Experience in machine learning application to predict pregnancy loss after assisted reproductive technologies
07.11.2024
14:52
Russian scientists conducted a study aimed to predict miscarriage in patients who undergo infertility treatment using ART methods based on clinical, anamnestic and embryological parameters, using the decision tree algorithm combined with linear regression.
Research in this area, especially using mashine learning tools for data processing makes it possible to build a software product for personalized and integrated prediction of live births for each married couple. The obtained results can optimize the state’s financial and economic expenditures to conduct ART cycles at the expense of Compulsory Health Insurance for different groups of patients. In addition, a clear and unified algorithm facilitates the targeted impact on the most probable cause of miscarriage, taking into account optimization of preparation time and achievement of maximum effect to reduce the rate of pregnancy loss after ART.
