Tamar Amitai1, Yoav Kan-Tor1,2, Yuval Or3, Zeev Shoham3, Yoel Shofaro4, Dganit Richter5,6, Iris Har-Vardi5,6, Assaf Ben-Meir7,8, Naama Srebnik9,10, Amnon Buxboim11,12,13. 1. The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem, Edmond J. Safra Campus, Jerusalem, 9190416, Israel. 2. The Center for Interdisciplinary Data Science Research, The Hebrew University of Jerusalem, Edmond J. Safra Campus, Givat Ram, Jerusalem, 9190401, Israel. 3. Department of Obstetrics and Gynecology, Division of Reproductive Endocrinology and Infertility, Kaplan Hospital, Rehovot, Israel. 4. Infertility and IVF Unit, Rabin Medical Center, Helen Schneider Hospital for Women, , Beilinson Hospital, Petach Tikva, Israel. 5. The IVF Unit Gyn/Obs, Soroka University Medical Center, Beer-Sheva, Israel. 6. Faculty of Health Sciences, Ben-Gurion University of the Negev, Beer-Sheva, Israel. 7. Department of Obstetrics and Gynecology, Hadassah Medical Center, Hebrew University of Jerusalem, Jerusalem, Israel. 8. Infertility and IVF Unit, Hadassah Hebrew University Hospital, Jerusalem, Israel. 9. The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem, Edmond J. Safra Campus - Givat Ram, Jerusalem, 9190401, Israel. 10. In Vitro Fertilization Unit, Department of Obstetrics and Gynecology, Shaare Zedek Medical Center, Jerusalem, 9103102, Israel. 11. The Rachel and Selim Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem, Edmond J. Safra Campus, Jerusalem, 9190416, Israel. amnon.buxboim@mail.huji.ac.il. 12. The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem, Edmond J. Safra Campus - Givat Ram, Jerusalem, 9190401, Israel. amnon.buxboim@mail.huji.ac.il. 13. The Alexender Grass Center for Bioengineering, The Hebrew University of Jerusalem, Edmond J. Safra Campus, Givat Ram, Jerusalem, 9190401, Israel. amnon.buxboim@mail.huji.ac.il.
Abstract
PURPOSE: First trimester miscarriage is a major concern in IVF-ET treatments, accounting for one out of nine clinical pregnancies and for up to one out of three recognized pregnancies. To develop a machine learning classifier for predicting the risk of cleavage-stage embryos to undergo first trimester miscarriage based on time-lapse images of preimplantation development. METHODS: Retrospective study of a 4-year multi-center cohort of 391 women undergoing intra-cytoplasmatic sperm injection (ICSI) and fresh single or double embryo transfers. The study included embryos with positive indication of clinical implantation based on gestational sac visualization either with first trimester miscarriage or live-birth outcome. Miscarriage was determined based on negative fetal heartbeat indication during the first trimester. Data were recorded and obtained in hospital setting and research was performed in university setting. RESULTS: A minimal subset of six non-redundant morphodynamic features were screened that maintained high prediction capacity. Features that account for the distribution of the nucleolus precursor bodies within the small pronucleus and pronuclei dynamics were highly predictive of miscarriage outcome as evaluated using the SHapley Additive exPlanations (SHAP) methodology. Using this feature subset, XGBoost and random forest models were trained following a 100-fold Monte-Carlo cross validation scheme. Miscarriage was predicted with AUC 0.68 to 0.69. CONCLUSION: We report the development of a decision-support tool for identifying the embryos with high risk of miscarriage. Prioritizing embryos for transfer based on their predicted risk of miscarriage in combination with their predicted implantation potential is expected to improve live-birth rates and shorten time-to-pregnancy.
PURPOSE: First trimester miscarriage is a major concern in IVF-ET treatments, accounting for one out of nine clinical pregnancies and for up to one out of three recognized pregnancies. To develop a machine learning classifier for predicting the risk of cleavage-stage embryos to undergo first trimester miscarriage based on time-lapse images of preimplantation development. METHODS: Retrospective study of a 4-year multi-center cohort of 391 women undergoing intra-cytoplasmatic sperm injection (ICSI) and fresh single or double embryo transfers. The study included embryos with positive indication of clinical implantation based on gestational sac visualization either with first trimester miscarriage or live-birth outcome. Miscarriage was determined based on negative fetal heartbeat indication during the first trimester. Data were recorded and obtained in hospital setting and research was performed in university setting. RESULTS: A minimal subset of six non-redundant morphodynamic features were screened that maintained high prediction capacity. Features that account for the distribution of the nucleolus precursor bodies within the small pronucleus and pronuclei dynamics were highly predictive of miscarriage outcome as evaluated using the SHapley Additive exPlanations (SHAP) methodology. Using this feature subset, XGBoost and random forest models were trained following a 100-fold Monte-Carlo cross validation scheme. Miscarriage was predicted with AUC 0.68 to 0.69. CONCLUSION: We report the development of a decision-support tool for identifying the embryos with high risk of miscarriage. Prioritizing embryos for transfer based on their predicted risk of miscarriage in combination with their predicted implantation potential is expected to improve live-birth rates and shorten time-to-pregnancy.