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

By Andreas Holzinger. 2016

859 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Science Applications, Human-Computer Interaction, Medical & Health AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Science Applications

In Human-Computer Interaction

In Medical & Health AI

Citations in the corpus

What do we need to build explainable AI systems for the medical domain? (2017, background): “If human intelligence is complemented by machine learning and at least in some cases even overruled, humans must be able to understand, to re-enact and to be able to interactively inﬂuence the machine decision process Holzinger (2016).”
Reinforcement Learning in Healthcare: A Survey (2019, background): “Knowledge-driven RL methods are of great interest to problems in healthcare domains, where traditional learning algorithms would possibly fail due to issues such as insufficient training samples, complex and incomplete data, or unexplainable learning processes [85].”
Towards Integrative Machine Learning and Knowledge Extraction (2017, background): “However, recent advances in the area of interactive machine learning (also called “human-in-a-loop”) [10,11] show exciting results in analysing datasets where usually neither human nor computer algorithms could solve on their own.”
Human-in-the-loop machine learning: a state of the art (2022, background): “For example, Holzinger (2016) defined IML as “algorithms that can interact with agents and can optimize their learning behavior through these interactions, where the agents can also be human”.”
Legal, regulatory, and ethical frameworks for development of standards in artificial intelligence (AI) and autonomous robotic surgery (2019, background): “Here, interactive ML (iML) is supportive: Humans can learn from very few examples and are able to understand the context; thus, a human ‐ in ‐ the ‐ loop, particularly a doctor ‐ in ‐ the ‐ loop, or even many doctors ‐ in ‐ the ‐ loop (crowdsourcing) 31 can help to reduce complexity.”
A historical perspective of explainable Artificial Intelligence (2020, background): “…recent successes in machine learning technology (Guidotti et al., 2018), for both autonomous (Nunes & Jannach, 2017) and human-in-the-loop systems (Holzinger, 2016; Holzinger, Plass, et al., 2019), with applications in recommender systems (Tintarev & Masthof, 2015), and approaches of…”
Causability and explainability of artificial intelligence in medicine (2019, background): “In medical decision support we are confronted with uncertainty, with probabilistic, unknown, incomplete, imbalanced, heterogeneous, noisy, dirty, erroneous, inaccurate and missing data sets in arbitrarily high-dimensional spaces (Holzinger, Dehmer, & Jurisica, 2014), (Lee & Holzinger, 2016).”
Artificial Intelligence and Management: The Automation–Augmentation Paradox (2020, background): “In such cases, rule-based automation is impossible, but managers could use an augmentation approach to explore the problem further (Holzinger, 2016).”
Trustworthy AI: From Principles to Practices (2021, background): “To minimize and make the best use of human effort in such interaction, efficient design of patterns of human–machine cooperation is an emerging topic in interdisciplinary work on HCI and AI and is referred to as human-in-the-loop or interactive machine learning [157] in the literature.”
Introduction to MAchine Learning & Knowledge Extraction (MAKE) (2017, background): “, a human kernel [33]), or the involvement of a human directly into the machine-learning algorithm [39], thereby making use of human cognitive abilities, is a promising approach.”
Explaining machine learning models in sales predictions (2017, background): “Based on the new insights, they have an opportunity to update the data set, retrain and re-evaluate the models before the next use, practicing human-in-the-loop in ML (Holzinger, 2016).”
Entity-Centric Information Access with Human in the Loop for the Biomedical Domain (2017, background): “Key to the approach is to think the user in the center of the process and offer the user an adaptive ML environment (Holzinger, 2016; Holzinger et al., 2017) where manual effort in terms of annotating entities or classifying relations immediately pays of in an improved representation in the EG.”
A Survey of Human-in-the-loop for Machine Learning (2021, background): “[22] A. Holzinger, M. Plass, M. Kickmeier-Rust, K. Holzinger, G. C. Crişan, C.-M. Pintea, and V. Palade, “Interactive machine learning: experimental evidence for the human in the algorithmic loop,” Applied Intelligence, vol. 49, no. 7, pp. 2401–2414, 2019.”
A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop (2017, methodology): “…human-in-the-loop (e.g., a human kernel (Wilson et al., 2015)), or the involvement of a human directly into the algorithm, iML is deﬁned by ”algorithms which interact with agents and can optimize their learning behaviour through this interaction – where the agents can be humans (Holzinger, 2016a)”.”