Academic literature on the topic 'Embryo quality, IVF, Assisted Reproduction Techiniques, In Vitro Fertilization. ART'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Embryo quality, IVF, Assisted Reproduction Techiniques, In Vitro Fertilization. ART.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Embryo quality, IVF, Assisted Reproduction Techiniques, In Vitro Fertilization. ART"
1
Noli, Stefania Antonia, Elena Ricci, Sonia Cipriani, Stefania Ferrari, Marta Castiglioni, Irene La Vecchia, Edgardo Somigliana, and Fabio Parazzini. "Dietary Carbohydrate Intake, Dietary Glycemic Load and Outcomes of In Vitro Fertilization: Findings from an Observational Italian Cohort Study." Nutrients 12, no. 6 (May 28, 2020): 1568. http://dx.doi.org/10.3390/nu12061568.
Full textAbstract:
In recent decades, increasing attention has been paid to the influence of diet on reproductive health. Carbohydrates in diet affect glucose metabolism and multiple evidences showed the key role of insulin sensitivity in regulating female fertility. We designed a prospective cohort study to investigate the relation between dietary carbohydrate intake, glycemic load (GL) and the outcomes of assisted reproduction. A population of 494 female partners of couples referring to an Italian Fertility Center and eligible for in vitro fertilization (IVF) were enrolled in the study. On the day of the oocyte retrieval, information on their diet was obtained using a validated food frequency questionnaire (FFQ). We calculated the relative risk and 95% confidence interval of embryo transfer, clinical pregnancy and live birth according to the following dietary exposures: GL, glycemic index (GI) as well as the daily carbohydrate and fiber intake. A multiple regression model was used to account for the confounders. After adjusting for age, college degree, body mass index (BMI), leisure physical activity and previous assisted reproduction techniques (ART) cycles, no significant association was observed between the considered dietary exposures and the IVF outcomes. The roles of GL, carbohydrate intake and GI were assessed in strata of the cause of infertility and body mass index and no relation emerged in this further analysis. We found no clear association between the dietary carbohydrate quantity and quality and IVF outcomes in a cohort of infertile Italian women.
2
Srinivas, MS, Kamini Rao, Richa Sharma, and Theodre Jones. "Is Endometrial Thickness on the Day of ET Really Predictive of IVF Outcome?" International Journal of Infertility & Fetal Medicine 3, no. 2 (2012): 40–47. http://dx.doi.org/10.5005/jp-journals-10016-1039.
Full textAbstract:
ABSTRACT Background The effect of endometrial thickness on pregnancy rates in assisted reproductive technology (ART) patients has been evaluated by many authors, with controversial results. Endometrial thickness has been utilized as an indirect indicator for endometrial receptivity. Objective To evaluate relationship between endometrial thickness on day of embryo transfer and pregnancy outcome in in vitro fertilization and embryo transfer (IVF-ET) cycles. Should we cancel cycles based on endometrial thickness only? Material and methods A prospective analysis was conducted at Dr Kamini Rao Hospital, Bangaluru, of 239 patients. Various parameters were compared between pregnant and nonpregnant patients to see whether there is any cut-off for endometrial thickness on day of embryo transfer by which we can predict good prognosis in form of pregnancy and what effect other variables on endometrial thickness and pregnancy respectively and should we cancel embryo transfer, if endometrial thickness is not within certain range? Results In the study population, 174 (73%) had primary and 65 (27%) had secondary infertility, Ovarian stimulation was performed with long protocol in 37% cases, antagonist protocol in 47% and other protocols like microflare, short, ultralong, ultrashort in 15%. Mean age of patients was 31.04 ± 3.79 years. Among causes of infertility male factor was present in 39%, tubal factor was seen in 18%, unexplained were 13%, polycystic ovarian syndrome in 11%, poor ovarian reserve in 4.1% and mixed causes in 13%. Majority of our patients were in normal and overweight as per body mass index (BMI). ET were easy in 90% of cases and 14 (5.8%) ETs were cancelled. The reason for cancellation was ovarian hyperstimulation syndrome (OHSS) in 9 cases, fluid in cavity in 2 cases, one patient had hyperpyrexia on day of ET and 2 cases of failed fertilization. Endometrial thickness was >10 mm in 35% cases. Overall clinical pregnancy rate was 39% with implantation rate of 21%, fertilization rate of 92% and cleavage rate of 95% and live birth rate of 26%. There were more follicles, oocytes and embryos, the endometrium was >10 mm and embryo quality was higher among women who became pregnant when compared with nonpregnant women after assisted reproduction though not statistically significant (p > 0.05). The pregnancy rate improved as endometrial thickness increased showing a linear association. Conclusion Increased endometrial thickness is associated with higher pregnancy rates, but as such a cut off cannot be decided. In our study we have seen pregnancies at both thin and thick endometrium so we should not cancel ET merely on the basis of endometrial thickness as pregnancy is affected by multiple variables and not by endometrial thickness alone. How to cite this article Sharma R, Rao K, Srinivas MS, Jones T. Is Endometrial Thickness on the Day of ET Really Predictive of IVF Outcome? Int J Infertility Fetal Med 2012;3(2): 40-47.
3
Meng, Fanchao, Sheng Deng, Lu Wang, Yumei Zhou, Mengjie Zhao, Haibin Li, Dong Liu, Guojing Gao, Xiaoxing Liao, and Jisheng Wang. "Bibliometric analysis and visualization of literature on assisted reproduction technology." Frontiers in Medicine 9 (December 1, 2022). http://dx.doi.org/10.3389/fmed.2022.1063040.
Full textAbstract:
IntroductionAssisted reproductive technology (ART) is a method that uses various techniques to process sperm or ova. Assisted reproductive technology involves removing ova from a woman's ovaries, combining them with sperm in the laboratory, and returning them to the woman's body or donating them to another woman.MethodsBased on the web of science core collection database, we firstly analyzed the quantity and quality of publications in the field of ART, secondly profiled the publishing groups in terms of country, institution, author's publication and cooperation network, and finally sorted out and summarized the hot topics of research.ResultsIn total, 6,288 articles on ART were published between 2001 and 2022 in 1,013 journals. Most of these published articles represent the global research status, potential hotspots and future research directions. Publications and citations of research on assisted reproductive technology have steadily increased over the past few decades. Academic institutions in Europe and the United States have been leading in assisted reproductive technology research. The countries, institutions, journals, and authors with the most published articles were the United States (1864), Harvard Univ (108), Fertility and Sterility (819), and Stern, Judy E. (64). The most commonly used keywords are Assisted reproductive technology (3303) and in-vitro Fertilization (2139), Ivf (1140), Pregnancy (1140), Women (769), Intracytoplasmic Sperm injection (644), In Fertilization (632), Risk (545), and Outcome (423).ConclusionFrozen embryo transfer, intracytoplasmic sperm injection, and in vitro fertilization are the main research topics and hotspots in the field of assisted reproductive technology.
4
Kanaka, Vasiliki, Stavros Proikakis, Petros Drakakis, Dimitrios Loutradis, and George Th Tsangaris. "Implementing a preimplantation proteomic approach to advance assisted reproduction technologies in the framework of predictive, preventive, and personalized medicine." EPMA Journal, May 21, 2022. http://dx.doi.org/10.1007/s13167-022-00282-5.
Full textAbstract:
AbstractThe evolution of the field of assisted reproduction technology (ART) in the last 40 years has significantly contributed to the management of global infertility. Despite the great numbers of live births that have been achieved through ART, there is still potential for increasing the success rates. As a result, there is a need to create optimum conditions in order to increase ART efficacy. The selection of the best sperm, oocyte, and embryo, as well as the achievement of optimal endometrial receptivity, through the contribution of new diagnostic and treatment methods, based on a personalized proteomic approach, may assist in the attainment of this goal. Proteomics represent a powerful new technological development, which seeks for protein biomarkers in human tissues. These biomarkers may aid to predict the outcome, prevent failure, and monitor in a personalized manner in vitro fertilization (IVF) cycles. In this review, we will present data from studies that have been conducted in the search for such biomarkers in order to identify proteins related to good sperm, oocyte, and embryo quality, as well as optimal endometrial receptivity, which may later lead to greater results and the desirable ART outcome.
5
Khudhari, Adhwaa, Ali Mourad, Simon Phillips, Mohammad Zubair Alam, Robert Hemmings, and Wael Jamal. "Perinatal outcomes of human singletons conceived naturally versus assisted reproductive technologies: analysis of the effect of stimulated IVF, modified natural IVF, and frozen embryo transfer." Middle East Fertility Society Journal 26, no. 1 (March 6, 2021). http://dx.doi.org/10.1186/s43043-021-00051-w.
Full textAbstract:
Abstract Background Obstetrical outcomes in assisted reproduction techniques (ART) were compared with naturally conceived pregnancies and among each other in multiple reports. However, many important changes in the practice of in vitro fertilization (IVF) over the years, including single embryo transfers (sET) and the introduction of modified natural IVF (mnIVF), and the advances in the frozen embryo transfer (FET) might have impacted the outcomes. Our study is the first to our knowledge to assess four different groups, including spontaneous pregnancies, mnIVF, stimulated IVF (sIVF), and FET altogether in a head-to-head comparison. This is a retrospective study on perinatal outcomes of singleton babies conceived naturally or using three different ART protocols between 2011 and 2014. The primary objective was the comparison of gestational age and birth weight between spontaneously conceived pregnancies (NAT, n= 15,770), mnIVF (n=235), sIVF (n=389), and FET (n=222). Results Our results show a significant difference in favor of naturally conceived pregnancies over ART in term of gestational age. In fact, the gestational age of babies in the NAT group was statistically higher compared to each one of the ART groups alone. Regarding the birth weight, the mean was significantly higher in the FET group compared to the other categories. Conclusion Differences in perinatal outcomes are still found among babies born after different modes of conception. However, there is still need for well-designed high-quality trials assessing perinatal outcomes between naturally conceived pregnancies and different ART protocols based on different maternal and treatment characteristics.
6
Dolci, C., V. S. Vanni, E. Papaleo, L. Pagliardini, G. Cermisoni, N. Salmeri, A. Salonia, and M. Candiani. "P-031 The extent of late paternal effect: does the blastocyst matter? A retrospective analysis of 703 single, frozen-thawed embryo-transfers." Human Reproduction 37, Supplement_1 (June 29, 2022). http://dx.doi.org/10.1093/humrep/deac107.029.
Full textAbstract:
Abstract Study question Do the blastocysts derived from severe male infertility show different ongoing pregnancy rates(OPR) compared to blastocysts of couples requiring assisted reproduction techniques(ART) for other indications? Summary answer First, single, frozen-thawed embryo transfers of blastocysts derived from severe male infertility did not affect OPR in-vitro fertilization (IVF)/ intracytoplasmic sperm injection (ICSI) cycles. What is known already Several studies reported a negative impact of severe male infertility on fertilization rate, embryo morphology and embryo cleavage speed, due to the so-called early paternal effect, caused by sperm cytoplasm deficiencies. Nuclear sperm defects are responsible for the late paternal effect, causing lower blastocyst formation rates and, theoretically, reducing implantation potential of the obtained blastocysts. However, the effects of male infertility on OPR and live birth rates (LBR) are still debated. Additionally, the heterogeneity in the definition and estimation of male infertility makes the existing data difficult to interpret. Study design, size, duration Retrospective analysis of first IVF/ICSI cycles performed between January 2019 and December 2021 in the Reproductive Sciences Unit of Gynaecology/Obstetrics Department of San Raffaele Hospital in Milan, Italy. Participants/materials, setting, methods First, single, frozen-thawed embryo transfers of infertile couples first IVF/ICSI cycles were included. Embryo transfers obtained by frozen semen were excluded. Couples characteristics, semen parameters and controlled ovarian stimulation (COS) data were collected. Semen quality was assessed using total motile count (TMC) and grouped into quartiles of TMC for the analyses. The effect of severe male factor infertility evaluated through TMC over OPR was the primary outcome of the study. Main results and the role of chance N = 703 transfers were analysed. Performing a logistic regression analysis adjusted for confounding factors (maternal age, COS protocols, number of oocytes retrieved and quality of transferred blastocysts), OPR was not influenced by TMC values [odds ratio (OR) = 0.999; confidence interval (CI) = 0.986-1.013; p = 0.932]. After grouping male infertility population into quartiles of TMC, no significant differences in OPR were found between extreme quartiles (TMC ≤2.55 million and TMC ≥20 million respectively), even when adjusted for confounders [OR = 1.007; CI 0.609-1.663; p = 0.98]. Therefore, the implantation potential of the obtained blastocysts, once formed, seems to be independent from sperm quality. Limitations, reasons for caution The major limitations of the present study are the retrospective design and sample size. Additionally, the estimation of male infertility as well as the routinary use of TMC in clinical practice are not yet standardized. However, having analysed only the first transfers of the included couples makes our results reliable. Wider implications of the findings Further prospective studies with larger sample size are needed to confirm our results and to validate the use TMC as a standard tool to classify male factor and to guide clinical choices. Pregnancy and obstetrical outcomes are also necessary to better understand the role of male infertility in human reproduction. Trial registration number not applicable
7
Li, Yuehong, Xuefen Cai, Binhua Dong, Qi Wang, Xiaohui Yang, Aili Yu, Huijuan Wei, et al. "The Impact of Malignancy on Assisted Reproductive Outcomes for Cancer Survivors: A Retrospective Case–Control Study." Frontiers in Oncology 12 (September 16, 2022). http://dx.doi.org/10.3389/fonc.2022.941797.
Full textAbstract:
BackgroundRelated studies have shown that it is safe for cancer patients to undergo assisted reproduction. However, studies on whether a history of cancer affects long-term reproductive outcomes in women who undergo assisted reproductive technology (ART) are scarce. In this study, we evaluated the long-term reproductive outcomes of patients with malignant tumors undergoing ART treatment and explored the impact of malignancy history on ART outcomes.MethodsThis retrospective study analyzed the clinical outcomes of patients with malignant tumors undergoing their first in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) cycles compared with those of age-matched healthy infertile women at Fujian Maternity and Child Health Hospital between January 2003 and October 2020. We evaluated ovarian stimulation outcome, the pregnancy rate, the live birth rate, the risk of adverse obstetric outcomes and birth outcomes.ResultsThis study included 59 patients in the cancer group for data analysis who had a history of malignancy. By matching, a total of 118 healthy infertile women were included in the control group. No statistically significant association was found in terms of age, duration of infertility, BMI, or insemination type between the two groups of patients. Thyroid cancer(45.8%) and gynecologic malignancies (44.07%) were the major cancer types in this study. There were statistically significant differences in the antral follicle count (AFC) (12.00 ± 7.86 vs. 14.90 ± 8.71, P=0.033), length of ovarian stimulation (9.98 ± 2.68 vs. 11.42 ± 2.43, P=0.033) and endometrial thickness on the trigger day (10.16 ± 3.11 vs. 10.84 ± 2.17, P<0.001) between the two groups. The total gonadotropin dose, number of oocytes retrieved, fertilization rate, cleavage rate, high-quality embryo rate, blastocyst rate and first-time embryo-transfer (ET) implantation rate were nonsignificantly lower in the cancer group than in the control group (P>0.05). There were no significant differences in the clinical pregnancy rate per ET cycle (32% vs. 40.39%, P=0.156), live birth rate per ET cycle (27% vs. 35.96%, P=0.119), miscarriage rate per ET cycle (5% vs. 4.43%, P=0.779), or preterm delivery rate per ET cycle (11.11% vs. 17.80%, P=0.547) between the two groups. Additionally, regression analysis showed that a history of malignancy was not a risk factor for reproductive outcomes.ConclusionsOverall, it is feasible for women with a history of cancer to conceive using ART is feasible and their long-term reproductive outcomes are similar to these of healthy infertile women. A history of cancer does not decrease the number of retrieved oocytes, increase the risk of adverse obstetric outcomes or affect birth outcomes.
8
Rodriguez Díaz, R., R. Blanes-Zamora, J. Gomez-Rodriguez, L. Alcaide Ruggiero, A. Hardisson, D. Gonzalez-Weller, A. J. Gutierrez, S. Paz, C. Rubio, and E. Gonzalez-Davila. "P-020 Influence of vanadium and lead in seminal fluid on assisted reproductive techniques." Human Reproduction 37, Supplement_1 (June 29, 2022). http://dx.doi.org/10.1093/humrep/deac107.019.
Full textAbstract:
Abstract Study question In recent decades there has been an increase in environmental contaminants than can affect assisted reproduction techniques. We analyze the influence of vanadium (V) and lead (Pb) on these results. Summary answer Higher seminal fluid V levels affect fertilization rate (FR). Higher Pb and V levels decrease embryo cleavage rate (CR). What is known already Some animal studies have shown that V produces toxicity in the male reproductive system through oxidative stress, and this leads to decreases sperm count and motility, as well increased concentration of abnormal sperm. Pb is one of the main pollutants and, it accumulates in the male reproductive organs, deteriorates the quality of semen, increases the frequency of spontaneous abortion and male infertility. And it has also been seen that it inhibits sperm functions in vitro, although its mechanism of action is still unknown. Study design, size, duration A prospective study was conducted in 102 males, with a mean age of 38.0 ± 5.7, attended successively for initial evaluation, in the Human Reproduction Unit of the Hospital Universitario de Canarias, between february and april 2018, who underwent a semen analysis and metal detection and, subsequently, an IVF/ICSI treatment during years 2019 and 2020 (n = 92). The relationship between the presence of metals and the results of ART has been established. Participants/materials, setting, methods We included two groups based on semen parameters: 41 patients with pathological spermiograms (40.2%), while the remaining 61 (59.8%) had a normal semen analysis and constituted the control group.The study of seminal parameters was performed according to the WHO guidelines. The metals analysis was carried out in the Toxicology Area of the Universidad de La Laguna, using the digestion for microwave method. Metal measurement was performed using inductively coupled plasma optical emission spectrometry (ICP-OES). Main results and the role of chance In our study we have observed 79.4% of patients have V in semen. Significant differences have been found in the concentration of V in semen (t100=1.988, p = 0.05), is higher in patients who drink alcohol (0.51± 0.40 mg/Kg) than in abstinent patients (0.35± 0.30 mg/Kg). The group with FR above 75% presented lower V values compared to those with rates below 75% (p = 0.039). Within this last group, 33.3% present V values higher than 0.7 mg / kg compared to 15.8% who present it in the group with FR greater than 75% (OR = 2.67 CI95% 1.01, 7.52; p = 0.048). A statistical relationship was found between CR and Pb and V. Those who did not reach 100% CR presented higher Pb values (p = 0.052). Of them, 63.6% presented Pb compared to 38.5% in the group reaching 100% division. This same relationship was observed for V, with higher values in the group that did not reach 100% (p = 0.032), and V being present in 90.9% of the samples compared to 79.5% in the group reaching 100%. Limitations, reasons for caution The limitation of this study was the volume of semen that could be obtained for the metal detection, only 0.5 ml. This was because the semen sample was used at the same time to make a diagnosis of infertility though a spermiogram Wider implications of the findings The determination of metals in semen opens a new field in the study of infertility, and many cases of unknown infertility could due to metal presence or absence in seminal fluid, with the option of performing several treatments to correct these possible anomalies. Trial registration number not applicable
Dissertations / Theses on the topic "Embryo quality, IVF, Assisted Reproduction Techiniques, In Vitro Fertilization. ART"
1
Ghelardi, Camilla. "Non-invasive biomarkers of embryo quality: how they can contribute to the success of Assisted Reproduction Techniques." Doctoral thesis, Università di Siena, 2022. http://hdl.handle.net/11365/1211556.
Full textAbstract:
Since the beginning of human IVF, various grading systems based on numerous characteristics that can be observed in pre-implantation embryos have been evolved, with the aim of quantitating embryo development, viability and implantation potential. The advantages of static morphological assessment are the simplicity and the limited expenses related to the method; there are, however, several limitations as it doesn’t allow to evaluate events that occur during in vitro development which are fundamental for determining embryo quality.
The introduction of Time Lapse Microscopy in the field of Assisted Reproduction allowed the identification of parameters that may non-invasively predict the developmental potential of a cleavage-stage embryo through continuous monitoring; the capture of images of the embryos developing in vitro at regular intervals throughout the culture period, in fact, provides embryologists with a more sophisticated and promising tool for the study and selection of the human preimplantation embryo. However, to date, and despite significant research effort, no single reliable biomarker with a sufficiently high predictability of live birth has yet been identified. Consequently, the search for biomarkers must no longer occur in isolation and the combination of TLT with other markers of embryo physiology is a natural evolution of both fields.
In recent years, new methods have been developed involving the analysis of embryo physiology to determine viability. The use of metabolomic and proteomic platforms has yet to be proven and employed clinically, and hence such approaches could ultimately assist in defining parameters that can be used in embryo selection. An example of a non-invasive assessment of embryo quality can be represented by the analysis of EVs in the spent culture media; extracellular vesicles, in fact, can be nowadays studied as biomarkers for several reproductive conditions.
The proposal of this thesis was to evaluate how the morphokinetic assessment of embryo development can contribute to the success of Assisted Reproduction treatments. Data obtained through the record of cellular divisions parameters of embryos incubated in a time lapse system, were retrospectively analyzed according to different outcomes of IVF treatments in order to identify markers that can provide more information on embryonic quality and, consequently, can guide the embryologist in the selection of embryos with the greatest development and implantation potential in a non-invasive way.
At the same time, a preliminary analysis was started on the spent culture media of the embryos cultured in vitro with the aim of evaluating the presence and quantity of extracellular vesicles (EVs) that can be considered non-invasive biomarkers able to provide additional information on embryo quality.
Book chapters on the topic "Embryo quality, IVF, Assisted Reproduction Techiniques, In Vitro Fertilization. ART"
1
García-Ferreyra, Javier, and Alfonso Sánchez-Pavón. "Improving Embryo Quality by Strictly Controlling IVF Laboratory Environment." In Embryology Update [Working Title]. IntechOpen, 2022. http://dx.doi.org/10.5772/intechopen.106782.
Full textAbstract:
In recent years, several changes have been made in different aspects of in vitro fertilization to improve embryo quality and ultimately the clinical outcomes in assisted reproduction technology (ART). These approaches include improvements in air quality inside the lab to ensure VOCs-free air, use of tri-gas incubator and embryo-tested devices and plastics, adequate control of pH and osmolarity of culture media, and strict quality control that allows an adequate development of the embryos until blastocyst stage. Other strategies to improve the embryo quality during in vitro culture include volume reduction of drop culture media, and individual or group culture of embryos. This work summarizes several strategies to improve embryonic quality during their in vitro culture in assisted reproduction procedures.
2
Correa, Núria, Rita Vassena, Jesús Cerquides, and Josep Lluís Arcos. "Limits of Conventional Machine Learning Methods to Predict Pregnancy and Multiple Pregnancy After Embryo Transfer." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210141.
Full textAbstract:
When training models to learn the relationship between two or more variables, we expect to see previously demonstrated knowledge about that relationship reflected in the resulting estimators. For some domains, such as healthcare, it is imperative for actual implementation of those models that their predictions respect this knowledge. In this study we focus on Assisted Reproduction Technology (ART), the subspecialty of gynecology occupied with treating human infertility, and where the goal of any treatment is the delivery of a healthy newborn. A common ART treatment is In vitro Fertilization (IVF), where embryos are generated in vitro from collected sperm and oocytes, and transferred to the uterus of the patient after selecting those most likely to give rise to a healthy pregnancy. IVF has an approximate 30% successes rate per cycle; to palliate for this low success rate, a common practice so far has been to transfer two embryos simultaneously, aiming to increase the chances of a favorable outcome. While increasing overall live birth rates, this method has also led to an alarmingly high rate of twin and triplet births, associated with four times higher risk of perinatal mortality and increased obstetric complications. Our objective is to predict the chances of both pregnancy (P) and multiple pregnancy (MP) following either single embryo transfer (SET) or double embryo transfer (DET), and in so facilitating an informed decision on how many embryos to transfer. From existing literature, it is known that: (1) it is not possible for the chances of both P and MP to be decreased by increasing the number of embryos; (2) MP chances cannot be higher than P; and (3) chances of pregnancy are highly correlated with age, embryo stage, and quality. With a dataset generated from an existing observational study, we trained several state-of-the-art classifiers to predict P and MP given SET and DET. Analyzing the results, all classifiers achieved promising AUC scores. However, Random Forest and Gradient Boosting predicted negative chance differences in many instances when increasing the number of embryos infringing the first constraint. Logistic Regression predicted always positive differences, but in some instances it infringes the second constraint, predicting higher chances of MP than of P. Moreover, it showed little to no variation across ages or embryo stages violating third constraint. Conventional Machine Learning models struggle to reflect the real-world outcomes when using DET versus SET in specific patients. More informative variables could help, but it is already worrisome that variables as important as age and embryo stage do not result already in any variation, and that when models do show variation, in many cases they predicted decreasing chances of success with more embryos. We conclude that new and different approaches are needed to correctly model this scenario and, likely, many others resembling this one.
3
Correa, Núria, Rita Vassena, Jesús Cerquides, and Josep Lluís Arcos. "Limits of Conventional Machine Learning Methods to Predict Pregnancy and Multiple Pregnancy After Embryo Transfer." In Frontiers in Artificial Intelligence and Applications. IOS Press, 2021. http://dx.doi.org/10.3233/faia210141.
Full textAbstract:
When training models to learn the relationship between two or more variables, we expect to see previously demonstrated knowledge about that relationship reflected in the resulting estimators. For some domains, such as healthcare, it is imperative for actual implementation of those models that their predictions respect this knowledge. In this study we focus on Assisted Reproduction Technology (ART), the subspecialty of gynecology occupied with treating human infertility, and where the goal of any treatment is the delivery of a healthy newborn. A common ART treatment is In vitro Fertilization (IVF), where embryos are generated in vitro from collected sperm and oocytes, and transferred to the uterus of the patient after selecting those most likely to give rise to a healthy pregnancy. IVF has an approximate 30% successes rate per cycle; to palliate for this low success rate, a common practice so far has been to transfer two embryos simultaneously, aiming to increase the chances of a favorable outcome. While increasing overall live birth rates, this method has also led to an alarmingly high rate of twin and triplet births, associated with four times higher risk of perinatal mortality and increased obstetric complications. Our objective is to predict the chances of both pregnancy (P) and multiple pregnancy (MP) following either single embryo transfer (SET) or double embryo transfer (DET), and in so facilitating an informed decision on how many embryos to transfer. From existing literature, it is known that: (1) it is not possible for the chances of both P and MP to be decreased by increasing the number of embryos; (2) MP chances cannot be higher than P; and (3) chances of pregnancy are highly correlated with age, embryo stage, and quality. With a dataset generated from an existing observational study, we trained several state-of-the-art classifiers to predict P and MP given SET and DET. Analyzing the results, all classifiers achieved promising AUC scores. However, Random Forest and Gradient Boosting predicted negative chance differences in many instances when increasing the number of embryos infringing the first constraint. Logistic Regression predicted always positive differences, but in some instances it infringes the second constraint, predicting higher chances of MP than of P. Moreover, it showed little to no variation across ages or embryo stages violating third constraint. Conventional Machine Learning models struggle to reflect the real-world outcomes when using DET versus SET in specific patients. More informative variables could help, but it is already worrisome that variables as important as age and embryo stage do not result already in any variation, and that when models do show variation, in many cases they predicted decreasing chances of success with more embryos. We conclude that new and different approaches are needed to correctly model this scenario and, likely, many others resembling this one.