Development and evaluation of a live birth prediction model for evaluating human blastocysts: a retrospective study
Abstract
Background: In infertility treatment, blastocyst morphological grading is commonly used in clinical practice for blastocyst evaluation and selection, but has shown limited predictive power on live birth outcomes of blastocysts. To improve live birth prediction, a number of artificial intelligence (AI) models have been established. Most existing AI models for blastocyst evaluation only used images for live birth prediction, and the area under the receiver operating characteristic (ROC) curve (AUC) achieved by these models has plateaued at ~0.65.
Methods: This study proposed a multi-modal blastocyst evaluation method using both blastocyst images and patient couple's clinical features (e.g., maternal age, hormone profiles, endometrium thickness, and semen quality) to predict live birth outcomes of human blastocysts. To utilize the multi-modal data, we developed a new AI model consisting of a convolutional neural network (CNN) to process blastocyst images and a multi-layer perceptron to process patient couple's clinical features. The dataset used in this study consists of 17,580 blastocysts with known live birth outcomes, blastocyst images, and patient couple's clinical features.
Results: This study achieved an AUC of 0.77 for live birth prediction, which significantly outperforms related works in the literature. Sixteen out of 103 clinical features were identified to be predictors of live birth outcomes and helped improve live birth prediction. Among these features, maternal age, the day of blastocyst transfer, antral follicle count, retrieved oocyte number, and endometrium thickness measured before transfer are the top five features contributing to live birth prediction. Heatmaps showed that the CNN in the AI model mainly focuses on image regions of inner cell mass and trophectoderm (TE) for live birth prediction, and the contribution of TE-related features was greater in the CNN trained with the inclusion of patient couple's clinical features compared with the CNN trained with blastocyst images alone.
Conclusions: The results suggest that the inclusion of patient couple's clinical features along with blastocyst images increases live birth prediction accuracy.
Funding: Natural Sciences and Engineering Research Council of Canada and the Canada Research Chairs Program.
Data availability
All processed data and code needed to reproduce the findings of the study are made openly available in deidentified form. This can be found in https://github.com/robotVisionHang/LiveBirthPrediction_Data_Code, and attached to this manuscript. All codes and software used to analyze the data can also be accessed through the link. Due to data privacy regulations of patient data, raw data cannot be publicly shared. Interested researchers are welcome to contact the corresponding author with a concise project proposal indicating aims of using the data and how they will use the data. The project proposal will be firstly assessed by Prof. Yu Sun, Prof. Ge Lin, and then by the Ethics Committee of the Reproductive and Genetic Hospital of CITIC-Xiangya. There are no restrictions on who can access the data.
Article and author information
Author details
Funding
Natural Sciences and Engineering Research Council of Canada
- Yu Sun
Canada Research Chairs
- Yu Sun
The funders had no role in study design, data collection and interpretation, or the decision to submit the work for publication.
Reviewing Editor
- Larisa V. Suturina, Scientific Center for Family Health and Human Reproduction, Russian Federation
Ethics
Human subjects: Informed consent was not necessary because this study used retrospective and fully de-identified data, no medical intervention was performed on the subject, and no biological samples from the patient were collected. This study was approved by the Ethics Committee of the Reproductive and Genetic Hospital of CITIC-Xiangya (approval number: LL-SC-2021-008).
Version history
- Received: September 23, 2022
- Preprint posted: October 21, 2022 (view preprint)
- Accepted: February 20, 2023
- Accepted Manuscript published: February 22, 2023 (version 1)
- Version of Record published: April 3, 2023 (version 2)
Copyright
© 2023, Liu et al.
This article is distributed under the terms of the Creative Commons Attribution License permitting unrestricted use and redistribution provided that the original author and source are credited.
Metrics
-
- 1,377
- views
-
- 227
- downloads
-
- 3
- citations
Views, downloads and citations are aggregated across all versions of this paper published by eLife.
Download links
Downloads (link to download the article as PDF)
Open citations (links to open the citations from this article in various online reference manager services)
Cite this article (links to download the citations from this article in formats compatible with various reference manager tools)
Further reading
-
- Computational and Systems Biology
The reconstruction of complete microbial metabolic pathways using ‘omics data from environmental samples remains challenging. Computational pipelines for pathway reconstruction that utilize machine learning methods to predict the presence or absence of KEGG modules in incomplete genomes are lacking. Here, we present MetaPathPredict, a software tool that incorporates machine learning models to predict the presence of complete KEGG modules within bacterial genomic datasets. Using gene annotation data and information from the KEGG module database, MetaPathPredict employs deep learning models to predict the presence of KEGG modules in a genome. MetaPathPredict can be used as a command line tool or as a Python module, and both options are designed to be run locally or on a compute cluster. Benchmarks show that MetaPathPredict makes robust predictions of KEGG module presence within highly incomplete genomes.
-
- Computational and Systems Biology
- Evolutionary Biology
As the genome encodes the information crucial for cell growth, a sizeable genomic deficiency often causes a significant decrease in growth fitness. Whether and how the decreased growth fitness caused by genome reduction could be compensated by evolution was investigated here. Experimental evolution with an Escherichia coli strain carrying a reduced genome was conducted in multiple lineages for approximately 1000 generations. The growth rate, which largely declined due to genome reduction, was considerably recovered, associated with the improved carrying capacity. Genome mutations accumulated during evolution were significantly varied across the evolutionary lineages and were randomly localized on the reduced genome. Transcriptome reorganization showed a common evolutionary direction and conserved the chromosomal periodicity, regardless of highly diversified gene categories, regulons, and pathways enriched in the differentially expressed genes. Genome mutations and transcriptome reorganization caused by evolution, which were found to be dissimilar to those caused by genome reduction, must have followed divergent mechanisms in individual evolutionary lineages. Gene network reconstruction successfully identified three gene modules functionally differentiated, which were responsible for the evolutionary changes of the reduced genome in growth fitness, genome mutation, and gene expression, respectively. The diversity in evolutionary approaches improved the growth fitness associated with the homeostatic transcriptome architecture as if the evolutionary compensation for genome reduction was like all roads leading to Rome.