Transfer learning to enhance amenorrhea status prediction in cancer and fertility data with missing values

TL;DR

This paper explores using transfer learning to improve the prediction of amenorrhea status in cancer and fertility datasets, addressing challenges of limited labeled data and missing values in health data.

Contribution

It introduces a transfer learning approach tailored for health datasets with missing values to enhance amenorrhea prediction accuracy.

Findings

Improved prediction accuracy with transfer learning

Effective handling of missing data in health datasets

Demonstrated benefits in cancer and fertility data contexts

Abstract

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.