<abstract xmlns="http://www.w3.org/1999/xhtml"><p>There are high hopes for using the artificial neural networks (ANN) technique to predict results of infertility treatment using the in vitro fertilization (IVF) method. Some reports show superiority of the ANN approach over conventional methods. However, fully satisfactory results have not yet been achieved. Hence, there is a need to continue searching for new data describing the treatment process, as well as for new methods of extracting information from these data. There are also some reports that the use of principal component analysis (PCA) before the process of training the neural network can further improve the efficiency of generated models. The aim of the study herein presented was to verify the thesis that the use of PCA increases the effectiveness of the prediction by ANN for the analysis of results of IVF treatment. Results for the PCA-ANN approach proved to be slightly better than the ANN approach, however the obtained differences were not statistically significant.</p></abstract>

There are high hopes for using the artificial neural networks (ANN) technique to predict results of infertility treatment using the in vitro fertilization (IVF) method. Some reports show superiority of the ANN approach over conventional methods. However, fully satisfactory results have not yet been achieved. Hence, there is a need to continue searching for new data describing the treatment process, as well as for new methods of extracting information from these data. There are also some reports that the use of principal component analysis (PCA) before the process of training the neural network can further improve the efficiency of generated models. The aim of the study herein presented was to verify the thesis that the use of PCA increases the effectiveness of the prediction by ANN for the analysis of results of IVF treatment. Results for the PCA-ANN approach proved to be slightly better than the ANN approach, however the obtained differences were not statistically significant.

Application of Artificial Neural Networks and Principal Component Analysis to Predict Results of Infertility Treatment Using the IVF Method

Department of Statistics and Medical Informatics, Medical University of Bialystok,

Department of Gamete and Embryo Biology, Institute of Animal Reproduction and Food Research, Polish Academy of Sciences, Olsztyn,

Shore Institute for Reproductive Medicine, Lakewood,

Department of Reproduction and Gynecological Endocrinology, Medical University of Bialystok,

Studies in Logic, Grammar and Rhetoric

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

There are high hopes for using the artificial neural networks (ANN) technique to predict results of infertility treatment using the in vitro fertilization...

Application of Artificial Neural Networks and Principal Component Analysis to Predict Results of Infertility Treatment Using the IVF Method

Online veröffentlicht: 23. Jan. 2017

Seitenbereich: 33 - 46

DOI: https://doi.org/10.1515/slgr-2016-0045

© 2016 Studies in Logic, Grammar and Rhetoric

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.