Fuzzy machine learning logic utilization on hormonal imbalance dataset

In this research work, a novel fuzzy data transformation technique has been proposed and applied to the hormonal imbalance dataset. Hormonal imbalance is ubiquitously found principally in females of reproductive age which ultimately leads to numerous related medical conditions. Polycystic Ovary Syndrome (PCOS) is one of them. Treatment along with adopting a healthy lifestyle is advised to mitigate its consequences on the quality of life. The biological dataset of hormonal imbalance “PCOS” provides limited results that is whether the syndrome is present or not. Also, there are input variables that contain binary responses only, to deal with this conundrum, a novel fuzzy data transformation technique has been developed and applied to them thus leading to their fuzzy transformation which provides a broader spectrum to diagnose PCOS. Due to this, the output variable has also been transformed. Hence, a novel fuzzy transformation technique has been employed due to the limitation of the dataset leading to the transition of binary classification output into three classes. An adaptive fuzzy machine learning logic model is developed in which the inference of the transformed biological dataset is performed by the machine learning techniques that provide the fuzzy output. Machine learning techniques have also been applied to the untransformed biological dataset. Both implementations have been compared by computation of the relevant metrics. Machine learning employment on untransformed biological dataset provides limited results whether the syndrome is present or absent however machine learning on fuzzy transformed biological dataset provides a broader spectrum of diagnosis consisting of a third class depicting that PCOS might be present which would ultimately alert a patient to take preventive measures to minimize the chances of syndrome development in future. © 2024 Elsevier Ltd