Machine Learning Based Assessment and Predictive Analysis of In-Vitro Fertilization Success Rate

Abstract

INTRODUCTION: The transformation in the lifestyle and other societal and economic factors during modern times have led to rise in the cases of infertility among young generation. Apart from these factors infertility may also be attributed to different medical conditions among both men and women. This rise in the cases of infertility is a matter of huge concern to the mankind and should be seriously pondered upon. However, the unprecedented advancements in the field of healthcare have led to In Vitro fertilization as a rescue to this devastating condition. Although the In Vitro fertilization has the potential to unfurl the happiness, it has associated challenges also in terms of physical and emotional health. Also, the success rate of In Vitro fertilization may vary from person to person. OBJECTIVES: To predict the success rate of In Vitro fertilization. METHODS: Machine Learning Models. RESULTS: It has been observed that Adaboost outperforms all other machine learning models by yielding an accuracy of 97.5%. CONCLUSION: During the result analysis, it is concluded that if age > 36, there is a negative propensity for clinical pregnancy and if age >40, the probability of a clinical pregnancy dramatically declines. Further, the propensity of clinical pregnancy is positively correlated to the count of embryos transferred in the same IVF cycle.