Analysis of Factors with Influence on Assisted Reproduction Outcome Using System for Data Mining SHLUK

Overview

Objective:
To retrospective explorating computer analysis of data about therapeutic cycles in assisted reproduction technology (ART) to confirm applicability of system for data mining SHLUK in partial analysis of fertilisation phase of therapeutic cycle. Relations between parameters of sperm count analysis and outcome of in vitro fertilisation were analyzed.Design: Retrospective analysis.Setting: 1st Depart of Obstet. and Gynaecol., Masaryk University, Brno; FEI, VŠB, Ostrava.Methods and material: Conditions of successful therapy in single phases of ART therapeutic cycles, were analysed using system SHLUK, which included a lot of methods for data mining. Analysis of relation between reasons and results in ART therapeutic cycles was done through method IMPL and method of group implication GRIMPL.Analysed file included data about 8516 therapeutic cycles ART in 4470 patients and data about 666 clinical pregnancies stored in electronical form in clinical data register. The model analysis of fertilisation tested relations between parameters of sperm analysis and outcome of in vitro fertilisation. Fertilisation rate (FR) - ratio of fertilized oocytes/obtained oocytes was evaluated as fertilisation stage outcome.Results: Significantly higher FR - 60.9 % was in the group with sperm concentration before preparation 41 - 60 min/ml. When sperm concentration before preparation was under 10 mil/ml - FR was significantly lower - 45.3 %. Motility of sperm before preparation 41 - 50 % - FR was significantly higher - 56.9 %. Significantly higher FR - minimal 56.0 % was in group of examinations with sperm after preparation was 41 - 90 %, then FR was significantly higher - 53.5 %. In sperm survival test, where more than 30 % of sperm survive 24 hours of cocultivation with oocytes FR was significantly higher - minimal 55.9 %.Conclusion: Applicability of system for data mining SHLUK in the analysis of factors with influence on assisted reproduction outcome was proved. System for data mining SHLUK makes posible to define statisticaly significant relations between atributes of fertilisation stage of ART cycles and it is able to postulate basic hypothesis about existing reasons and results in therapeutic cycles of ART.

Key words:
explorating computer analysis, assisted reproduction technology (ART), parameters of sperm, results in ART