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

  • Holzinger A
  • 248


    Mendeley users who have this article in their library.
  • 40


    Citations of this article.


Machine learning (ML) is a growing eld in computer science, and health informatics is amongst 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 bene t from big data with many training sets. However, in the health domain, sometimes we are confronted with small data, or rare events, where aML-approaches su er of insucient training samples. Here interactive Machine Learning (iML) may be of help, having its roots in Reinforcement Learning (RL), Preference Learning (PL) and Active Learning (AL). The term iML is not yet well used, so we de ne it as "algorithms that can interact with agents and can optimize their learning behaviour through these interactions, where the agents can also be human". This "human-in-the-loop" can be bene cial 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 NPhard problem, reduces greatly in complexity through the input and assistance of a human agent involved in the learning phase.

Author-supplied keywords

  • Health informatics
  • Interactive machine learning

Get free article suggestions today

Mendeley saves you time finding and organizing research

Sign up here
Already have an account ?Sign in

Find this document


Cite this document

Choose a citation style from the tabs below

Save time finding and organizing research with Mendeley

Sign up for free