ABSTRACT
BACKGROUND: Preimplantation genetic testing for aneuploidy has been proven to be effective in determining the embryo's chromosomal or ploidy status. The test requires a biopsy of embryonic cells on day 3, 5, or 6 from which complete information on the chromosomes would be obtained. The main drawbacks of preimplantation genetic testing for aneuploidy include its relatively invasive approach and the lack of research studies on the long-term effects of preimplantation genetic testing for aneuploidy. OBJECTIVE: Computer-assisted predictive modeling through machine learning and deep learning algorithms has been proposed to minimize the use of invasive preimplantation genetic testing for aneuploidy. The capability to predict morphologic characteristics of embryo ploidy status creates a meaningful support system for decision-making before further treatment. STUDY DESIGN: Image processing is a component in developing a predictive model specialized in image classification through which a model is able to differentiate images based on unique features. Image processing is obtained through image augmentation to capture segmented embryos and perform feature extraction. Furthermore, multiple machine learning and deep learning algorithms were used to create prediction-based modeling, and all of the prediction models undergo similar model performance assessments to determine the best model prediction algorithm. RESULTS: An efficient artificial intelligence model that can predict embryo ploidy status was developed using image processing through a histogram of oriented gradient and then followed by principal component analysis. The gradient boosting algorithm showed an advantage against other algorithms and yielded an accuracy of 0.74, an aneuploid precision of 0.83, and an aneuploid predictive value (recall) of 0.84. CONCLUSION: This research study proved that machine-assisted technology perceives the embryo differently than human observation and determined that further research on in vitro fertilization is needed. The study finding serves as a basis for developing a better computer-assisted prediction model.
ABSTRACT
Background: Kisspeptin plays a role in the oestradiol negative-feedback regulation of GnRH as well as gonadotropin. In addition, kisspeptin has been postulated to induce the production of an important cytokine called leukaemia inhibitory factor (LIF). Aims: This study aims to investigate the correlation between varying oestradiol levels measured on trigger day of the ovarian stimulation and the mRNA expression level of endometrial kisspeptin and LIF. Study Setting and Design: Prospective cross-sectional study took place in Morula IVF Jakarta clinic. Materials and Methods: A total of 43 infertile couples underwent an in-vitro fertilization (IVF) program. Subjects were grouped based on oestradiol levels as follows: group A ([⧠3000 pg/mL, n = 15], group B [2000-2999 pg/mL, n = 14], group C [<2000 pg/mL, n = 14]). Statistical Analysis Used: ANOVA test was utilised to compare the expression of kisspeptin and LIF among study groups while Pearson correlation was used to identify the correlation between variables. Results: A significantly higher mRNA expression of both Kisspeptin and LIF was found in group A than in groups B and C (P < 0.001). The mRNA expression of kisspeptin and LIF correlated positively with the oestradiol level (r = 0.638, P < 0.001 and r = 0.634, P < 0.001, respectively). Moreover, a strong association between Kisspeptin and LIF expression was also detected (r = 0.700, P < 0.001). Conclusions: mRNA expression of kisspeptin and LIF was significantly different according to the oestradiol levels in the study groups. Increased oestradiol level was shown to elevate the expression of endometrial kisspeptin and LIF in women undergoing the IVF programme.
