Analyzing Outcomes of Intrauterine Insemination Treatment by Application of Cluster Analysis or Kohonen Neural Networks
Anna Justyna Milewska, Dorota Jankowska, Urszula Cwalina, Teresa Więsak, Dorota Citko, Allen Morgan, Robert Jay Milewski · Studies in Logic Grammar and Rhetoric · 2013
Abstract Intrauterine insemination (IUI) is one of many treatments provided to infertility patients. Many factors such as, but not limited to, quality of semen, the age of a woman, and reproductive hormone levels contribute to infertility. Therefore, the aim of our study is to establish a statistical probability concerning the prediction of which groups of patients have a very good or poor prognosis for pregnancy after IUI insemination. For that purpose, we compare the results of two analyses: Cluster Analysis and Kohonen Neural Networks. The k-means algorithm from the clustering methods was the best to use for selecting patients with a good prognosis but the Kohonen Neural Networks was better for selecting groups of patients with the lowest chances for pregnancy.