Human-in-the-Loop Machine Learning for the Treatment of Pancreatic Cancer

Abstract

Human-in-the-Loop Machine Learning (HITL-ML) is a set of techniques that attempt to actively introduce experts into the learning loop of machine learning (ML) models to improve the learning process. In this paper we present a HITL-ML strategy for the treatment of pancreatic cancer in which a classifier should decide whether a chemotherapy treatment is suitable or not for the patient. The contribution of this work is, first, to demonstrate that involving human experts in the learning process improves the learning capacity of the model; second, to develop a relatively novel Interactive Machine Learning (IML) approach in which unstructured feedback obtained from the experts is used to optimize the synthetic cases generator implemented by a Generative Adversarial Network (GAN). This GAN is used to augment the dataset and to improve the generalization capabilities of the model. Finally, the inclusion of humans in the learning process also poses new challenges, e.g., aspects related to Human-Computer Interaction (HCI), normally irrelevant in ML systems, are now of great importance and can condition the success of a HITL approach. This paper also discusses the approach taken to address these challenges.