Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2023 Sep 8;4(9):100830.
doi: 10.1016/j.patter.2023.100830.

A historical perspective of biomedical explainable AI research

Luca Malinverno  1 , Vesna Barros  2   3 , Francesco Ghisoni  1 , Giovanni Visonà  4 , Roman Kern  5   6 , Philip J Nickel  7 , Barbara Elvira Ventura  1 , Ilija Šimić  6 , Sarah Stryeck  8 , Francesca Manni  9 , Cesar Ferri  10 , Claire Jean-Quartier  11 , Laura Genga  7 , Gabriele Schweikert  12 , Mario Lovrić  6   13 , Michal Rosen-Zvi  2   3
Affiliations
Review

A historical perspective of biomedical explainable AI research

Luca Malinverno et al. Patterns (N Y). .

Abstract

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.

Keywords: COVID-19; PRISMA; artificial intelligence; coronavirus; decision-making; explainability; foundation models; machine learning; meta-review; trustworthiness.

PubMed Disclaimer

Conflict of interest statement

M.R.-Z. and V.B. are employees of IBM Research, Haifa, Israel. F.M. is an employee of Philips Research, Eindhoven, the Netherlands. I.S. has received funding from multiple funding agencies through a collaborative funding program and declares no support from any organization for the submitted work. P.J.N. receives funding from the Dutch Research Council (DWO) for the grant “Mobile Support Systems for Behavior Change,” of which he is the principal investigator (P.I.). M.L. is funded by the EU-Commission grant no. 101057497-EDIAQI.

Figures

None
Graphical abstract
Figure 1
Figure 1
Trends in XAI papers related to COVID-19 (A) Proportions of COVID-19 categories in the dataset. (B) Cumulative number of XAI papers for each category throughout time. The increase in COVID-19-related papers, represented by the light blue and light green curves, set off around 7 months after the pandemic onset.
Figure 2
Figure 2
Comparison between the overall number of biomedical XAI publications (blue curve) and its proportion within the biomedical AI field (brown curve) Both plots show quarterly patterns of publications throughout time smoothed by a 1-year rolling average window.
Figure 3
Figure 3
Biomedical XAI statistics and trends of the cohort of eligible papers (A) Proportions of biomedical XAI categories. (B) Average number of citations per month since published date. Error bars represent 95% confidence intervals. (C) Counts of biomedical XAI papers published per quarter year. For each category (colored curve), we smoothed quarterly patterns by using the 1 year rolling average window.
See this image and copyright information in PMC

References

    1. Tanne J.H. Covid-19: FDA approves Pfizer-BioNTech vaccine in record time. BMJ. 2021;374:n2096. - PubMed
    1. A critical overview of current progress for COVID-19: development of vaccines, antiviral drugs, and therapeutic antibodies. J. Biomed. Sci. 2022;29:68. doi: 10.1186/s12929-022-00852-9. https://link.springer.com/article/10.1186/s12929-022-00852-9 - DOI - DOI - PMC - PubMed
    1. Addressing Backlogs and Managing Waiting Lists during and beyond the COVID-19 Pandemic [Internet]. [cited 2023 Jan 11]. Available from: https://eurohealthobservatory.who.int/publications/i/addressing-backlogs.... - PubMed
    1. Haldane V., De Foo C., Abdalla S.M., Jung A.S., Tan M., Wu S., Chua A., Verma M., Shrestha P., Singh S., et al. Health systems resilience in managing the COVID-19 pandemic: lessons from 28 countries. Nat. Med. 2021 Jun;27:964–980. - PubMed
    1. Martin A., Nateqi J., Gruarin S., Munsch N., Abdarahmane I., Zobel M., Knapp B. An artificial intelligence-based first-line defence against COVID-19: digitally screening citizens for risks via a chatbot. Sci. Rep. 2020;10 - PMC - PubMed