Interactive machine learning for health informatics: when do we need the human-in-the-loop?

TLDR

Machine learning is rapidly expanding, especially in health informatics, but while automatic ML thrives on large datasets, small or rare health data sets limit its effectiveness. The paper proposes interactive machine learning (iML) as a solution to address data scarcity in health informatics. iML algorithms interact with human agents to optimize learning, enabling human‑guided heuristic sampling that reduces the search space for hard problems such as subspace clustering, protein folding, and k‑anonymization. The inclusion of human input dramatically lowers the complexity of NP‑hard problems during the learning phase.

Abstract

Machine learning (ML) is the fastest growing field in computer science, and health informatics is among the greatest challenges. The goal of ML is to develop algorithms which can learn and improve over time and can be used for predictions. Most ML researchers concentrate on automatic machine learning (aML), where great advances have been made, for example, in speech recognition, recommender systems, or autonomous vehicles. Automatic approaches greatly benefit from big data with many training sets. However, in the health domain, sometimes we are confronted with a small number of data sets or rare events, where aML-approaches suffer of insufficient training samples. Here interactive machine learning (iML) may be of help, having its roots in reinforcement learning, preference learning, and active learning. The term iML is not yet well used, so we define it as "algorithms that can interact with agents and can optimize their learning behavior through these interactions, where the agents can also be human." This "human-in-the-loop" can be beneficial in solving computationally hard problems, e.g., subspace clustering, protein folding, or k-anonymization of health data, where human expertise can help to reduce an exponential search space through heuristic selection of samples. Therefore, what would otherwise be an NP-hard problem, reduces greatly in complexity through the input and the assistance of a human agent involved in the learning phase.