A historical perspective of biomedical explainable AI research
Patterns · 2023-09 · 4 (9) · 100830
DOI: 10.1016/j.patter.2023.100830 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Patterns, 2023-09. Verfasst von Luca Malinverno und 15 weiteren Autor:innen. Beteiligte Einrichtung: Porini SRL, Via Cavour, 222074 Lomazzo, Italy. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Medical Research Council, Bundesministerium für Verkehr, Innovation und Technologie, Horizon 2020 Framework Programme.
Abstract (Originalsprache)
The black-box nature of most artificial intelligence (AI) models encourages the development of explainability methods to engender trust into the AI decision-making process. Such methods can be broadly categorized into two main types: post hoc explanations and inherently interpretable algorithms. We aimed at analyzing the possible associations between COVID-19 and the push of explainable AI (XAI) to the forefront of biomedical research. We automatically extracted from the PubMed database biomedical XAI studies related to concepts of causality or explainability and manually labeled 1,603 papers with respect to XAI categories. To compare the trends pre- and post-COVID-19, we fit a change point detection model and evaluated significant changes in publication rates. We show that the advent of COVID-19 in the beginning of 2020 could be the driving factor behind an increased focus concerning XAI, playing a crucial role in accelerating an already evolving trend. Finally, we present a discussion with future societal use and impact of XAI technologies and potential future directions for those who pursue fostering clinical trust with interpretable machine learning models.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Porini SRL, Via Cavour, 222074 Lomazzo, Italy.
- AI for Accelerated Healthcare & Life Sciences Discovery, IBM R&D Laboratories, University of Haifa Campus, Mount Carmel, Haifa 3498825, Israel.
- The Hebrew University of Jerusalem, Ein Kerem Campus, 9112102, Jerusalem, Israel.
- Empirical Inference, Max-Planck Institute for Intelligent Systems, 72076 Tübingen, Germany.
- Institute of Interactive Systems and Data Science, Graz University of Technology, Sandgasse 36/III, 8010 Graz, Austria.
- Know-Center GmbH, Sandgasse 36/4A 8010, Graz, Austria.
Förderung
- Medical Research Council
- Bundesministerium für Verkehr, Innovation und Technologie
- Horizon 2020 Framework Programme
- Bundesministerium für Digitalisierung und Wirtschaftsstandort
- H2020 Marie Skłodowska-Curie Actions
- European Commission
- Österreichische Forschungsförderungsgesellschaft
- Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Zitieren
APA
Malinverno, L., Barros, V., Ghisoni, F., Visonà, G., Kern, R., Nickel, P. J., Ventura, B. E., Šimić, I., Stryeck, S., Manni, F., Ferri, C., Jean-Quartier, C., Genga, L., Schweikert, G., Lovrić, M., & Rosen-Zvi, M. (2023). A historical perspective of biomedical explainable AI research. Patterns, 4(9), 100830. https://doi.org/10.1016/j.patter.2023.100830
Vancouver
Malinverno L, Barros V, Ghisoni F, Visonà G, Kern R, Nickel PJ, et al. A historical perspective of biomedical explainable AI research. Patterns. 2023;4(9):100830. doi:10.1016/j.patter.2023.100830
BibTeX
@article{Malinverno2023,
author = {Malinverno, Luca and Barros, Vesna and Ghisoni, Francesco and Visonà, Giovanni and Kern, Roman and Nickel, Philip J and Ventura, Barbara Elvira and Šimić, Ilija and Stryeck, Sarah and Manni, Francesca and Ferri, Cesar and Jean-Quartier, Claire and Genga, Laura and Schweikert, Gabriele and Lovrić, Mario and Rosen-Zvi, Michal},
title = {A historical perspective of biomedical explainable AI research},
journal = {Patterns},
year = {2023},
volume = {4},
number = {9},
pages = {100830},
doi = {10.1016/j.patter.2023.100830}
}
EUVIMED