PriMera Scientific Engineering (ISSN: 2834-2550)

Research Article

Volume 4 Issue 2

Rethinking Challenges of Machine Learning in Assisted Reproductive Technology

Chenwei Wu*

January 22, 2024


Predicting pregnancy and live births using machine learning in the field of in-vitro fertilization (IVF) has long posed a significant challenge due to the difficulty in achieving consistent performance across various studies. In this paper, we conduct a comprehensive review and analysis of the existing limitations in current research. Additionally, we introduce a standardized machine learning pipeline, which serves as a valuable guide for future researchers. Furthermore, we propose two alternative modeling approaches: phase-by-phase modeling and subgroup FMLR modeling. These two alternatives not only enhance prediction performance but also offer clinically sensible explanations and timely guidance for users. Most notably, they shed light on the complexities of the IVF cycle, highlighting when, who, and where machine learning tasks face their greatest challenges. This insight can inspire future efforts in data collection and patient engagement processes.

Keywords: In-vitro fertilization; Machine Learning; Explainable AI; Medical AI


  1. Templeton Allan, Joan K Morris and William Parslow. "Factors that affect outcome of in-vitro fertilisation treatment". The Lancet 348.9039 (1996): 1402-1406.
  2. Minaretzis Demetrios., et al. "Multivariate analysis of factors predictive of successful live births in in vitro fertilization (IVF) suggests strategies to improve IVF outcome". Journal of assisted reproduction and genetics 15 (1998): 365-371.
  3. Hunault Claudine C., et al. "A prediction model for selecting patients undergoing in vitro fertilization for elective single embryo transfer". Fertility and sterility 77.4 (2002): 725-732.
  4. Nelson Scott M and Debbie A Lawlor. "Predicting live birth, preterm delivery, and low birth weight in infants born from in vitro fertilisation: a prospective study of 144,018 treatment cycles". PLoS medicine 8.1 (2011): e1000386.
  5. Van Loendersloot LL., et al. "Individualized decision-making in IVF: calculating the chances of pregnancy". Human Reproduction 28.11 (2013): 2972-2980.
  6. Qiu Jiahui., et al. "Personalized prediction of live birth prior to the first in vitro fertilization treatment: a machine learning method". Journal of translational medicine 17.1 (2019): 317.
  7. McLernon David J., et al. "Predicting the chances of a live birth after one or more complete cycles of in vitro fertilisation: population based study of linked cycle data from 113 873 women". BMJ 355 (2016).
  8. Meijerink AM., et al. "Prediction model for live birth in ICSI using testicular extracted sperm". Human Reproduction 31.9 (2016): 1942-1951.
  9. Metello José Luis, Claudia Tomás and Pedro Ferreira. "Can we predict the IVF/ICSI live birth rate?". JBRA Assisted Reproduction 23.4 (2019): 402-407.
  10. Raef Behnaz, Masoud Maleki and Reza Ferdousi. "Computational prediction of implantation outcome after embryo transfer". Health Informatics Journal 26.3 (2020): 1810-1826.
  11. Goyal Ashish, Maheshwar Kuchana and Kameswari Prasada Rao Ayyagari. "Machine learning predicts live-birth occurrence before in-vitro fertilization treatment". Scientific reports 10.1 (2020): 20925.
  12. Kaptein Maurits and Paul Ketelaar. "Maximum likelihood estimation of a finite mixture of logistic regression models in a continuous data stream". arXiv preprint arXiv:1802.10529 (2018).
  13. Li Gen. "Application of finite mixture of logistic regression for heterogeneous merging behavior analysis". Journal of Advanced Transportation (2018): 1-9.