A visual analytics system for multi-model comparison on clinical data predictions

Li, Yiran; Fujiwara, Takanori; Choi, Yong K.; Kim, Katherine; Liu, Kwan

doi:10.1016/j.visinf.2020.04.005

Cited by 27 publications

(16 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zintgraf, Cohen, Adel, and Welling (2017) present a method that visualizes which pixels of an input image are evidence for or evidence against a node in a deep neural network. Moreover, Li, Fujiwara, Choi, Kim, and Ma (2020) focus on visualizing features to explain the reasoning of a model. The approach is used to explain and compare different models for clinical data beyond their accuracy scores.…”

Section: Box 1 Visual Analytics and Interpretabilitymentioning

confidence: 99%

Interpretability of machine learning‐based prediction models in healthcare

Štiglic

Kocbek

Fijačko

et al. 2020

WIREs Data Min & Knowl

288

148

View full text Add to dashboard Cite

There is a need of ensuring that learning (ML) models are interpretable. Higher interpretability of the model means easier comprehension and explanation of future predictions for end-users. Further, interpretable ML models allow healthcare experts to make reasonable and data-driven decisions to provide personalized decisions that can ultimately lead to higher quality of service in healthcare. Generally, we can classify interpretability approaches in two groups where the first focuses on personalized interpretation (local interpretability) while the second summarizes prediction models on a population level (global interpretability). Alternatively, we can group interpretability methods into model-specific techniques, which are designed to interpret predictions generated by a specific model, such as a neural network, and model-agnostic approaches, which provide easy-to-understand explanations of predictions made by any ML model. Here, we give an overview of interpretability approaches using structured data and provide examples of practical interpretability of ML in different areas of healthcare, including prediction of healthrelated outcomes, optimizing treatments, or improving the efficiency of screening for specific conditions. Further, we outline future directions for interpretable ML and highlight the importance of developing algorithmic solutions that can enable ML driven decision making in high-stakes healthcare problems.

show abstract

Section: Box 1 Visual Analytics and Interpretabilitymentioning

confidence: 99%

Interpretability of machine learning‐based prediction models in healthcare

Štiglic

Kocbek

Fijačko

et al. 2020

WIREs Data Min & Knowl

288

148

View full text Add to dashboard Cite

show abstract

“…Another example from pain research is how subsymbolic AI can be subjected to further analysis to extract the individual decision process for each case, or how it can be complemented by symbolic AI that provides understandable explanations for group assignment, although the exact decision process may differ from that of subsymbolic AI [37]. This has been elaborated in more detail in a visual analysis system for multimodel comparison of predictions for clinical data [75]. The system allows comparison and evaluation of different AI models based on their interpretable information, with the goal of assisting clinicians in decision making.…”

Section: Accessibilitymentioning

confidence: 99%

Explainable Artificial Intelligence (XAI) in Biomedicine: Making AI Decisions Trustworthy for Physicians and Patients

2021

View full text Add to dashboard Cite

The use of artificial intelligence (AI) systems in biomedical and clinical settings can disrupt the traditional doctor–patient relationship, which is based on trust and transparency in medical advice and therapeutic decisions. When the diagnosis or selection of a therapy is no longer made solely by the physician, but to a significant extent by a machine using algorithms, decisions become nontransparent. Skill learning is the most common application of machine learning algorithms in clinical decision making. These are a class of very general algorithms (artificial neural networks, classifiers, etc.), which are tuned based on examples to optimize the classification of new, unseen cases. It is pointless to ask for an explanation for a decision. A detailed understanding of the mathematical details of an AI algorithm may be possible for experts in statistics or computer science. However, when it comes to the fate of human beings, this “developer’s explanation” is not sufficient. The concept of explainable AI (XAI) as a solution to this problem is attracting increasing scientific and regulatory interest. This review focuses on the requirement that XAIs must be able to explain in detail the decisions made by the AI to the experts in the field.

show abstract

“…G3 Comparative analysis of RF models. Another design goal is the ability to have a comparative analysis between two or more RF models to assist model developers in selecting reliable models [50]. An RF model is built using various parameters such as the number of trees, splitting criteria, maximum depth of a tree, and the maximum number of features to be considered during a split.…”

Section: G2 Local Interpretation By Preserving the Global Context Loc...mentioning

confidence: 99%

Random Forest Similarity Maps: A Scalable Visual Representation for Global and Local Interpretation

2021

View full text Add to dashboard Cite

Machine Learning prediction algorithms have made significant contributions in today’s world, leading to increased usage in various domains. However, as ML algorithms surge, the need for transparent and interpretable models becomes essential. Visual representations have shown to be instrumental in addressing such an issue, allowing users to grasp models’ inner workings. Despite their popularity, visualization techniques still present visual scalability limitations, mainly when applied to analyze popular and complex models, such as Random Forests (RF). In this work, we propose Random Forest Similarity Map (RFMap), a scalable interactive visual analytics tool designed to analyze RF ensemble models. RFMap focuses on explaining the inner working mechanism of models through different views describing individual data instance predictions, providing an overview of the entire forest of trees, and highlighting instance input feature values. The interactive nature of RFMap allows users to visually interpret model errors and decisions, establishing the necessary confidence and user trust in RF models and improving performance.

show abstract

A visual analytics system for multi-model comparison on clinical data predictions

Cited by 27 publications

References 45 publications

Interpretability of machine learning‐based prediction models in healthcare

Interpretability of machine learning‐based prediction models in healthcare

Explainable Artificial Intelligence (XAI) in Biomedicine: Making AI Decisions Trustworthy for Physicians and Patients

Random Forest Similarity Maps: A Scalable Visual Representation for Global and Local Interpretation

Contact Info

Product

Resources

About