Transfer learning to enhance amenorrhea status prediction in cancer and fertility data with missing values
This work aims to improve amenorrhea status prediction for cancer and fertility patients, which is a domain-specific problem. The significance is incremental due to the lack of concrete results or specific problem statements.
This paper addresses the challenges of insufficient labeled training data and unavoidable missing values in health and medical datasets for predicting amenorrhea status. It proposes using machine learning algorithms, specifically transfer learning, to overcome these issues.
Collecting sufficient labelled training data for health and medical problems is difficult (Antropova, et al., 2018). Also, missing values are unavoidable in health and medical datasets and tackling the problem arising from the inadequate instances and missingness is not straightforward (Snell, et al. 2017, Sterne, et al. 2009). However, machine learning algorithms have achieved significant success in many real-world healthcare problems, such as regression and classification and these techniques could possibly be a way to resolve the issues.