2023 / 06

Next Paper
DOI: 10.24075/brsmu.2023.057

ORIGINAL RESEARCH

Predicting the outcomes of in vitro fertilization programs using a random forest machine learning model

Vladimirsky GM1, Zhuravleva MA1, Dashieva AE2, Korneeva IE2, Nazarenko TA2
About authors

1 Higher School of Economics National Research University, Moscow, Russia

2 Kulakov National Medical Scientific Centre for Obstetrics, Gynecology and Perinatal Medicine, Moscow, Russia

Correspondence should be addressed: Ayuna E. Dashieva
Akademika Oparina, 4B, Moscow, 117198, Russia, ur.liam@aveihsad.rd

About paper

Author contribution: Vladimirsky GM — predictive models training, literature analysis, choice of research methods; Zhuravleva MA — preprocessing and analysis of data, literature analysis, manuscript authoring; Dashieva AE — processing of source material, analysis of results; Korneeva IE, Nazarenko TA — development of the survey for the database, manuscript editing.

Received: 2023-11-24 Accepted: 2023-12-19 Published online: 2023-12-31
|
Fig. 1. Geographical scope of the study
Fig. 2. Mean cross validation ROC AUC dynamics during elimination of attributes. The diagram shows the maximum ROC AUC and the standard deviation of the value in cross validation
Fig. 3. Gini significance for 33 best attributes learned after training the random forest on 220 attributes
Fig. 4. Diagram of SHAP values for the 20 most significant attributes. A positive class means successful IVF, negative class — failure thereof
Table. Results of five-fold cross validation of the random forest model, individual infertility diagnoses, in the context of selection of hyperparameters using the GridSearch method