Purpose
To study the effectiveness of federated learning in in vitro fertilization on embryo evaluation tasks.

Methods
This is a retrospective cohort analysis. Two datasets were used in this study. The ploidy status dataset consisted of 10,065 embryo records, 3760 treatments, and 2479 infertile couples from 5 hospitals. The clinical pregnancy dataset consisted of 4495 embryo records, 4495 treatments, and 3704 infertile couples from 4 hospitals. Federated learning and the gradient boosting decision tree algorithm were utilized for modeling.

Results
On the ploidy status dataset, the areas under the receiver operating characteristic curves of our model trained with federated learning were 71.78%, 73.10%, 69.39%, 69.72%, and 73.46% for 5 hospitals respectively, showing an average increase of 2.5% compared to those of our model trained without federated learning. On the clinical pregnancy dataset, the areas under the receiver operating characteristic curves of our model trained with federated learning were 72.03%, 56.77%, 61.63%, and 58.58% for 4 hospitals respectively, showing an average increase of 3.08%.

Conclusions
Federated learning can improve data privacy and data security and meanwhile improve the performance of embryo selection tasks by leveraging data from multiple sources. This study demonstrates the effectiveness of federated learning in embryo evaluation, and the results show the promise for future application. 

Authors
Chun‐I Lee · Chii‐Ruey Tzeng · Monty Li· Hsing‐Hua Lai · Chi‐Huang Chen · Yulun Huang· T. Arthur Chang · Chien‐Hong Chen · Chun‐Chia Huang · Maw‐Sheng Lee · Mark Liu 

More Information
J Assist Reprod Genet . 2024 Jul;41(7):1811-1820.
https://link.springer.com/article/10.1007/s10815-024-03148-z