Abstract
Progress in statistical machine learning made AI in medicine successful, in certain classification tasks even beyond human level performance. Nevertheless, correlation is not causation and successful models are often complex "black-boxes", which make it hard to understand why a result has been achieved. The explainable AI (xAI) community develops methods, e. g. to highlight which input parameters are relevant for a result; however, in the medical domain there is a need for causability: In the same way that usability encompasses measurements for the quality of use, causability encompasses measurements for the quality of explanations produced by xAI. The key for future human-AI interfaces is to map explainability with causability and to allow a domain expert to ask questions to understand why an AI came up with a result, and also to ask "what-if" questions (counterfactuals) to gain insight into the underlying independent explanatory factors of a result. A multi-modal causability is important in the medical domain because often different modalities contribute to a result.
Highlights
Deep Learning Success Examples in Medical AITo reach human-level AI is the quest of AI researchers since the emergence of this field [1]
What did they do? They classified skin lesions using a single convolutional neural network (CNN), trained it end-to-end from the derma images directly, and used only pixels and disease labels as inputs
Available and practical useable deep learning approaches achieve a performance that is beyond human level performance – even in the medical domain
Summary
To reach human-level AI is the quest of AI researchers since the emergence of this field [1]. Because highlighting such overlaps between human thinking and machine “thinking” can contribute to what are currently top issues in the machine learning community: i) to eliminate bias and to improve algorithms robustness, and ii) to make the results retraceable, explainable in order to meet the quest of accountability of medical AI. Despite all these successes, one of the most pressing problems is in robustness, i. We briefly discuss some basics of explainability and causability
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
