Dataset Information

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction.

ABSTRACT: This study investigated whether combining metabolomic and embryologic data with machine learning (ML) models improve the prediction of embryo implantation potential. In this prospective cohort study, infertile couples (n=56) undergoing day-5 single blastocyst transfer between February 2019 and August 2021 were included. After day-5 single blastocyst transfer, spent culture medium (SCM) was subjected to metabolite analysis using nuclear magnetic resonance (NMR) spectroscopy. Derived metabolite levels and embryologic parameters between successfully implanted and failed groups were incorporated into ML models to explore their predictive potential regarding embryo implantation. The SCM of blastocysts that resulted in successful embryo implantation had significantly lower pyruvate (p<0.05) and threonine (p<0.05) levels compared to medium control but not compared to SCM related to embryos that failed to implant. Notably, the prediction accuracy increased when classical ML algorithms were combined with metabolomic and embryologic data. Specifically, the custom artificial neural network (ANN) model with regularized parameters for metabolomic data provided 100% accuracy, indicating the efficiency in predicting implantation potential. Hence, combining ML models (specifically, custom ANN) with metabolomic and embryologic data improves the prediction of embryo implantation potential. The approach could potentially be used to derive clinical benefits for patients in real-time.

SUBMITTER: Cheredath A

PROVIDER: S-EPMC10014658 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction.

Cheredath Aswathi A Uppangala Shubhashree S C S Asha A Jijo Ameya A R Vani Lakshmi VL Kumar Pratap P Joseph David D G A Nagana Gowda NG Kalthur Guruprasad G Adiga Satish Kumar SK

Reproductive sciences (Thousand Oaks, Calif.) 20220912 3

This study investigated whether combining metabolomic and embryologic data with machine learning (ML) models improve the prediction of embryo implantation potential. In this prospective cohort study, infertile couples (n=56) undergoing day-5 single blastocyst transfer between February 2019 and August 2021 were included. After day-5 single blastocyst transfer, spent culture medium (SCM) was subjected to metabolite analysis using nuclear magnetic resonance (NMR) spectroscopy. Derived metabolite le ...[more]

PMID: 36097248

Similar Datasets

Project description:BackgroundIn assisted reproduction technology embryo competence is routinely evaluated on morphological criteria but efficacy remains relatively low. Additional information could be obtained by evaluating pronuclear (PN) morphology. Up to now controversial results have been reported about the prognostic value of PN score. One of the main limitations of literature data is the use of different PN classification methods. In this regard, in 2011 the ESHRE and Alpha Scientists in Reproductive Medicine defined three PN categories to standardize zygote assessment. In this study we evaluated whether the consensus ESHRE-Alpha system for the pronuclear scoring could be an useful additional criterion to improve prediction of embryo implantation potential.MethodsThis is a retrospective, longitudinal, observational, cohort study. We included 3004 zygotes from 555 women who underwent ICSI treatment at our Center between January 2014 and June 2019. The PN were categorized as score 1: symmetrical, 2: non-symmetrical, 3: abnormal. A subset of 110 zygotes did not cleaved. On day 2-3 1163 embryos were transferred, 232 arrested, and 9 were cryopreserved. Among the 1490 embryos cultured up to day 5-7, 516 became blastocysts: 123 were transferred on day 5 and 393 were cryopreserved. Comparisons of age, cleavage and blastocyst rate, quality of embryos, implantation success among PN score groups were evaluated by chi-square test or Kruskal-Wallis test as appropriate. Potential predictors of embryo implantation were first tested in univariable analysis using generalized estimating equations taking into account correlation between embryos originated from the same patient. Then, variables potentially associated with implantation success (P<0.05) were included in a multivariable analysis for calculating the adjusted odds ratio (OR) and 95% confidence interval (CI).ResultsThere was no significant difference in patients'age, cleavage and blastulation rates, and embryo morphology among the three PNscore groups. The PN score 1-embryos had a greater implantation success respect to score 2-3-ones (OR 1.83; 95% CI 1.34-2.50, P=0.0001). Consistently, the pronuclear score remained predictive of implantation in top quality embryos (OR 1.68; 95%CI 1.17-2.42, P= 0.005).ConclusionsThe consensus pronuclear score may be routinely included among criteria for embryo evaluation to increase patients' chance of becoming pregnant.

Project description:BackgroundSpatiotemporal dengue forecasting using machine learning (ML) can contribute to the development of prevention and control strategies for impending dengue outbreaks. However, training data for dengue incidence may be inflated with frequent zero values because of the rarity of cases, which lowers the prediction accuracy. This study aimed to understand the influence of spatiotemporal resolutions of data on the accuracy of dengue incidence prediction using ML models, to understand how the influence of spatiotemporal resolution differs between quantitative and qualitative predictions of dengue incidence, and to improve the accuracy of dengue incidence prediction with zero-inflated data.MethodologyWe predicted dengue incidence at six spatiotemporal resolutions and compared their prediction accuracy. Six ML algorithms were compared: generalized additive models, random forests, conditional inference forest, artificial neural networks, support vector machines and regression, and extreme gradient boosting. Data from 2009 to 2012 were used for training, and data from 2013 were used for model validation with quantitative and qualitative dengue variables. To address the inaccuracy in the quantitative prediction of dengue incidence due to zero-inflated data at fine spatiotemporal scales, we developed a hybrid approach in which the second-stage quantitative prediction is performed only when/where the first-stage qualitative model predicts the occurrence of dengue cases.Principal findingsAt higher resolutions, the dengue incidence data were zero-inflated, which was insufficient for quantitative pattern extraction of relationships between dengue incidence and environmental variables by ML. Qualitative models, used as binary variables, eased the effect of data distribution. Our novel hybrid approach of combining qualitative and quantitative predictions demonstrated high potential for predicting zero-inflated or rare phenomena, such as dengue.SignificanceOur research contributes valuable insights to the field of spatiotemporal dengue prediction and provides an alternative solution to enhance prediction accuracy in zero-inflated data where hurdle or zero-inflated models cannot be applied.

Dataset Information

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction.

Publications

Combining Machine Learning with Metabolomic and Embryologic Data Improves Embryo Implantation Prediction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets