Purpose
AI and its machine learning algorithms have proven useful in several fields of medicine, including medically assisted reproduction. The purpose of the study was to construct several ...predictive models based on clinical data and select the best models to predict IUI procedure outcomes.
Methods
Clinical data (patient baseline characteristics, sperm quality, hormonal status, and cycle data) from 1029 IUI procedures performed in 413 couples stimulated by clomiphene citrate, letrozole, or gonadotropins were used to build several models to predict clinical pregnancy. The models included ANN, random forest, PLS, SVM, and linear models using the caret package in R. The models were evaluated using ROC analysis by means of random CV on test data.
Results
Out of the best performing models, the random forest model achieved an AUC of 0.66, a sensitivity of 0.432, and a specificity of 0.756. This performance was followed by the PLS model, which achieved a sensitivity of 0.459 and specificity of 0.734. The other models achieved significantly lower AUCs. When adjusting the predictive cutoff value, confusion matrices show that clinical pregnancy is twice as likely in the case of positive prediction.
Conclusion
Among the compared methods, the random forest and PLS models demonstrated superior performance in predicting the clinical outcome of IUI. With additional research and clinical validation, AI methods may be successfully used in improving patient selection and consequently lead to better clinical results.
The aim of the study was to determine predictive factors for live birth after in vitro fertilization with autologous oocytes in women ≥40 years of age.
Authors conducted a retrospective analysis of ...in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) cycles performed at the Department of Reproductive Medicine and Gynecologic Endocrinology, University Medical Centre Maribor, Slovenia between January 2006 and December 2015 in women aged 40 or more. The characteristics of patients and cycles were compared regarding live birth as the final outcome.
A total of 1920 IVF/ICSI cycles with egg retrieval in women ≥40 years of age were performed leading to 1591 embryo transfers. The live birth rate per embryo transfer was 17.3% at 40, 11.6% at 41, 8.2% at 42, 7.9% at 43, 1.9% at 44 and 0.0% at ≥45 years of age. The multivariate logistic regression model showed that besides women's age (OR 0.66, 95% CI: 0.55-0.78), the number of previous cycles (OR 0.88, 95% CI: 0.82-0.95), number of good quality embryos on day 2 (OR 1.19, 95% CI: 1.05-1.36), number of embryos transferred (OR 1.57, 95% CI: 1.19-2.07) and day 5 embryo transfer (OR 2.21, 95% CI: 1.37-3.55) were also independent prognostic factors for live birth.
The chance of in vitro fertilization success in women ≥40 years of age should not be estimated only on the woman's age, but also on other predictive factors: number of previous cycles, number of good quality embryos on day 2, number of transferred embryos and blastocyst embry transfer.
Obravnava žensk v obdobju predmenopavze, ob menopavzi in kasneje se je v novem tisočletju pomembno spremenila. Randomizirane klinične raziskave so bistveno omejile indikacije za uvedbo hormonskega ...zdravljenja (HZ) in s tem menopavzno medicino postavile pred velik izziv. Na srečo so najnovejša dognanja potrdila, da je ob pravilni uporabi in izbiri HZ korist še vedno bistveno večja od tveganja. Zato smo pripravili posodobljena stališča o menopavzni medicini, ki so v skladu z aktualnimi mednarodnimi priporočili in prilagojena posebnostim slovenskega prostora.
•Blastocyst collapsing is an invasive intervention and still not evidence based•This is the first matched case-control study analysing live births and neonatal outcome•Collapsing resulted in better ...survival and a non-significant 5% increase in live births•To confirm a 5% improvement, more than 2500 cases will be needed•No difference was found in neonatal outcomes
Does laser-induced artificial blastocoel collapse result in better blastocyst cryopreservation survival and a higher live birth rate (LBR) in comparison with intact counterparts?
Half of the supernumerary blastocysts from IVF cycles were randomly selected before vitrification for laser-induced artificial collapsing or vitrification in intact form. A matched case-control study of first transfers of single blastocysts artificially collapsed (case) or intact (control) before vitrification was conducted. Controls were matched to cases on a 1:1 ratio by female age, parity, fresh and vitrified cycle protocol, blastocyst age and quality, resulting in 309 case-control pairs.
The two groups were comparable in terms of their characteristics. Survival rates in the case and control groups (97.8% and 95.7%; P = 0.133) were comparable, but the optimal survival rate was higher in the case group (78.2% and 69.3%; P = 0.03). Clinical pregnancy rates (38.2% and 35.3%; P = 0.518), miscarriage rates (15.2% and 22%; P = 0.190), LBR per transfer (32.4% and 27.5%; P = 0.221) and LBR per warmed blastocyst (31.6% and 26.3%; P = 0.137) were not statistically different between the case and control groups. No significant difference in preterm births (11.1% versus 15.7%), birthweights (3333 ± 723 g versus 3304 ± 609 g) or sex ratio (49.3% versus 50.7% boys) was observed between the two groups. No major malformations were detected in the study population.
Compared with vitrification of intact blastocysts, collapsed blastocysts resulted in a significantly higher optimal survival rate, and although they resulted in a 5% higher LBR, this was not significant for the chosen sample size. Neonatal outcomes were comparable in the two groups.
Display omitted
What is the clinical importance of vitrified-warmed blastocyst transfer timing if performed on days 5, 6 and 7 after detecting the LH surge using urine tests?
Between 2013 and 2019, 2080 ...vitrified-warmed blastocyst transfers in a true natural cycle were performed and later analysed at the Department of Reproductive Medicine, University Medical Centre Maribor, Slovenia. Urine LH tests were performed twice daily to monitor the onset of the LH surge. Vitrified-warmed blastocyst transfer (frozen embryo transfer FET) was performed on day 5 (group 1), 6 (group 2) or 7 (group 3) after the LH surge in 18%, 77% and 4% of cycles, respectively. The patient and cycle characteristics among the groups were compared using the Cochran–Mantel–Haenszel test and respective generalized linear mixed models. Propensity score matching was used to adjust for potential differences among the groups.
There were no statistically significant differences between groups 1, 2 and 3 in the cycle and patient characteristics, clinical pregnancy rate (38% versus 39% versus 31%), implantation rate (34% versus 36% versus 31%), miscarriage rate (7% versus 9% versus 7%) and delivery rate (31% versus 31% versus 24%). The day of FET after the LH surge detected using a urine test was not significantly associated with live births.
The results of the current study suggested that the vitrified-warmed blastocyst transfer could be scheduled on day 5, 6 or 7 after a positive LH urine test without having a significant impact on the clinical outcome.
Purpose
The aim of the study was to compare the levels of angiogenic markers and markers of placentation between pregnancies conceived with fresh (ET) and vitrified-warmed blastocyst transfer (FET).
...Methods
Women with singleton pregnancies resulting from fresh ET or FET during the period between 2013 and 2017 were included in this prospective observational study. Fresh ET was performed in a stimulated and FET in natural cycle. At 6–7 weeks of gestation, after ultrasound confirmation of a single gestational sac with a viable embryo, serum levels of free β-hCG, pregnancy-associated plasma protein A (PAPP-A), placental growth factor (PIGF) and fms-like tyrosine kinase (sFlt-1) were measured. Data on the patients’ characteristics, pregnancy complications and outcomes were collected from a questionnaire and National Perinatal Information System of Slovenia.
Results
Among 211 pregnancies, 126 were achieved with fresh ET and 85 with FET. There were no significant differences in perinatal outcome, pregnancy complication and PIGF level between the fresh ET and FET group. Women achieving pregnancy with FET had significant higher levels of free β-hCG (40.20 ± 30.62 IU/L vs. 28.74 ± 23.52,
p
= 0.002), PAPP-A (0.09 ± 0.06 vs. 0.06 ± 0.05 IU/L,
p
= 0.004) and sFlt-1 (596.19 ± 283.06 vs. 436.53 ± 248.23 pg/L,
p
< 0.0001) compared to women having conceived with fresh ET. There were no significant differences in the levels of evaluated biomarkers between patients with different pregnancy outcomes and complications.
Conclusion
Levels of angiogenic markers and markers of placentation differ between pregnancies achieved with fresh ET and FET which may reflect altered implantation and early placentation with some forms of assisted reproductive technologies.
Our aim of the study was to evaluate the efficacy and complication rate of our inpatient medical management protocol for missed miscarriages. Three-hundred and ninety women hospitalised at our ...tertiary centre because of a missed miscarriage/anembryonic pregnancy in 2012-2013 were included in this retrospective study. The women underwent either a low (until 9 + 0 weeks of gestation) or high gestational age (from 9 + 1 until 15 + 6 weeks of gestation) management protocol. The success rate, curettage in the first 48 hours after the procedure, the complication rate and the factors that might influence these outcomes were evaluated. The overall success rate was 83.3%. The curettage in the first 48 hours after the procedure was performed in 7.4% of the patients and was more often in the high gestational age protocol. Complications that required another outpatient visit or hospitalisation occurred in 9% of the patients. Higher beta-hCG values 14 days after the procedure and the absence of evacuation of products of conception during hospitalisation were associated with a higher complication rate.
IMPACT STATEMENT
What is already known on this subject? As much as 10-20% of clinically recognised pregnancies end in a spontaneous abortion. A missed miscarriage and a blighted ovum represent a form of spontaneous abortion, which has long been treated with surgical evacuation. However, nowadays, medical management represents a well-established alternative with very high success rates and is considered as an equivalent and safe method that is also very well accepted by patients.
What do the results of this study add? According to our results, a medical management of a first trimester missed miscarriage and a blighted ovum is very effective with an overall success rate of 83.3% and a very low percentage of curettage in the first 48 hours after the procedure (7.4%). Our study was also able to identify higher beta-hCG values 14 days after procedure and absence of evacuation of products of conception during hospitalisation as risk factors for complication occurrence.
What are the implications of these findings for clinical practice and/or further research? Our study helps to identify patients who are at greater risk for developing complications after the medical management of a first trimester missed miscarriage.
BACKGROUND Ovarian hyperstimulation syndrome (OHSS) is a potentially serious complication of ovulation stimulation. Modest vulvar edema is frequently seen in a severe form of OHSS; however, cases of ...massive bilateral vulvar edema are rare and pathogenesis is uncertain. CASE REPORT We report a 31-year-old patient with massive vulvar edema and severe OHSS after IVF treatment with GnRH antagonist and gonadotropins. Five days after embryo transfer, she was hospitalized because of severe clinical manifestation of OHSS and on the fifth day after admission she developed a massive bilateral vulvar edema. After conventional medical therapy of OHSS, vulvar edema spontaneously resolved. CONCLUSIONS Hypoproteinemia with low oncotic pressure and certain personal tissue characteristics may play the main role in the pathogenesis of massive vulvar edema in OHSS.
•Publishing of the USOVA3D public database of annotated 3D ovarian ultrasound images.•Ovaries and follicles annotated by two gynaecologists.•Design of a verification protocol for unbiased assessment ...of detection algorithms.•Introduction of two advanced algorithms for follicle and ovary detection.•Inter-rater variability and baseline performance assessed on this database.
Background and objective: Automated follicle detection in ovarian ultrasound volumes remains a challenging task. An objective comparison of different follicle-detection approaches is only possible when all are tested on the same data. This paper describes the development and structure of the first publicly accessible USOVA3D database of annotated ultrasound volumes with ovarian follicles. Methods: The ovary and all follicles were annotated in each volume by two medical experts. The USOVA3D database is supplemented by a general verification protocol for unbiased assessment of detection algorithms that can be compared and ranked by scoring according to this protocol. This paper also introduces two baseline automated follicle-detection algorithms, the first based on Directional 3D Wavelet Transform (3D DWT) and the second based on Convolutional Neural Networks (CNN). Results: The USOVA3D testing data set was used to verify the variability and reliability of follicle annotations. The intra-rater overall score yielded around 83 (out of a maximum of 100), while both baseline algorithms pointed out just a slightly lower performance, with the 3D DWT-based algorithm being better, with an overall score around 78. Conclusions: On the other hand, the development of the CNN-based algorithm demonstrated that the USOVA3D database contains sufficient data for successful training without overfitting. The inter-rater reliability analysis and the obtained statistical metrics of effectiveness for both baseline algorithms confirmed that the USOVA3D database is a reliable source for developing new automated detection methods.