Explainable AI and Multi-Modal Causability in Medicine
Open accessThe DOI matches its Crossref record; 81 of the 81 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Moreover, nontextual data types play a crucial role in diagnosis, effective treatment planning, research, and patient care [9-11].”
From Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook. (2024) · cites this paper as [9]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
The Elements of Statistical Learning
Hastie, T., Tibshirani, R., & Friedman, J. (2009) · Springer Series in Statistics · doi:10.1007/978-0-387-84858-7 · Cited by 25,970 · cited 1×
“learning theory [2] and statistical learning practice [3].”
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 1×
“Other methods include deconvolution by reversing the effects of convolution and bringing out from two functions a third function which is then the product of both, guided backpropagation, and the use of so-called concept activation vectors [35], [36], [37], [38].”
MethodArrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.10045 · Cited by 11,321 · cited 1×
“The field of explainable AI is meanwhile very popular [23], [24], [25], [26], and the explainable AI (xAI) community is very active in developing various methods to help making such “black box” approaches, as outlined in the introduction, retraceable, understandable, and human interpretable.”
BackgroundRudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 3×
“Consequently, to make such approaches even more successful we need further work to make them robust [20], [21], understandable [22], and interpretable for a human expert [14].”
BackgroundBarredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423
An overview of statistical learning theory
Vapnik, V. N. (1999) · IEEE Transactions on Neural Networks · doi:10.1109/72.788640 · Cited by 6,266 · cited 1×
“Research in the last decades has proved it to be very difficult and the progress has been slow, despite great success in statistical machine learning theory [2] and statistical learning practice [3].”
BackgroundArtificial intelligence in radiology
Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. W. L. (2018) · Nature Reviews Cancer · doi:10.1038/s41568-018-0016-5 · Cited by 3,803 · cited 1×
“One particular relevant field is medical image analysis, including AI-applications in pathology [6], radiology [7], dermatology [8], ophthalmology [9], oncology [10], and many other medical application fields.”
BackgroundMethods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665 · cited 1×
“pixel-wise relevancepropagation [31], layer-wise relevance propagation [32], or deepTaylor decomposition [33],which also works on graph-based data [34].”
Background
Cited by
Antoniadi, A. M., Du, Y., Guendouz, Y., Wei, L., Mazo, C., Becker, B. A., & Mooney, C. (2021) · Applied Sciences · doi:10.3390/app11115088 · Cited by 629
“One could argue that it would not be ethical to apply in clinical practice a model that does not have the best possible performance, as the ultimate goal is to provide the best possible assistance to patients [92].”
BackgroundExplainable Artificial Intelligence Applications in Cyber Security: State-of-the-Art in Research
Zhang, Z., Hamadi, H. A., Damiani, E., Yeun, C. Y., & Taher, F. (2022) · IEEE Access · doi:10.1109/access.2022.3204051 · Cited by 450
“[88] Argued the necessity to apply XAI in clinical practice”
BackgroundHolzinger, A., Malle, B., Saranti, A., & Pfeifer, B. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.01.008 · Cited by 352
“…and causability requires new human–AI interfaces which allow domain experts to interactively ask questions and counterfactual questions to gain deep insight into the underlying independent and disentangled explanatory factors of a result, adapted to the needs of the respective end user [16].”
BackgroundSelf-citationMultimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349
“Moreover, nontextual data types play a crucial role in diagnosis, effective treatment planning, research, and patient care [9-11].”
Chou, Y.-L., Moreira, C., Bruza, P., Ouyang, C., & Jorge, J. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.11.003 · Cited by 302
Metadata
- Authors
- Holzinger, A.
- Affiliations
- Medical University of Graz (AT)
- Corresponding author
- Holzinger, Andreas
- ORCID
- Holzinger, Andreas
- Venue
- i-com
- Publisher
- Walter de Gruyter GmbH
- Published
- 2020-12-01
- Volume
- 19
- Issue
- 3
- Pages
- 171-179
- ISSN
- 1618-162X (ISSN-L)
- 2196-6826
- PMC
- PMC10064549
- OpenAlex
- W3122765966
- Semantic Scholar
- 83d8ec478bc88c86e32340d0a2d8dc338c7df918
- Cited by
- 87
- References
- 78
- Citations by year
- 2026: 13 · 2025: 11 · 2024: 11 · 2023: 10 · 2022: 21 · 2021: 20
- FWCI
- 5.01
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- i-com (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Funders
- Horizon 2020 Framework Programme (826078)
- Austrian Science Fund (P-32554)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- explainable AI, causality, counterfactual reasoning, what-if questions, black-box models, artificial intelligence in healthcare, human-AI interaction, feature importance
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Explainable AI and Multi-Modal Causability in Medicine. https://app.cochat.ai/papers/10.1515/icom-2020-0024
- The paper
- Holzinger, A. (2021). Explainable AI and Multi-Modal Causability in Medicine. i-com. https://doi.org/10.1515/icom-2020-0024
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
