Dataset Information

Deep phenotyping to predict live birth outcomes in in vitro fertilization.

ABSTRACT: Nearly 75% of in vitro fertilization (IVF) treatments do not result in live births and patients are largely guided by a generalized age-based prognostic stratification. We sought to provide personalized and validated prognosis by using available clinical and embryo data from prior, failed treatments to predict live birth probabilities in the subsequent treatment. We generated a boosted tree model, IVFBT, by training it with IVF outcomes data from 1,676 first cycles (C1s) from 2003-2006, followed by external validation with 634 cycles from 2007-2008, respectively. We tested whether this model could predict the probability of having a live birth in the subsequent treatment (C2). By using nondeterministic methods to identify prognostic factors and their relative nonredundant contribution, we generated a prediction model, IVF(BT), that was superior to the age-based control by providing over 1,000-fold improvement to fit new data (p<0.05), and increased discrimination by receiver-operative characteristic analysis (area-under-the-curve, 0.80 vs. 0.68 for C1, 0.68 vs. 0.58 for C2). IVFBT provided predictions that were more accurate for approximately 83% of C1 and approximately 60% of C2 cycles that were out of the range predicted by age. Over half of those patients were reclassified to have higher live birth probabilities. We showed that data from a prior cycle could be used effectively to provide personalized and validated live birth probabilities in a subsequent cycle. Our approach may be replicated and further validated in other IVF clinics.

SUBMITTER: Banerjee P

PROVIDER: S-EPMC2922227 | biostudies-literature | 2010 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep phenotyping to predict live birth outcomes in in vitro fertilization.

Banerjee Prajna P Choi Bokyung B Shahine Lora K LK Jun Sunny H SH O'Leary Kathleen K Lathi Ruth B RB Westphal Lynn M LM Wong Wing H WH Yao Mylene W M MW

Proceedings of the National Academy of Sciences of the United States of America 20100719 31

Nearly 75% of in vitro fertilization (IVF) treatments do not result in live births and patients are largely guided by a generalized age-based prognostic stratification. We sought to provide personalized and validated prognosis by using available clinical and embryo data from prior, failed treatments to predict live birth probabilities in the subsequent treatment. We generated a boosted tree model, IVFBT, by training it with IVF outcomes data from 1,676 first cycles (C1s) from 2003-2006, followed ...[more]

PMID: 20643955

Similar Datasets

Project description:The likelihood of achieving a live birth with repeat in vitro fertilization (IVF) is unclear, yet treatment is commonly limited to 3 or 4 embryo transfers.To determine the live-birth rate per initiated ovarian stimulation IVF cycle and with repeated cycles.Prospective study of 156,947 UK women who received 257,398 IVF ovarian stimulation cycles between 2003 and 2010 and were followed up until June 2012.In vitro fertilization, with a cycle defined as an episode of ovarian stimulation and all subsequent separate fresh and frozen embryo transfers.Live-birth rate per IVF cycle and the cumulative live-birth rates across all cycles in all women and by age and treatment type. Optimal, prognosis-adjusted, and conservative cumulative live-birth rates were estimated, reflecting 0%, 30%, and 100%, respectively, of women who discontinued due to poor prognosis and having a live-birth rate of 0 had they continued.Among the 156,947 women, the median age at start of treatment was 35 years (interquartile range, 32-38; range, 18-55), and the median duration of infertility for all 257,398 cycles was 4 years (interquartile range, 2-6; range, <1-29). In all women, the live-birth rate for the first cycle was 29.5% (95% CI, 29.3%-29.7%). This remained above 20% up to and including the fourth cycle. The cumulative prognosis-adjusted live-birth rate across all cycles continued to increase up to the ninth cycle, with 65.3% (95% CI, 64.8%-65.8%) of women achieving a live birth by the sixth cycle. In women younger than 40 years using their own oocytes, the live-birth rate for the first cycle was 32.3% (95% CI, 32.0%-32.5%) and remained above 20% up to and including the fourth cycle. Six cycles achieved a cumulative prognosis-adjusted live-birth rate of 68.4% (95% CI, 67.8%-68.9%). For women aged 40 to 42 years, the live-birth rate for the first cycle was 12.3% (95% CI, 11.8%-12.8%), with 6 cycles achieving a cumulative prognosis-adjusted live-birth rate of 31.5% (95% CI, 29.7%-33.3%). For women older than 42 years, all rates within each cycle were less than 4%. No age differential was observed among women using donor oocytes. Rates were lower for women with untreated male partner-related infertility compared with those with any other cause, but treatment with either intracytoplasmic sperm injection or sperm donation removed this difference.Among women in the United Kingdom undergoing IVF, the cumulative prognosis-adjusted live-birth rate after 6 cycles was 65.3%, with variations by age and treatment type. These findings support the efficacy of extending the number of IVF cycles beyond 3 or 4.

Project description:In-vitro fertilization (IVF) is a popular method of resolving complications such as endometriosis, poor egg quality, a genetic disease of mother or father, problems with ovulation, antibody problems that harm sperm or eggs, the inability of sperm to penetrate or survive in the cervical mucus and low sperm counts, resulting human infertility. Nevertheless, IVF does not guarantee success in the fertilization. Choosing IVF is burdensome for the reason of high cost and uncertainty in the result. As the complications and fertilization factors are numerous in the IVF process, it is a cumbersome task for fertility doctors to give an accurate prediction of a successful birth. Artificial Intelligence (AI) has been employed in this study for predicting the live-birth occurrence. This work mainly focuses on making predictions of live-birth occurrence when an embryo forms from a couple and not a donor. Here, we compare various AI algorithms, including both classical Machine Learning, deep learning architecture, and an ensemble of algorithms on the publicly available dataset provided by Human Fertilisation and Embryology Authority (HFEA). Insights on data and metrics such as confusion matrices, F1-score, precision, recall, receiver operating characteristic (ROC) curves are demonstrated in the subsequent sections. The training process has two settings Without feature selection and With feature selection to train classifier models. Machine Learning, Deep learning, ensemble models classification paradigms have been trained in both settings. The Random Forest model achieves the highest F1-score of 76.49% in without feature selection setting. For the same model, the precision, recall, and area under the ROC Curve (ROC AUC) scores are 77%, 76%, and 84.60%, respectively. The success of the pregnancy depends on both male and female traits and living conditions. This study predicts a successful pregnancy through the clinically relevant parameters in In-vitro fertilization. Thus artificial intelligence plays a promising role in decision making process to support the diagnosis, prognosis, treatment etc.

Dataset Information

Deep phenotyping to predict live birth outcomes in in vitro fertilization.

Publications

Deep phenotyping to predict live birth outcomes in in vitro fertilization.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets