1PN) and tripronuclear (3PN) zygotes formation during assisted reproduction in POSEIDON group 4 patients: Emphasizing on polar bodies

Predicting the risk of a high proportion of three/multiple pronuclei (3PN/MPN) zygotes in individual IVF cycles using comparative machine learning algorithms

BACKGROUND

The majority of machine learning applications in assisted reproduction have been focused on predicting the likelihood of pregnancy. In the present study, we aim to investigate which machine learning models are most effective in predicting the occurrence of a high proportion (>30 %) of 3PN/MPN zygotes in individual IVF cycles.

METHODS

Eight machine learning algorithms were trained and compared, including the AdaBoost and Gaussian NB. Data from IVF cycles carried out from September 2015 to September 2019 were used as a training set. Cycle data from October 2019 to June 2020 were used as a validation set to verify the training model. Cycles with a 3PN/MPN zygote proportion higher than 30 % were classified as high 3PN/MPN zygote proportion cycles.

RESULTS

The AdaBoost algorithm was the best model for model construction and external validation. In both the training and validation sets, age, basal FSH, FSH and E2 level on the day of Gonadotrophin (GN) stimulation, and FSH and LH levels on the day of HCG were statistically higher in patients with 3PN/MPN > 30 % than in patients with 3PN/MPN ≤ 30 %; AFC, AMH, E2 level on HCG day and total number of oocytes were lower in patients with 3PN/MPN > 30 % than in patients with 3PN/MPN ≤ 30 %. The top five predictors were the number of oocytes retrieved, age, male factor infertility, AFC, and total days of GN stimulation.

CONCLUSION

By applying a suitable machine learning algorithm, we can potentially predict the risk of a high proportion of 3PN/MPN zygotes in individual IVF cycles before insemination and avoid polyspermy fertilization by ICSI fertilization method.

Comparison of miscarriage rates in low prognosis patients according to the POSEIDON criteria

OBJECTIVE

The POSEIDON criteria stratified patients with poor ovarian response into four subgroups with exclusive characteristics and assisted reproductive technology success rates. However, limited studies focused on miscarriage in the POSEIDON population. This study aimed to explore whether the miscarriage rate different among low prognosis patients according to POSEIDON criteria.

MATERIALS AND METHODS

This is a retrospective observational study. All clinical pregnancies achieved after in vitro fertilization or intracytoplasmic sperm injection treatment between January 1998 and April 2021 were analyzed. The primary outcome was miscarriage, defined as the pregnancy loss before 20 weeks of gestation age. Miscarriage rate was estimated per clinical pregnancy and gestational sac.

RESULTS

A total of 1222 clinical pregnancies from 1088 POSEIDON patients met the inclusion criteria. The miscarriage rates per clinical pregnancy in each POSEIDON subgroup were as follows: Group 1: 11.7 %, Group 2: 26.5 %, Group 3: 20.9 %, and Group 4: 37.5 %. The miscarriage rate per gestational sac showed a similar trend as the clinical miscarriage rate. Multivariate regression analysis showed that advanced maternal age is an independent factor for miscarriage (Group 2 vs. 1: OR 2.476; Group 4 vs. 3: OR 2.252). Patients with diminished ovarian reserve (DOR) have higher miscarriage risks but without significance (Group 3 vs. 1: OR 1.322; Group 4 vs. 2: OR 1.202).

CONCLUSION

Miscarriage rates differed among low prognosis patients according to the POSEIDON criteria. Age remains a determined risk for miscarriage. DOR might be a potential factor for miscarriage, but it didn't account for a significant impact in POSEIDON patients.

Novel modified criteria for sperm morphology in oocyte insemination could reduce ICSI rates without affecting IVF outcomes

OBJECTIVE

To evaluate the IVF outcomes of conventional insemination for less severe teratozoospermia (LST) patients (sperm morphology >2% and <4% normal forms and total motile sperm count ≥10 × 10⁶) and normal sperm patients defined by WHO criteria 2010 in the interest of reducing intracytoplasmic sperm injection (ICSI) rate in IVF.

MATERIALS AND METHODS

In this retrospective study, a total of 330 patients were recruited in the conventional IVF insemination. Among them, there were 76 patients in LST group and 254 patients in the normal sperm group. Fertilization rate, abnormal fertilization rate, embryo quality, implantation rate, chemical pregnancy rate, clinical pregnancy rate, abortion rate and live birth rate were assessed.

RESULTS

No statistical differences were achieved in the percentage of normally fertilized eggs (85.9% vs. 85.8%), abnormal fertilization rates of 1 PN (2.76% vs. 3.01%) or 3 PN (5.70% vs. 6.30%), good embryo rate (52.4% vs. 51.5%), implantation rate (20.9% vs 17.5%), chemical pregnancy rate (45.1% vs. 39.4%), clinical pregnancy rate (36.0% vs. 31.7%), live birth rate (28.9% vs. 26.7%) and abortion rate (9.6% vs. 10.2%) between LST group and normal sperm group regardless of the sperm morphology.

CONCLUSION

Patients with less severe teratozoospermia may not need ICSI in their IVF treatment since the outcomes particularly the fertilization rates were not affected by the less compromised sperm morphology at all when compared with the normal sperm patients.