lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

Explainable AI in Biomedical Research: A Systematic Review and Meta-Analysis

20 Pages Posted: 24 Jan 2023

See all articles by Luca Malinverno

Luca Malinverno

Porini SRL

Vesna Barros

Porini SRL

Francesco Ghisoni

Porini SRL

Giovanni Visonà

Max Planck Institute for Intelligent Systems - Empirical Inference

Roman Kern

Graz University of Technology - Institute of Interactive Systems and Data Science

Philip Nickel

Eindhoven University of Technology (TUE)

Barbara Elvira Ventura

Porini SRL

Ilija Šimić

Know-Center

Sarah Stryeck

Research Center Pharmaceutical Engineering GmbH

Francesca Manni

Philips Research

Cesar Ferri

Polytechnic University of Valencia

Claire Jean-Quartier

Graz University of Technology - Research Data Management

Laura Genga

Eindhoven University of Technology

Gabriele Schweikert

University of Dundee - School of Life Sciences

Mario Lovrić

Porini SRL

Michal Rosen-Zvi

University of Haifa - AI for Accelerated Healthcare & Life Sciences Discovery

More...

Abstract

Background: 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. We aimed to analyze the possible role of Covid-19 in bringing explainable AI (XAI) to the forefront of biomedical research.

Methods: In this systematic review and meta-analysis, we searched in the PubMed database for studies published from Jan 1, 2010, to Nov 3, 2022. Biomedical XAI papers were extracted based on a set of pre-defined keywords. We automatically excluded papers that were not related to concepts of causality or explainability and manually labeled 1603 papers with respect to XAI categories that best describe the study. We compared the trends pre- and post- Covid -19 and fit a change point detection model to evaluate significant changes in publication rates.

Findings: We found an exponential growth of biomedical XAI papers. Specifically, an inflection period in the publication rate was observed in October 2020, when the quantity of XAI research in biomedical sciences surged upward significantly. When modeling the effect of the changepoint as a shift in time, we observed that such abrupt change would have been observed only 22 months later, had Covid -19 not happened.

Interpretation: The advent of Covid -19 in the beginning of 2020 could be the driving factor behind the increased focus concerning XAI, accounting for the several months necessary to analyze data and publish manuscripts. However, our analyses were done based on the review of titles and abstracts of the studies. Establishing the causal nature of this link would require careful mining of the content of these papers.

Funding: We acknowledge the funding received from the European Union’s Framework Programme for Research and Innovation Horizon 2020 (2014-2020) under the Marie Skłodowska-Curie Grant Agreement No. 813533-MSCA-ITN-2018. I.S. was funded by the “DDAI” COMET Module within the COMET – Competence Centers for Excellent Technologies Programme, funded by the Austrian Federal Ministry for Transport, Innovation and Technology (bmvit), the Austrian Federal Ministry for Digital and Economic Affairs (bmdw), the Austrian Research Promotion Agency (FFG), the province of Styria (SFG) and partners from industry and academia. The COMET Programme is managed by FFG. Finally, we acknowledge the Big Data Value Association (BDVA), Brussels, Belgium.

Declaration of Interests: MRZ and VB are employees of IBM Research, Haifa, Israel. FM is an employee of Philips Research, Eindhoven, the Netherlands. IS has received funding from multiple funding agencies through a collaborative funding program and declare 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 P.I. All other authors declare no competing interests.

Keywords: Explainable Artificial Intelligence, Systematic literature review, Covid-19

Suggested Citation

Malinverno, Luca and Barros, Vesna and Ghisoni, Francesco and Visonà, Giovanni and Kern, Roman and Nickel, Philip 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, Explainable AI in Biomedical Research: A Systematic Review and Meta-Analysis. Available at SSRN: https://ssrn.com/abstract=4335108

Luca Malinverno

Porini SRL ( email )

Vesna Barros

Porini SRL ( email )

Francesco Ghisoni

Porini SRL ( email )

Giovanni Visonà

Max Planck Institute for Intelligent Systems - Empirical Inference ( email )

Roman Kern

Graz University of Technology - Institute of Interactive Systems and Data Science ( email )

Philip Nickel

Eindhoven University of Technology (TUE) ( email )

PO Box 513
Eindhoven, 5600 MB
Netherlands

Barbara Elvira Ventura

Porini SRL ( email )

Ilija Šimić

Know-Center ( email )

Sarah Stryeck

Research Center Pharmaceutical Engineering GmbH ( email )

Francesca Manni

Philips Research ( email )

Prof. Holstlaan 4
High Tech Campus 34
Eindhoven
Netherlands

Cesar Ferri

Polytechnic University of Valencia ( email )

Camino de Vera, s/n
Valencia, 46022
Spain

Claire Jean-Quartier

Graz University of Technology - Research Data Management ( email )

Laura Genga

Eindhoven University of Technology ( email )

Gabriele Schweikert

University of Dundee - School of Life Sciences ( email )

Mario Lovrić

Porini SRL ( email )

Michal Rosen-Zvi (Contact Author)

University of Haifa - AI for Accelerated Healthcare & Life Sciences Discovery ( email )

Click here to go to TheLancet.com

Paper statistics

Abstract Views
456
Downloads
53
PlumX Metrics